Computer-implemented system, method using same, and computer-readable medium

Abstract

To provide a computer-implemented system.SOLUTION: A computer-implemented system 10 includes: a treatment device 70 including at least a sensor operated by a user while the user executes a treatment plan; and a patient interface 50 suitable to a user for executing the treatment plan by using the treatment device for receiving treatment data including at least a characteristic of the user, suitable measurement information while using the treatment device, at least one characteristic of the treatment device, and at least a mode of the treatment plan, generating treatment information by using the treatment data, sending the treatment information to an assistant interface 94 of a medical provider, communicating with a server for receiving a treatment plan input on the basis of the treatment information by the assistant interface of the medical provider, receiving the treatment plan input including correction to the mode of at least the treatment plan, and being corrected to at least the mode of the treatment plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation patent application of U.S. Provisional Patent Application No. 17 / 021,895, entitled "Telemedicine for Orthopedic Treatment," filed on September 15, 2020, which claims priority to and benefit of U.S. Provisional Patent Application No. 63 / 048,456, entitled "Method and System for Using Sensor Data from Rehabilitation or Exercise Equipment to Treat Patients via Telemedicine," filed on July 6, 2020, and which claims priority to and benefit of U.S. Provisional Patent Application No. 62 / 910,232, entitled "Telemedicine for Orthopedic Treatment," filed on October 3, 2019, which claims priority to and benefit of U.S. Provisional Patent Application No. 17 / 021,895, entitled "Telemedicine for Orthopedic Treatment," filed on January 12, 2021. This application claims priority to and benefit of U.S. patent application Ser. No. 17 / 147,428, entitled "Telemedicine," the entire disclosure of which is incorporated herein by reference.

[0002] This application claims priority to and the benefit of U.S. patent application Ser. No. 16 / 856,985, filed April 23, 2020, entitled "Method and System for Describing and Recommending Optimal Treatment Plans in Adaptive Telemedical or Other Contexts," the entire disclosure of which is incorporated herein by reference.

[0003] This application is a continuation-in-part patent application entitled "Method and System Using Artificial Intelligence to Monitor User Characteristics During a Telemedicine Session," filed on January 12, 2021, which claims priority to and benefit of U.S. Provisional Patent Application No. 63 / 088,657, filed on October 7, 2020, entitled "Method and System Using Artificial Intelligence to Monitor User Characteristics During a Telemedicine Session," and which claims priority to and benefit of U.S. Provisional Patent Application No. 62 / 910,232, filed on October 3, 2019, entitled "Telemedicine for Orthopedic Treatment." This application claims priority to and benefit of U.S. patent application Ser. No. 17 / 147,439, entitled "Synthetic Electromagnetic Wave Propagation System for Electromagnetic Wave Propagation," the entire disclosure of which is incorporated herein by reference.

[0004] This application is a continuation-in-part patent application claiming priority to and benefit of U.S. Provisional Patent Application No. 63 / 104,716, entitled "Method and System for Using Virtual Avatars Associated with Medical Professionals During Exercise Sessions," filed October 23, 2020, which claims priority to and benefit of U.S. Provisional Patent Application No. 17 / 021,895, entitled "Telemedicine for Orthopedic Treatment," filed September 15, 2020, which claims priority to and benefit of U.S. Provisional Patent Application No. 62 / 910,232, entitled "Telemedicine for Orthopedic Treatment," filed October 3, 2019, which claims priority to and benefit of U.S. Provisional Patent Application No. This application claims priority to and benefit of U.S. patent application Ser. No. 17 / 147,211, entitled "Synthetic Electromagnetic Wave Propagation System for Electromagnetic Waves," the entire disclosure of which is incorporated herein by reference. [Background technology]

[0005] Remote medical assistance, or telemedicine, can assist a patient in implementing various aspects of a rehabilitation regimen for a body part. The patient can use a patient interface that communicates with the assistant interface to receive remote medical assistance via voice and / or audio-visual communication. Summary of the Invention [Means for solving the problem]

[0006] The computer-implemented system of the present invention comprises: an electromechanical machine including at least one pedal adapted to be operated by a user while the user is performing a treatment plan; a computing device of the user suitable for the user executing the treatment plan using the electromechanical machine, the computing device being configured to receive treatment data including at least one characteristic of the user, measurement information suitable for the user while the user is using the electromechanical machine, at least one characteristic of the electromechanical machine, and at least one aspect of the treatment plan, generate treatment information using the treatment data, send the treatment information to a computing device of a healthcare provider, communicate at the computing device of the healthcare provider with an interface configured to receive treatment plan input based on the treatment information, and modify at least one aspect of the treatment plan upon receiving the treatment plan input including modifications to at least one aspect of the treatment plan; The present invention is characterized by having the following.

[0007] The computer-implemented system may be such that the user's computing device is configured to further control the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine.

[0008] The computer-implemented system may be such that the user's computing device is further configured to control the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine during a remote treatment session.

[0009] The computer-implemented system may be such that the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

[0010] The computer-implemented system may be such that at least some of the therapy data corresponds to at least some sensor data from a sensor associated with the electromechanical machine.

[0011] The computer-implemented system may be such that at least some of the therapy data corresponds to at least some sensor data from sensors associated with a wearable device worn by the user while the user is using the electromechanical machine.

[0012] The method of the present invention is suitable for a user performing a treatment plan using an electromechanical machine, and includes receiving treatment data including at least one characteristic of the user, measurement information suitable for the user while the user is using the electromechanical machine, at least one characteristic of the electromechanical machine, and at least one aspect of the treatment plan; generating treatment information using the treatment data; sending said treatment information to a healthcare provider's computing device; communicating with an interface at the computing device of the healthcare provider configured to receive treatment plan input based on the treatment information; and modifying at least one aspect of the treatment plan upon receiving the treatment plan input including a modification to at least one aspect of the treatment plan; That is it.

[0013] The method may further comprise controlling the electromechanical machine while the user is using the electromechanical machine based on at least one modified aspect of the treatment plan.

[0014] The method may further comprise controlling the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine during a remote treatment session.

[0015] The method may be such that the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

[0016] The method may be such that at least some of the therapy data corresponds to at least some sensor data from a sensor associated with the electromechanical machine.

[0017] The method may be such that at least some of the therapy data corresponds to at least some sensor data from sensors associated with a wearable device worn by the user while the user is using the electromechanical machine.

[0018] The method may further comprise receiving subsequent treatment data appropriate for the user while the user is implementing the treatment plan using the electromechanical machine.

[0019] The method may further modify at least one modified aspect of the treatment plan in response to receiving a subsequent treatment plan input based on at least one of the treatment data and the subsequent treatment data, the subsequent treatment plan input including at least one further modification of the at least one modified aspect of the treatment plan.

[0020] The computer-readable medium of the present invention comprises: A tangible, non-transitory computer-readable medium storing instructions that, for execution, cause a processing device to: receiving treatment data suitable for a user executing a treatment plan using an electromechanical machine, the treatment data including at least one characteristic of the user, measurement information suitable for the user while the user is using the electromechanical machine, at least one characteristic of the electromechanical machine, and at least one aspect of the treatment plan; generating treatment information using the treatment data; causing said treatment information to be transmitted to a healthcare provider's computing device; communicating at the healthcare provider's computing device with an interface configured to receive treatment plan input based on the treatment information; and and modifying at least one aspect of the treatment plan upon receiving the treatment plan input including a modification to at least one aspect of the treatment plan. That is it.

[0021] The computer-readable medium may be such that the processing device is further configured to control the electromechanical machine based on modified aspects of at least one of the modified treatment plans while the user is using the electromechanical machine.

[0022] The computer-readable medium may be one in which the processing device is configured to further control the electromechanical machine based on modified aspects of at least one of the treatment plans while the user is using the electromechanical machine during a remote treatment session.

[0023] The computer-readable medium may be such that the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

[0024] The computer readable medium may be such that at least some of the therapy data corresponds to at least some sensor data from a sensor associated with the electromechanical machine.

[0025] The computer-readable medium may be such that at least some of the therapy data corresponds to at least some sensor data from sensors associated with a wearable device worn by the user while the user is using the electromechanical machine.

[0026] More specifically, aspects of the disclosed embodiments include a method that includes receiving treatment data related to a user implementing a treatment plan using a treatment device. The treatment data includes at least one of characteristics of the user, measurement information related to the user while the user uses the treatment device, characteristics of the treatment device, and the treatment plan. The method also includes generating treatment information using the treatment data and writing the treatment information to an associated memory for access at a healthcare provider's computing device. The method also includes communicating with an interface at the healthcare provider's computing device, the interface configured to receive treatment plan input, and modifying the treatment plan in response to receiving the treatment plan input including at least one modification to the treatment plan.

[0027] Aspects of the disclosed embodiments include a computer-implemented system including a therapeutic device configured to be operated by a patient while performing an exercise session and a patient interface configured to receive a virtual avatar. The patient interface includes an output device configured to present the virtual avatar. The virtual avatar guides the patient through the exercise session using a virtual representation of the therapeutic device. The virtual avatar is associated with a healthcare professional. The computer-implemented system includes a server computing device configured to: provide a virtual avatar of the patient to the patient interface; receive a message from the patient interface regarding a trigger event, the message including a severity level of the trigger event; determine whether the severity level of the trigger event exceeds a threshold severity level; and, in response to determining that the severity level of the trigger event exceeds the threshold severity level, replace the presentation of the virtual avatar on the patient interface with a presentation of a multimedia feed from the healthcare professional's computing device.

[0028] Aspects of the disclosed embodiments include a method for providing an optimal treatment plan for use with a treatment device by an artificial intelligence engine, the method including receiving, from a data source, clinical information regarding results of administering a particular treatment plan to people with particular characteristics using the treatment device, the clinical information having a first data format, converting a portion of the clinical information from the first data format into a medical description language used by the artificial intelligence engine, determining an optimal treatment plan for the patient to follow to achieve a desired outcome using the treatment device based on the portion of the clinical information described in the medical description language and a plurality of characteristics related to the patient, and providing the optimal treatment plan for presentation on a computing device of a medical professional.

[0029] Aspects of the disclosed embodiments include a method for providing an optimal treatment plan for use with a treatment device by an artificial intelligence engine, the method including receiving, from a data source, clinical information regarding results of administering a particular treatment plan to people with particular characteristics using the treatment device, the clinical information having a first data format, converting a portion of the clinical information from the first data format into a medical description language used by the artificial intelligence engine, determining an optimal treatment plan for the patient to follow to achieve a desired outcome using the treatment device based on the portion of the clinical information described in the medical description language and a plurality of characteristics related to the patient, and providing the optimal treatment plan for presentation on a computing device of a medical professional.

[0030] Another aspect of the disclosed embodiments includes a system including a processing device and a memory communicatively coupled to the processing device and capable of storing instructions, the processing device executing the instructions to perform any of the methods, operations, or steps described herein.

[0031] Another aspect of the disclosed embodiments includes a tangible, non-transitory computer-readable medium storing instructions that, when executed, cause a processing device to perform any of the methods, operations, or steps described herein. [Effects of the Invention]

[0032] The present disclosure is best understood from the following detailed description when read in conjunction with the accompanying drawings. It should be noted that, according to common practice, the various features of the drawings are not to scale. Conversely, the dimensions of the various features have been arbitrarily increased or decreased for clarity. [Brief explanation of the drawings]

[0033] [Figure 1] 1 illustrates generally a block diagram of one embodiment of a computer-implemented system for managing a treatment plan, in accordance with the principles of the present disclosure. [Figure 2] 1 generally illustrates a perspective view of one embodiment of a treatment device according to the principles of the present disclosure; [Figure 3] 3 generally illustrates a perspective view of a pedal of the treatment device of FIG. 2 in accordance with the principles of the present disclosure. [Figure 4] 3 generally illustrates a perspective view of a person using the treatment device of FIG. 2 in accordance with the principles of the present disclosure. [Figure 5] 1 illustrates generally one exemplary embodiment of an overview display of an assistant interface in accordance with the principles of the present disclosure. [Figure 6] 1 illustrates generally an exemplary block diagram for training a machine learning model to output a treatment plan for a patient based on data about the patient, in accordance with the principles of the present disclosure. [Figure 7] 1 illustrates generally one embodiment of an overview display of an assistant interface presenting recommended and ruled-out treatment plans in real time during a telemedicine session in accordance with the principles of the present disclosure. [Figure 8]1 illustrates generally one embodiment of an overview display of an assistant interface presenting a recommended treatment plan that has changed as a result of changes in patient data in real time during a telemedicine session in accordance with the principles of the present disclosure. [Figure 9] FIG. 3 is a flow diagram generally illustrating a method for modifying a patient's treatment plan based on treatment data received while a user is using the treatment device of FIG. 2, and controlling at least one treatment device based on the modification, in accordance with the principles of the present disclosure. [Figure 10] FIG. 10 is a flow diagram generally illustrating an alternative method for modifying a patient's treatment plan based on treatment data received while a user is using the treatment device of FIG. 2, and controlling at least one treatment device based on the modification, in accordance with the principles of the present disclosure. [Figure 11] FIG. 10 is a flow diagram generally illustrating an alternative method for modifying a patient's treatment plan based on treatment data received while a user is using the treatment device of FIG. 2, and controlling at least one treatment device based on the modification, in accordance with the principles of the present disclosure. [Figure 12] 1 illustrates generally an exemplary computer system in accordance with the principles of the present disclosure. [Figure 13] 1 shows a block diagram of one embodiment of a computer-implemented system for managing a treatment plan according to the present disclosure. [Figure 14] 1 shows a perspective view of one embodiment of a treatment device according to the present disclosure. [Figure 15] 15 shows a perspective view of a pedal of the treatment device of FIG. 14 in accordance with the present disclosure. [Figure 16] 15 shows a perspective view of a person using the treatment device of FIG. 14 in accordance with the present disclosure. [Figure 17] 1 illustrates an exemplary embodiment of an overview display of an assistant interface according to the present disclosure. [Figure 18] 1 illustrates an exemplary embodiment of an overview display of an assistant interface that presents recommended optimal and excluded treatment plans in real time during a telemedicine session according to the present disclosure. [Figure 19] 1 illustrates an exemplary embodiment of a server that converts clinical information into a medical description language for processing by an artificial intelligence engine, according to the present disclosure. [Figure 20] 1 illustrates an exemplary embodiment of a method for recommending an optimal treatment plan according to the present disclosure. [Figure 21] 1 illustrates an exemplary embodiment of a method for converting clinical information into a medical description language according to the present disclosure. [Figure 22] 1 illustrates an exemplary computer system according to the present disclosure. [Figure 23] 1 illustrates generally a block diagram of one embodiment of a computer-implemented system for managing a treatment plan, in accordance with the principles of the present disclosure. [Figure 24] 1 generally illustrates a perspective view of one embodiment of a treatment device according to the principles of the present disclosure; [Figure 25] FIG. 25 generally illustrates a perspective view of a pedal of the treatment device of FIG. 24, in accordance with the principles of the present disclosure. [Figure 26] 25 generally illustrates a perspective view of a person using the treatment device of FIG. 24 in accordance with the principles of the present disclosure. [Figure 27] 1 illustrates generally one exemplary embodiment of an overview display of an assistant interface in accordance with the principles of the present disclosure. [Figure 28] 1 illustrates generally an exemplary block diagram for training a machine learning model to output a treatment plan for a patient based on data about the patient, in accordance with the principles of the present disclosure. [Figure 29] 1 illustrates generally one embodiment of an overview display of an assistant interface presenting recommended and excluded treatment plans in real time during a telemedicine session in accordance with the principles of the present disclosure. [Figure 30] 1 illustrates generally one embodiment of an overview display of an assistant interface presenting a recommended treatment plan that has changed as a result of changes in patient data in real time during a telemedicine session in accordance with the principles of the present disclosure. [Figure 31]FIG. 25 is a flow diagram generally illustrating a method for monitoring characteristics of a user while the user uses the treatment device of FIG. 24 based on treatment data received while the user uses the treatment device, in accordance with the principles of the present disclosure. [Figure 32] FIG. 26 is a flow diagram generally illustrating an alternative method for monitoring characteristics of a user while the user uses the treatment device of FIG. 24 based on treatment data received while the user uses the treatment device, in accordance with the principles of the present disclosure. [Figure 33] FIG. 26 is a flow diagram generally illustrating an alternative method for monitoring characteristics of a user while the user uses the treatment device of FIG. 24 based on treatment data received while the user uses the treatment device, in accordance with the principles of the present disclosure. [Figure 34] FIG. 1 is a flow diagram generally illustrating a method for receiving a selection of an optimal treatment plan and controlling a treatment device while a patient is using the treatment device based on the optimal treatment plan, according to the present disclosure. [Figure 35] 1 illustrates generally a computer system in accordance with the principles of the present disclosure. [Figure 36] 1 shows a block diagram of one embodiment of a computer-implemented system for managing a treatment plan according to the present disclosure. [Figure 37] 1 shows a perspective view of one embodiment of a treatment device according to the present disclosure. [Figure 38] 38 shows a perspective view of a pedal of the treatment device of FIG. 37 in accordance with the present disclosure. [Figure 39] 38 shows a perspective view of a person using the treatment device of FIG. 37 in accordance with the present disclosure. [Figure 40] 1 illustrates an exemplary embodiment of an overview display of an assistant interface according to the present disclosure. [Figure 41] FIG. 1 illustrates an exemplary block diagram for training a machine learning model to output a treatment plan for a patient based on data about the patient, according to the present disclosure. [Figure 42] 1 illustrates one embodiment of an overview display of a patient interface presenting a virtual avatar guiding a patient through an exercise session according to the present disclosure. [Figure 43] 1 illustrates one embodiment of an overview display of an assistant interface that receives notifications about a patient and allows an assistant to initiate a telemedicine session in real time according to the present disclosure. [Figure 44] 1 illustrates one embodiment of a patient interface overview display that presents a feed of a healthcare professional replaced by a virtual avatar in real time during a telemedicine session according to the present disclosure. [Figure 45] 1 illustrates an exemplary embodiment of a method for replacing a virtual avatar with a healthcare worker's feed based on a trigger event occurring, according to the present disclosure. [Figure 46] 1 illustrates an exemplary embodiment of a method for providing a virtual avatar according to the present disclosure. [Figure 47] 1 illustrates an exemplary computer system according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0034] Notation and name Various terms are used to refer to specific system components. Different companies may refer to components by different names, and this document does not intend to distinguish between components that differ in name but do not function. In the following discussion and claims, the terms "including" and "comprising" are used in an open-ended manner and, therefore, should be interpreted to mean "including, but not limited to." Also, the terms "couple" or "couples" are intended to mean either an indirect connection or a direct connection. Thus, when a first device couples to a second device, the connection may be via a direct connection or an indirect connection via other devices and connections.

[0035] The terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. As used herein, the singular forms "a," "an," and "the" may be intended to include the plural forms unless the context clearly indicates otherwise. The method steps, processes, and acts described herein should not be construed as necessarily requiring their performance in the particular order discussed or illustrated, unless specifically identified as such. It is also understood that additional or alternative steps may be employed.

[0036] Terms such as first, second, and third may be used herein to describe various elements, components, regions, layers, and / or sections, but these elements, components, regions, layers, and / or sections should not be limited by these terms. These terms may be used only to distinguish one element, component, region, layer, or section from another region, layer, or section. Terms such as "first," "second," and other numerical terms, when used herein, do not imply a permutation or order unless explicitly indicated by context. Thus, a first element, component, region, layer, or section discussed below could be referred to as a second element, component, region, layer, or section without departing from the teachings of the exemplary embodiments. When used in conjunction with a list of items, the phrase "at least one of" means that different combinations of one or more of the listed items may be used, and that only one item in the list may be required. For example, "at least one of: A, B, and C" includes any of the following combinations: A, B, C, A and B, A and C, B and C, and A and B and C. As another example, the phrase "one or more," when used in conjunction with a list of items, means that there can be one item or any suitable number of items greater than one.

[0037] Spatially relative terms such as "inner," "outer," "below," "lower," "lower," "upper," "upper," "top," "lowest," and the like may be used herein. These spatially relative terms may be used for ease of description to describe the relationship of one element or feature to another element or feature illustrated in the figures. Spatially relative terms may also be intended to encompass different orientations or operations of the device in use in addition to the orientation depicted in the figures. For example, if the device in the figures were turned over, elements described as "below" or "below" other elements or features would be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device may be oriented differently (rotated 90 degrees or to another orientation), and the spatially relative descriptions used herein may be interpreted accordingly.

[0038] A "treatment plan" can include one or more treatment protocols, each of which includes one or more treatment sessions. Each treatment session includes several session durations, each of which includes specific exercises for treating a patient's body part. For example, a treatment plan for postoperative rehabilitation after knee surgery may include an initial treatment protocol with two stretching sessions per day for the first three days after surgery and a more intensive treatment protocol with active exercise sessions performed four times per day starting on the fourth day after surgery. The treatment plan may also include information regarding medical procedures to be performed on the patient, the patient's treatment protocol using a therapeutic device, the patient's dietary regimen, the patient's medication regimen, the patient's sleep regimen, additional regimens, or any combination thereof. The treatment plan may also include one or more training protocols, such as a strength training protocol, a range of motion training protocol, a cardiovascular training protocol, an endurance training protocol, etc. Each training protocol can include one or more training sessions with several training session durations, each of which includes specific exercises targeting one or more of strength training, range of motion training, cardiovascular training, endurance training, etc.

[0039] Terms such as telemedicine, telehealth, telemed, teletherapeutic, telemedicine, and remote medicine may be used interchangeably herein.

[0040] The term "augmented reality" may include user experiences that include one or more of augmented reality, virtual reality, mixed reality, immersive reality, or a combination of the above (e.g., immersive augmented reality, mixed augmented reality, virtual and augmented immersive reality, etc.).

[0041] The term "augmented reality" may refer, without limitation, to an interactive user experience that provides an enhanced environment that combines elements of the real-world environment with computer-generated components that are perceptible by the user.

[0042] The term "virtual reality" may refer, without limitation, to an interactive simulated user experience that provides an enhanced environment perceivable by a user, which may be similar to or different from a real-world environment.

[0043] The term "mixed reality" may refer to an interactive user experience that combines aspects of augmented reality with aspects of virtual reality to provide a mixed reality environment perceivable by the user.

[0044] The term "immersive reality" may refer to an interactive simulated user experience that uses virtual and / or augmented reality images, sounds, and other stimuli that immerse a user in the interactive simulated experience to a certain possible degree (e.g., partial immersion or full immersion). For example, in some embodiments, to a certain possible degree, a user experiences one or more aspects of the immersive reality in a manner similar to how a user would normally experience a corresponding aspect of the real world. Additionally or alternatively, the immersive reality experience may include actors, narrative elements, a theme (e.g., an entertainment theme or other suitable theme), and / or other suitable characteristics of the elements.

[0045] The term "body halo" may refer to one or more hardware components, where such one or more components may include one or more platforms, one or more body supports or cages, one or more chairs or seats, one or more back supports or back engagement mechanisms, one or more leg or foot engagement mechanisms, one or more arm or hand engagement mechanisms, one or more head engagement mechanisms, other suitable hardware components, or combinations thereof.

[0046] As used herein, the term "enhanced environment" may refer to the entire enriched environment, at least one aspect of the enriched environment, two or more aspects of the enriched environment, or any suitable number of aspects of the enriched environment.

[0047] As used herein, the term "threshold" and / or the term "range" may include one or more values expressed as a percentage, an absolute value, a unit of measure, a difference value, a numerical amount, or other suitable representation of one or more values.

[0048] The term "optimal treatment plan" may refer to optimizing a treatment plan based on a particular parameter or combination of two or more parameters, such as, but not limited to, the amount of monetary value generated by the treatment plan and / or billing sequence, measured in absolute terms in dollars or another currency, net present value (NPV) or any other measure, patient outcomes resulting from the treatment plan and / or billing sequence, fees paid to healthcare providers, patient payment plans to pay off amounts due or portions thereof, reimbursement plans, amount of revenue to be paid to insurance or third party providers, profits, or other monetary value amounts, or any combination thereof.

[0049] Real-time may refer to two seconds or less. Near real-time may refer to any interaction short enough in duration to allow two individuals to engage in a dialogue through such a user interface, which will generally be less than ten seconds but more than two seconds.

[0050] Any of the systems and methods described in this disclosure may be used in connection with rehabilitation, which may include cardiac rehabilitation, stroke rehabilitation, multiple sclerosis, Parkinson's disease, myasthenia gravis, Alzheimer's disease, any other neurodegenerative or neuromuscular disease, brain injury, spinal cord injury or disease, joint injury or disease, etc. Rehabilitation may further involve muscle contraction to improve blood and lymph flow, engage the brain and nervous system to control and affect traumatized areas to increase the rate of healing, reverse or reduce pain (including joint and muscle pain), reverse or reduce stiffness, restore range of motion, promote cardiovascular function, stimulate the release of pain-blocking hormones, or promote oxygen-rich blood flow to help feel an overall state of well-being. Rehabilitation may be provided to individuals of average height who are in fairly good physical condition without substantial deformities, as well as to individuals who more typically require rehabilitation, such as those who are elderly, obese, subject to a disease process, injured, and / or have severely limited range of motion. Unless otherwise specified, rehabilitation should be understood to include pre-operative rehabilitation (also referred to as "prehabilitation" or "prehab"). Pre-operative rehabilitation may be used as a preventative measure or as a pre-surgical or pre-therapeutic measure. Pre-operative rehabilitation may include, but is not limited to, any action performed by or on a patient (or directed to be performed by or on a patient, including but not limited to, remotely or at a distance via telemedicine) to prevent or reduce the risk of injury (e.g., before an injury occurs), improve recovery time after surgery, improve strength after surgery, or any of the above related to any non-surgical clinical treatment plan undertaken for the purpose of improving or mitigating an injury, impairment, or other negative consequence of any surgical or non-surgical procedure on any external or internal part of the patient's body.For example, a mastectomy may require preoperative rehabilitation to strengthen muscles or muscle groups directly or indirectly affected by the mastectomy. As a further non-limiting example, removal of an intestinal tumor, hernia repair, open-heart surgery, or other procedures performed on internal organs or structures, whether repairing, removing, or treating those organs or structures, may require cutting, dissecting, and / or injuring numerous muscles and muscle groups in or around the skull or face, abdomen, ribs, and / or chest cavity, as well as all joints and appendages. Preoperative rehabilitation can improve a patient's recovery rate, quality of life, pain level, and the like in all of these procedures. In one embodiment of preoperative rehabilitation, preoperative or non-preoperative treatment may include one or more exercise sets for the patient to perform prior to such procedure or treatment. One or more exercise sets may be required to accommodate elective surgery, such as a knee replacement. A patient may prepare an area of their body for a surgical procedure by performing one or more exercise sets, thereby strengthening muscle groups, improving existing muscle memory, reducing pain, reducing stiffness, establishing new muscle memory, increasing mobility (i.e., improving range of motion), improving blood flow, etc.

[0051] The following discussion is directed to various embodiments of the present disclosure. While one or more of these embodiments may be preferred, the disclosed embodiments should not be construed or otherwise used as limiting the scope of the present disclosure, including the claims. In addition, those skilled in the art will understand that the following description has broad applicability, and the discussion of any embodiment is meant only to exemplify that embodiment and is not intended to imply that the scope of the present disclosure, including the claims, is limited to that embodiment.

[0052] Determining a treatment plan for a patient with specific characteristics (e.g., vital signs or other measurements, performance, demographic, geographic, diagnostic, measurement-based or test-based, medical history, etiological, cohort-related, differential diagnosis, surgical, physical therapy, pharmacological, and recommended other treatments, etc.) can be a technically challenging problem. For example, a large amount of information may be considered when determining a treatment plan, which can lead to inefficiency and inaccuracy in the treatment plan selection process. In a rehabilitation setting, some of the large amount of information considered may include patient characteristics, such as personal information, performance information, and measurement information. Personal information may include demographic, psychological, or other information, such as age, weight, sex, height, body mass index, medical conditions, family medical history, injuries, medical procedures, prescribed medications, or some combination thereof. Performance information may include, for example, elapsed time using a treatment device, amount of force exerted on a portion of the treatment device, range of motion achieved with the treatment device, speed of movement of a portion of the treatment device, an indication of multiple pain levels using the treatment device, or some combination thereof. The measured information may include, for example, vital signs, respiratory rate, heart rate, body temperature, blood pressure, or some combination thereof. It may be desirable to process the characteristics of multiple patients, the treatment plans implemented for those patients, and the results of those treatment plans.

[0053] Yet another technical challenge may involve treating a patient remotely from a location different from where the patient is located via a computing device during a telemedicine or telehealth session. An additional technical challenge is controlling or enabling control of a treatment device used by a patient from a location different from where the patient is located. Often, when a patient undergoes rehabilitation surgery (e.g., knee surgery), a healthcare provider may prescribe the patient a treatment device to be used to implement the treatment protocol at the patient's home or any mobile or temporary location. A healthcare provider may refer to a doctor, physician assistant, nurse, chiropractor, dentist, physical therapist, acupuncturist, physical trainer, coach, personal trainer, etc. A healthcare provider may refer to any person with a credential, license, position, etc. in the fields of medicine, physical therapy, rehabilitation, etc.

[0054] When the healthcare provider is located at a different location than the patient and the treatment device, it can be technically difficult for the healthcare provider to use the treatment device to monitor the patient's actual progress (as opposed to relying on the patient's word about their progress), modify the treatment plan according to the patient's progress, adapt the treatment device to the patient's personal characteristics as the patient implements the treatment plan, etc.

[0055] Therefore, systems and methods such as those described herein that use sensor data to modify a treatment plan and / or adapt a treatment device while a patient is implementing the treatment plan using the treatment device may be desirable.

[0056] In some embodiments, the systems and methods described herein can be configured to receive therapy data about a user while the user is performing a therapy plan using a therapy device. The user can include a patient-user or person performing various exercises using a therapy device. The therapy plan can correspond to a rehabilitation therapy plan, a pre-operative rehabilitation therapy plan, an exercise therapy plan, or other suitable therapy plan. The therapy data can include various characteristics of the user, various measurement information about the user while the user is using the therapy device, various characteristics of the therapy device, the therapy plan, other suitable data, or a combination thereof.

[0057] In some embodiments, at least a portion of the treatment data may correspond to sensor data from sensors configured to sense various characteristics of the treatment device and / or measurements of the user while the user is implementing the treatment plan using the treatment device. Additionally or alternatively, at least a portion of the treatment data may correspond to sensor data from sensors associated with the wearable device configured to sense measurements of the user while the user is implementing the treatment plan using the treatment device.

[0058] The various characteristics of the therapy device may include one or more settings of the therapy device, the current number of revolutions per time period (e.g., minute, etc.) of a rotating member (e.g., wheel, etc.) of the therapy device, a resistance setting of the therapy device, other suitable characteristics of the therapy device, or a combination thereof. The measurement information may include one or more vital signs of the user, the user's respiratory rate, the user's heart rate, the user's temperature, the user's blood pressure, other suitable measurement information of the user, or a combination thereof.

[0059] In some embodiments, the systems and methods described herein may be configured to generate treatment information using the treatment data. The treatment information may include a summary of the user's implementation of the treatment plan while using the treatment device formatted so that the treatment data is presentable on a computing device of a healthcare provider or healthcare worker responsible for implementing the treatment plan by the user. The terms "healthcare provider" and "healthcare worker" may be used interchangeably herein. A healthcare provider or healthcare worker may include a medical professional (e.g., a doctor, nurse, therapist, etc.), an exercise professional (e.g., a coach, trainer, nutritionist, etc.), or another professional who shares at least one of medical attributes and exercise attributes (e.g., an exercise physiologist, physical therapist, occupational therapist, etc.). As used herein, without limitation to the foregoing, a healthcare provider or healthcare worker may be a human, a robot, a virtual assistant, a virtual assistant in virtual reality and / or augmented reality, or an artificial intelligence entity including a software program, integrated software and hardware, or hardware alone.

[0060] The systems and methods described herein may be configured to write treatment information to an associated memory for access at a healthcare provider's computing device and / or to provide the treatment information at the healthcare provider's computing device. For example, the systems and methods described herein may be configured to provide the treatment information to an interface configured to present the treatment information to a healthcare provider. The interface may include a graphical user interface configured to provide the treatment information and receive input from the healthcare provider. The interface may include one or more input fields, such as a text input field, a drop-down selection input field, a radio button input field, a virtual switch input field, a virtual lever input field, an input field that is voice-activated, haptically, tactilely, biometrically, or otherwise activated and / or driven, other suitable input fields, or a combination thereof.

[0061] In some embodiments, a healthcare provider may review the treatment information and determine whether to modify one or more characteristics of the treatment plan and / or treatment device. For example, the healthcare provider may review the treatment information and compare it to the treatment plan being implemented by the user.

[0062] The healthcare provider may compare (i) expected information about the user while the user is using the therapeutic device to implement the treatment plan with (ii) measured information about the user while the user is using the therapeutic device to implement the treatment plan (e.g., as indicated by the treatment information). The expected information may include one or more vital signs of the user, the user's respiratory rate, the user's heart rate, the user's body temperature, the user's blood pressure, other suitable information about the user, or a combination thereof. The healthcare provider may determine that the treatment plan is having the desired effect if one or more portions or parts of the measured information are within an acceptable range associated with one or more corresponding portions or parts of the expected information. Conversely, the healthcare provider may determine that the treatment plan is not having the desired effect if one or more portions or parts of the measured information are outside an acceptable range associated with one or more corresponding portions or parts of the expected information.

[0063] For example, the healthcare provider may determine whether blood pressure values (e.g., systolic pressure, diastolic pressure, and / or pulse pressure) corresponding to a user (e.g., indicated by the measurement information) while the user uses the therapeutic device are within an acceptable range (e.g., plus or minus 1%, plus or minus 5%, or any suitable range) of expected blood pressure values indicated by the predictive information. The healthcare provider may determine that the treatment plan is having the desired effect if blood pressure values corresponding to a user while the user uses the therapeutic device are within the expected range of blood pressure values. Conversely, the healthcare provider may determine that the treatment plan is not having the desired effect if blood pressure values corresponding to a user while the user uses the therapeutic device are outside the expected range of blood pressure values.

[0064] In some embodiments, the healthcare provider may compare the expected characteristics of the treatment device while the user is using the treatment device to implement the treatment plan with the characteristics of the treatment device indicated by the treatment information. For example, the healthcare provider may compare the expected resistance setting of the treatment device with the actual resistance setting of the treatment device indicated by the treatment information. The healthcare provider may determine that the user is properly implementing the treatment plan if the actual characteristics of the treatment device indicated by the treatment information are within a corresponding range of the expected characteristics of the treatment device. Conversely, the healthcare provider may determine that the user is not properly implementing the treatment plan if the actual characteristics of the treatment device indicated by the treatment information are outside a corresponding range of the expected characteristics of the treatment device.

[0065] If the healthcare provider determines that the treatment information indicates that the user is properly implementing the treatment plan and / or that the treatment plan is having the desired effect, the healthcare provider may decide not to modify the treatment plan or one or more characteristics of the treatment device. Conversely, if, while the user is implementing the treatment plan using the treatment device, the healthcare provider determines that the treatment information indicates that the user is not, or has not been implementing the treatment plan properly and / or that the treatment plan is not, or has not been having the desired effect, the healthcare provider may decide to modify the treatment plan and / or one or more characteristics of the treatment device.

[0066] In some embodiments, if a healthcare provider decides to modify the treatment plan and / or one or more characteristics of the treatment device, the healthcare provider may interact with the interface to provide a treatment plan input indicating one or more modifications to the treatment plan and / or to one or more characteristics of the treatment device. For example, the healthcare provider may use the interface to provide an input indicating an increase or decrease in a resistance setting of the treatment device, or other suitable modifications to one or more characteristics of the treatment device. Additionally or alternatively, the healthcare provider may use the interface to provide an input indicating a modification to the treatment plan. For example, the healthcare provider may use the interface to provide an input indicating an increase or decrease in the amount of time a user is required to use the treatment device according to the treatment plan, or other suitable modifications to the treatment plan.

[0067] In some embodiments, the systems and methods described herein may be configured to modify the treatment plan based on one or more modifications indicated by the treatment plan input. Additionally or alternatively, the systems and methods described herein may be configured to modify one or more characteristics of the treatment device based on at least one modified aspect of the treatment plan and / or the treatment plan input. For example, the treatment plan input may indicate that one or more characteristics of the treatment device should be modified, and / or the treatment plan may require or indicate that the user should adjust the treatment device to achieve the desired results of the modified treatment plan.

[0068] In some embodiments, the systems and methods described herein may be configured to receive subsequent treatment data about a user while the user is implementing a treatment plan using a treatment device. For example, after a healthcare provider provides input to modify a treatment plan and / or control one or more characteristics of a treatment device, the user may continue to implement the modified treatment plan using the treatment device. The subsequent treatment data may correspond to treatment data generated while the user is implementing the modified treatment plan using the treatment device. In some embodiments, the subsequent treatment data may correspond to treatment data generated while the user continues to implement a treatment plan using a treatment device after a healthcare provider receives treatment information and decides not to modify the treatment plan and / or control one or more characteristics of the treatment device.

[0069] Based on subsequent treatment plan input received from the healthcare provider's computing device, the systems and methods described herein may be configured to further modify the treatment plan and / or control one or more characteristics of the treatment device. The subsequent treatment plan input may correspond to input provided by the healthcare provider at the interface in response to receiving and / or reviewing subsequent treatment information corresponding to the subsequent treatment data. It should be understood that the systems and methods described herein may be configured to continuously and / or periodically provide treatment information to the healthcare provider's computing device based on treatment data continuously and / or periodically received from the sensors described herein or other suitable sources.

[0070] A healthcare provider may continuously or periodically receive and / or review the therapy information while the user is implementing the therapy plan using the therapy device. Based on one or more trends indicated by the continuously and / or periodically received therapy information, the healthcare provider may determine whether to modify the therapy plan and / or control one or more characteristics of the therapy device. For example, the one or more trends may indicate an increase in heart rate or other suitable trend that indicates the user is not properly implementing the therapy plan and / or that the user's implementation of the therapy plan is not having the desired effect.

[0071] In some embodiments, the systems and methods described herein may be configured to use artificial intelligence and / or machine learning to assign patients to cohorts and dynamically control treatment devices based on the assignments during adaptive telemedicine sessions. In some embodiments, multiple treatment devices may be provided to a patient. The treatment devices may be used by the patient to implement a treatment plan at any suitable location, including the patient's home, gym, rehabilitation center, hospital, or permanent or temporary residence.

[0072] In some embodiments, the treatment device may be communicatively coupled to a server. Patient characteristics, including treatment data, may be collected before, during, and / or after a patient implements a treatment plan. For example, personal information, performance information, and measurement information may be collected before, during, and / or after a person implements a treatment plan. Results of each exercise implementation (e.g., improved performance or reduced performance) may be collected from the treatment device throughout the treatment plan and after the treatment plan is implemented. Treatment device parameters, settings, configurations, etc. (e.g., pedal position, amount of resistance, etc.) may be collected before, during, and / or after a treatment plan is implemented.

[0073] Each patient characteristic, each outcome, and each parameter, setting, configuration, etc. can be time-stamped and correlated to a particular step in the treatment plan. Such technology may make it possible to determine which steps in the treatment plan lead to a desired outcome (e.g., improved strength, range of motion, etc.) and which steps lead to reduced return (e.g., continuing to exercise after 3 minutes actually delays or harms recovery).

[0074] Data may be collected from the treatment device and / or any suitable computing device (e.g., a computing device into which personal information is entered, such as a computing device interface described herein, a clinician interface, a patient interface, etc.) over time as the patient uses the treatment device to implement various treatment regimens. Data that may be collected may include patient characteristics, treatment regimens implemented by the patient, results of the treatment regimens, any of the data described herein, any other suitable data, or a combination thereof.

[0075] In some embodiments, the data can be processed to group specific people into cohorts. People can be grouped by those with specific or selected similar characteristics, treatment plans, and results of implementing the treatment plans. For example, athletes without medical conditions who implement a treatment plan (e.g., using a treatment device 30 minutes per day, 5 times per week for 3 weeks) and fully recover can be grouped into a first cohort. Elderly people classified as obese who implement a treatment plan (e.g., using a treatment plan 10 minutes per day, 3 times per week for 4 weeks) and improve their range of motion by 75 percent can be grouped into a second cohort.

[0076] In some embodiments, the artificial intelligence engine may include one or more machine learning models trained using the cohort. For example, the one or more machine learning models may be trained to receive input of characteristics of a new patient and to output a treatment plan for the patient that will produce a desired outcome. The machine learning models may match patterns between the characteristics of the new patient and at least one of the patients included in the particular cohort. If a pattern is matched, the machine learning models may assign the new patient to the particular cohort and select a treatment plan associated with the at least one patient. The artificial intelligence engine may be configured to remotely control the treatment device based on the treatment plan while the new patient uses the treatment device to implement the treatment plan.

[0077] As can be appreciated, the characteristics of a new patient (e.g., a new user) may change as the new patient uses a treatment device to implement a treatment plan. For example, the patient's performance may improve faster than expected for people in the cohort to which the new patient is currently assigned. Thus, a machine learning model can be trained to dynamically reassign the new patient to a different cohort containing people with similar characteristics to the new patient's currently changed characteristics based on the changed characteristics. For example, a clinically obese patient may lose weight and no longer meet the weight criteria for the initial cohort, resulting in the patient's weight being reassigned to a different cohort with different weight criteria.

[0078] A different treatment plan may be selected for the new patient, and the treatment device may be remotely (e.g., may be referred to as remotely) controlled based on the different treatment plan while the new patient is using the treatment device to implement the treatment plan. Such technology may provide a technical solution for remotely controlling the treatment device.

[0079] Furthermore, the systems and methods described herein may lead to faster recovery times and / or better outcomes for patients because a treatment plan that most accurately matches the patient's characteristics is selected and implemented in real time at any given time. "Real time" may also refer to near real time, which may be less than 10 seconds. As used herein, the term "result" may refer to a medical result or a medical outcome. Results and outcomes may refer to a response to a medical intervention.

[0080] Depending on what outcomes are desired, the artificial intelligence engine can be trained to output several treatment plans. For example, one outcome may include recovery to a threshold level (e.g., 75% range of motion) in the fastest amount of time, while another outcome may include full recovery (e.g., 100% range of motion) regardless of the amount of time. Data obtained from patients and sorted into cohorts may indicate that a first treatment plan provides a first outcome for people with characteristics similar to those of the patient, and a second treatment plan provides a second outcome for people with characteristics similar to those of the patient.

[0081] Additionally, the artificial intelligence engine may be trained to output treatment plans that are not optimal for the patient, i.e., suboptimal, non-standard, or otherwise excluded (all referred to without limitation as "excluded treatment plans"). For example, if a patient has high blood pressure, a particular exercise may not be approved or suitable for the patient if the exercise may expose the patient to unnecessary risk or even induce a hypertensive crisis, and thus the exercise may be flagged as an excluded treatment plan for the patient. In some embodiments, the artificial intelligence engine may monitor treatment data received while a patient (e.g., a user) with high blood pressure is using a treatment device to implement an appropriate treatment plan, and if the treatment data indicates that the patient is managing the appropriate treatment plan without, for example, worsening the patient's hypertension condition, the artificial intelligence engine may modify the appropriate treatment plan to include features of the excluded treatment plan that may provide beneficial results for the patient.

[0082] In some embodiments, the treatment plan and / or excluded treatment plans may be presented to the healthcare provider during a telemedicine or telehealth session. The healthcare provider may select a particular treatment plan to have that treatment plan transmitted to the patient and / or control the treatment device based on the treatment plan. In some embodiments, an artificial intelligence engine may receive and / or operate remotely from the patient and treatment device to facilitate telehealth or telemedicine applications, including remote diagnosis, treatment plan determination, and rehabilitation and / or pharmacological prescription.

[0083] In such cases, the recommended and / or excluded treatment plans may be presented simultaneously with the patient's video in real time or near real time during the telemedicine or telehealth session on the user interface of the healthcare provider's computing device. The video may also be accompanied by audio, text, and other multimedia information. Real time may refer to two seconds or less. Near real time may refer to any interaction short enough in duration to allow two individuals to engage in a dialogue via such a user interface, generally less than ten seconds but more than two seconds.

[0084] Presenting a treatment plan generated by an artificial intelligence engine simultaneously with the presentation of the patient video may provide an enhanced user interface because the healthcare provider can continue to visually and / or otherwise communicate with the patient while also reviewing the treatment plan on the same user interface. The enhanced user interface may improve the healthcare provider's experience using the computing device and encourage the healthcare provider to reuse the user interface. Such techniques may also reduce computing resources (e.g., processing, memory, network) because the healthcare provider does not need to switch to another user interface screen to enter a query for a recommended treatment plan based on patient characteristics. The artificial intelligence engine may be configured to dynamically provide treatment plans and exclusions on the fly.

[0085] In some embodiments, the treatment device may be adaptive and / or personalized, as its properties, configuration, and position may be adapted to the needs of a particular patient. For example, pedals may be dynamically adjusted on the fly (e.g., based on a programmed configuration via a telemedicine session or in response to the detection of specific measurements) to increase or decrease range of motion to comply with a treatment plan designed for the user. In some embodiments, a healthcare provider may remotely adapt the treatment device to the patient's needs by causing control instructions to be transmitted from a server to the treatment device during a telemedicine session. Such adaptive properties may improve patient recovery outcomes, further advance the goals of personalized medicine, and enable the individualization of treatment plans on an individual basis.

[0086] 1 generally illustrates a block diagram of a computer-implemented system 10 for managing a treatment plan, hereafter referred to as the "system." Managing a treatment plan may include using an artificial intelligence engine to recommend treatment plans and / or provide exclusions for treatment plans that should not be recommended for a patient.

[0087] The system 10 also includes a server 30 configured to store (e.g., write to associated memory) and provide data related to managing the treatment plan. The server 30 may include one or more computers and may take the form of one or more distributed and / or virtualized computers. The server 30 also includes a first communication interface 32 configured to communicate with the clinician interface 20 via a first network 34. In some embodiments, the first network 34 may include wired and / or wireless network connections, such as Wi-Fi, Bluetooth, ZigBee, near field communication (NFC), cellular data networks, etc. The server 30 includes a first processor 36 and a first machine-readable storage memory 38, which may be referred to for short as “memory,” and which retains first instructions 40 for carrying out various actions of the server 30 for execution by the first processor 36.

[0088] Server 30 is configured to store data related to treatment plans. For example, memory 38 includes a system data store 42 configured to hold system data, such as data related to treatment plans for treating one or more patients. Server 30 is also configured to store data related to patient performance according to the treatment plans. For example, memory 38 includes a patient data store 44 configured to hold patient data, such as data related to one or more patients, including data describing each patient's performance within the treatment plan.

[0089] Additionally or alternatively, characteristics of people (e.g., personal, practice, measurements, etc.), the treatment plans they follow, their level of compliance with the treatment plans, and the outcomes of the treatment plans may be used to enable the division of treatment plans into databases corresponding to different patient cohorts within the patient data store 44 or to divide the treatment plans into databases corresponding to different patient cohorts using correlations and other statistical or probabilistic measures. For example, data regarding a first cohort of first patients having a first similar injury, a first similar medical condition, a first similar medical procedure performed, a first treatment plan followed by the first patient, and a first outcome of the treatment plan may be stored in a first patient database. Data regarding a second cohort of second patients having a second similar injury, a second similar medical condition, a second similar medical procedure performed, a second treatment plan followed by the second patient, and a second outcome of the treatment plan may be stored in a second patient database. Any single characteristic, or any combination of characteristics, may be used to separate patient cohorts. In some embodiments, different cohorts of patients may be stored in different partitions or volumes of the same database. There is no particular limit to the number of different cohorts of patients permitted, except as limited by mathematical combination and / or partitioning theory.

[0090] This characteristic data, treatment plan data, and outcome data may be obtained from multiple treatment devices and / or computing devices over time and stored in database 44. The characteristic data, treatment plan data, and outcome data may be correlated in a patient-cohort database within patient data store 44. The characteristics of people may include personal information, performance information, and / or measurement information.

[0091] In addition to historical information about other people stored in patient cohort-equivalent databases, real-time or near-real-time information about the current patient being treated based on the patient's characteristics can be stored in appropriate patient cohort-equivalent databases. A patient's characteristics can be determined to match or be similar to the characteristics of another person in a particular cohort (e.g., Cohort A), and the patient can be assigned to that cohort.

[0092] In some embodiments, the server 30 may implement an artificial intelligence (AI) engine 11 that implements at least one of the embodiments disclosed herein using one or more machine learning models 13. The server 30 may include a training engine 9 that can generate one or more machine learning models 13. The machine learning models 13 may be trained to, among other things, assign people to specific cohorts based on their characteristics, select treatment plans using real-time and historical data correlation with corresponding patient cohorts, and control treatment devices 70.

[0093] The one or more machine learning models 13 may be generated by the training engine 9 and may be implemented in computer instructions executable by one or more processing devices of the training engine 9 and / or the server 30. To generate the one or more machine learning models 13, the training engine 9 may train the one or more machine learning models 13. The one or more machine learning models 13 may be used by the artificial intelligence engine 11.

[0094] The training engine 9 may be a rack-mounted server, a router computer, a personal computer, a portable digital assistant, a smartphone, a laptop computer, a tablet computer, a netbook, a desktop computer, an Internet of Things (IoT) device, any other suitable computing device, or a combination thereof. The training engine 9 may also be a cloud-based or real-time software platform and may include privacy and / or security software or protocols.

[0095] To train the one or more machine learning models 13, the training engine 9 may use a training dataset of a corpus of characteristics of people who used the treatment device 70 to implement a treatment plan, details of the treatment plan implemented by people using the treatment device 70 (e.g., treatment protocol including exercise, amount of time to implement the exercise, frequency of implementation of the exercise, exercise schedule, parameters / configurations / settings of the treatment device 70 throughout each step of the treatment plan, etc.), and results of the treatment plan implemented by people. The one or more machine learning models 13 may be trained to match patterns of a patient's characteristics with characteristics of other people assigned to a particular cohort. The term "match" may refer to an exact match, a correlation match, a substantial match, etc. The one or more machine learning models 13 may be trained to receive the patient's characteristics as input, map the characteristics to characteristics of people assigned to a cohort, and select a treatment plan from that cohort. The one or more machine learning models 13 may also be trained to control the machine learning device 70 based on the treatment plan.

[0096] Different machine learning models 13 may be trained to recommend different treatment plans for different desired outcomes. For example, one machine learning model may be trained to recommend a treatment plan for the most effective recovery, while another machine learning model may be trained to recommend a treatment plan based on the speed of recovery.

[0097] Using training data including training inputs and corresponding target outputs, one or more machine learning models 13 may reference the model artifacts created by the training engine 9. The training engine 9 may find patterns in the training data that map training inputs to target outputs and generate machine learning models 13 that capture these patterns. In some embodiments, the artificial intelligence engine 11, database 33, and / or training engine 9 may reside in another component depicted in FIG. 1 (e.g., assistant interface 94, clinician interface 20, etc.).

[0098] The one or more machine learning models 13 may, for example, include a single level of linear or nonlinear operations (e.g., a support vector machine (SVM)), or the machine learning model 13 may be a deep network, i.e., a machine learning model that includes multiple levels of nonlinear operations. Examples of deep networks are neural networks (e.g., each neuron may transmit its output signal to the input of the remaining neurons and to itself), including generative adversarial networks, convolutional neural networks, recurrent neural networks with one or more hidden layers, and fully connected neural networks. For example, a machine learning model may include multiple layers and / or hidden layers that perform calculations (e.g., dot products) using various neurons.

[0099] The system 10 also includes a patient interface 50 configured to communicate information to and receive feedback from the patient. Specifically, the patient interface includes an input device 52 and an output device 54, which may be collectively referred to as a patient user interface 52, 54. The input device 52 may include one or more devices, such as a keyboard, a mouse, a touchscreen input, a gesture sensor, and / or a microphone and processor configured for voice recognition. The output device 54 may take one or more different forms, including, for example, a computer monitor or display screen on a tablet, smartphone, or smartwatch. The output device 54 may include other hardware and / or software components, such as a projector, virtual reality capabilities, augmented reality capabilities, etc. The output device 54 may incorporate a variety of different visual, audio, or other presentation technologies. For example, the output device 54 may include a non-visual display, such as an audio signal that may include speech and / or other sounds, such as tones, chimes, and / or melodies, that may signal various conditions and / or directions. The output device 54 may include one or more different display screens that present various data and / or interfaces or controls for use by the patient. The output device 54 may also include graphics, which may be presented by a web-based interface and / or by a computer program or application (app).

[0100] As generally illustrated in FIG. 1 , the patient interface 50 includes a second communication interface 56, which may also be referred to as a remote communication interface, configured to communicate with the server 30 and / or the clinician interface 20 via a second network 58. In some embodiments, the second network 58 may include a local area network (LAN), such as an Ethernet network. In some embodiments, the second network 58 may include the Internet, and communications between the patient interface 50 and the server 30 and / or the clinician interface 20 may be secured via encryption, such as by using a virtual private network (VPN). In some embodiments, the second network 58 may include wired and / or wireless network connections, such as Wi-Fi, Bluetooth, ZigBee, near field communication (NFC), cellular data networks, etc. In some embodiments, the second network 58 may be the same as the first network 34 and / or may be operatively coupled to the first network 34.

[0101] The patient interface 50 includes a second processor 60 and a second machine-readable storage memory 62 that holds second instructions 64 for execution by the second processor 60 to perform various actions of the patient interface 50. The second machine-readable storage memory 62 also includes a local data store 66 configured to hold patient data, such as data related to a treatment plan and / or data representative of the patient's performance within the treatment plan. The patient interface 50 also includes a local communication interface 68 configured to communicate with various devices for use by the patient in proximity of the patient interface 50. The local communication interface 68 may include wired and / or wireless communication. In some embodiments, the local communication interface 68 may include a local wireless network, such as Wi-Fi, Bluetooth, ZigBee, near field communication (NFC), a cellular data network, or the like.

[0102] The system 10 also includes a treatment device 70 configured to be operated by the patient and / or to manipulate a body part of the patient to perform activities according to the treatment plan. In some embodiments, the treatment device 70 may take the form of an exercise and rehabilitation device configured to administer and / or assist in administering a rehabilitation regimen, which may be an orthopedic rehabilitation regimen, where the treatment includes rehabilitation of a body part of the patient, such as a joint, bone, or muscle group. The treatment device 70 may be any suitable medical, rehabilitation, therapeutic, etc. device configured to be remotely controlled via another computing device to treat and / or exercise the patient. The treatment device 70 may be an electromechanical machine, including one or more weights, an electromechanical bicycle, an electromechanical spin wheel, a smart mirror, a treadmill, etc. The body part may include, for example, the spine, a hand, a foot, a knee, or a shoulder. The body part may include a portion of a joint, bone, or muscle group, such as one or more vertebrae, tendons, or ligaments. 1 , the therapy device 70 includes a controller 72, which may include one or more processors, computer memory, and / or other components. The therapy device 70 also includes a fourth communication interface 74 configured to communicate with the patient interface 50 via the local communication interface 68. The therapy device 70 also includes one or more internal sensors 76 and an actuator 78, such as a motor. The actuator 78 may be used, for example, to move a body part of the patient and / or to resist forces by the patient.

[0103] The internal sensor 76 may measure one or more operating characteristics of the treatment device 70, such as, for example, force, position, speed, and / or velocity. In some embodiments, the internal sensor 76 may include a position sensor configured to measure at least one of linear or angular motion of a patient's body part. For example, the internal sensor 76 in the form of a position sensor may measure a distance a patient can move a portion of the treatment device 70, and such distance may correspond to a range of motion that the patient's body part can achieve. In some embodiments, the internal sensor 76 may include a force sensor configured to measure a force applied by the patient. For example, the internal sensor 76 in the form of a force sensor may measure a force or load that a patient can apply to the treatment device 70 using a particular body part.

[0104] 1 also includes an gait sensor 82 that communicates with the server 30 via the local communication interface 68 of the patient interface 50. The gait sensor 82 may track and store the number of steps taken by the patient. In some embodiments, the gait sensor 82 may take the form of a wristband, a wristwatch, or a smartwatch. In some embodiments, the gait sensor 82 may be integrated into a phone, such as a smartphone.

[0105] 1 also includes a goniometer 84 that communicates with the server 30 via the local communication interface 68 of the patient interface 50. The goniometer 84 measures the angle of a patient's body part. For example, the goniometer 84 may measure the angle of flexion of the patient's knee, elbow, or shoulder.

[0106] 1 also includes a pressure sensor 86 in communication with the server 30 via the local communication interface 68 of the patient interface 50. The pressure sensor 86 measures the amount of pressure or load exerted by a body part of the patient. For example, the pressure sensor 86 may measure the amount of force exerted by the patient's feet when pedaling a stationary bicycle.

[0107] 1 also includes a supervisory interface 90, which may be similar to or identical to clinician interface 20. In some embodiments, supervisory interface 90 may have enhanced functionality than that provided in clinician interface 20. Supervisory interface 90 may be configured for use by a person responsible for treatment planning, such as an orthopedic surgeon.

[0108] System 10, generally illustrated in FIG. 1, also includes a reporting interface 92, which may be similar or identical to clinician interface 20. In some embodiments, reporting interface 92 may have less functionality than that provided in clinician interface 20. For example, reporting interface 92 may not have the ability to modify a treatment plan. Such a reporting interface 92 may be used, for example, by a biller to determine use of system 10 for billing purposes. In another example, reporting interface 92 may not have the ability to display patient-identifiable information and may present only depersonalized and / or anonymized data for certain data fields related to a data subject and / or for certain data fields related to a data subject's quasi-identifiers. Such a reporting interface 92 may be used, for example, by researchers to determine the varying effects of treatment plans on various patients.

[0109] The system 10 includes an assistant interface 94 for a healthcare provider, such as those described herein, to remotely communicate with the patient interface 50 and / or the therapy device 70. Such remote communication may enable the healthcare provider to provide assistance or guidance to a patient using the system 10. More specifically, the assistant interface 94 is configured to communicate telemedicine signals 96, 97, 98a, 98b, 99a, 99b with the patient interface 50 over a network connection, such as via the first network 34 and / or the second network 58. The telemedicine signals 96, 97, 98a, 98b, 99a, 99b include one of an audio signal 96, an audiovisual signal 97, an interface control signal 98a for controlling a function of the patient interface 50, an interface monitor signal 98b for monitoring a status of the patient interface 50, an equipment control signal 99a for changing an operating parameter of the therapy device 70, and / or an equipment monitor signal 99b for monitoring a status of the therapy device 70. In some embodiments, each of the control signals 98a, 99a may be unidirectional and communicate a command from the assistant interface 94 to the patient interface 50. In some embodiments, an acknowledgement message may be sent from the patient interface 50 to the assistant interface 94 in response to successfully receiving the control signal 98a, 99a and / or communicating successful and / or unsuccessful implementation of a requested control action. In some embodiments, each of the monitor signals 98b, 99b may be a unidirectional status information command from the patient interface 50 to the assistant interface 94. In some embodiments, an acknowledgement message may be sent from the assistant interface 94 to the patient interface 50 in response to successfully receiving one of the monitor signals 98b, 99b.

[0110] In some embodiments, the patient interface 50 can be configured as a pass-through for device control signals 99a and device monitor signals 99b between the treatment device 70 and one or more other devices, such as the assistant interface 94 and / or the server 30. For example, the patient interface 50 can be configured to transmit the device control signal 99a in response to the device control signal 99a in the telemedicine signals 96, 97, 98a, 98b, 99a, 99b from the assistant interface 94.

[0111] In some embodiments, assistant interface 94 may be presented on a shared physical device as clinician interface 20. For example, clinician interface 20 may include one or more screens that implement assistant interface 94. Alternatively or additionally, clinician interface 20 may include additional hardware components, such as a video camera, a speaker, and / or a microphone, for implementing aspects of assistant interface 94.

[0112] In some embodiments, one or more portions of the telemedicine signals 96, 97, 98a, 98b, 99a, 99b may be generated from a pre-recorded source (e.g., an audio recording, a video recording, or an animation) for presentation by the output device 54 of the patient interface 50. For example, a tutorial video may be streamed from the server 30 and presented on the patient interface 50. Content from a pre-recorded source may be requested by the patient via the patient interface 50. Alternatively, via controls on the assistant interface 94, a healthcare provider may play content from a pre-recorded source on the patient interface 50.

[0113] The assistant interface 94 includes an assistant input device 22 and an assistant display 24, which may be collectively referred to as an assistant user interface 22, 24. The assistant input device 22 may include, for example, one or more of a telephone, a keyboard, a mouse, a trackpad, or a touchscreen. Alternatively or additionally, the assistant input device 22 may include one or more microphones. In some embodiments, the one or more microphones may take the form of a telephone handset, a headset, or one or more wide-range microphones configured for the healthcare provider to speak to the patient via the patient interface 50. In some embodiments, the assistant input device 22 may have hardware and / or software configured to interpret commands spoken by the healthcare provider using the one or more microphones and may be configured to provide voice-based functionality. The assistant input device 22 may include functionality provided by or similar to existing voice-based assistants such as Apple's Siri, Amazon's Alexa, Google Assistant, or Samsung's Bixby. The assistant input device 22 may include other hardware and / or software components. The assistant input device 22 may include one or more general-purpose and / or dedicated devices.

[0114] Assistant display 24 may take one or more different forms, including, for example, a computer monitor or display screen on a tablet, smartphone, or smartwatch. Assistant display 24 may include other hardware and / or software components, such as a projector, virtual reality capabilities, or augmented reality capabilities. Assistant display 24 may incorporate a variety of different visual, audio, or other presentation technologies. For example, assistant display 24 may include non-visual displays, such as audio signals, which may include speech and / or other sounds, such as tones, chimes, melodies, and / or songs, that may signal various conditions and / or directions. Assistant display 24 may comprise one or more different display screens that present various data and / or interfaces or controls for use by the healthcare provider. Assistant display 24 may include graphics, which may be presented by a web-based interface and / or by a computer program or application (app).

[0115] In some embodiments, the system 10 may provide computerized translation of language from the assistant interface 94 to the patient interface 50, and / or vice versa. The computerized translation of language may include computerized translation of speech and / or computerized translation of text. Additionally or alternatively, the system 10 may provide speech recognition of text and / or speech sounds. For example, the system 10 may convert speech to printed text and / or the system 10 may audibly recite words from printed text. The system 10 may be configured to recognize words spoken by any or all of the patient, clinician, and / or healthcare provider. In some embodiments, the system 10 may be configured to recognize and react to requests or commands spoken by the patient. For example, the system 10 may automatically initiate a telemedicine session in response to a verbal command by the patient (which may be given in any one of several different languages).

[0116] In some embodiments, server 30 can generate aspects of assistant display 24 for presentation by assistant interface 94. For example, server 30 can include a web server configured to generate display screens for presentation on assistant display 24. For example, artificial intelligence engine 11 can generate recommended and / or excluded treatment plans for a patient and generate display screens including the recommended and / or excluded treatment plans for presentation on assistant display 24 of assistant interface 94. In some embodiments, assistant display 24 can be configured to present a virtualized desktop hosted by server 30. In some embodiments, server 30 can be configured to communicate with assistant interface 94 via a first network 34. In some embodiments, first network 34 can include a local area network (LAN), such as an Ethernet network.

[0117] In some embodiments, the first network 34 may include the Internet, and communications between the server 30 and the assistant interface 94 may be secured through privacy-enhancing techniques, such as by using encryption via a virtual private network (VPN). Alternatively or additionally, the server 30 may be configured to communicate with the assistant interface 94 through one or more networks independent of the first network 34 and / or other communication means, such as direct wired or wireless communication channels. In some embodiments, the patient interface 50 and the therapy devices 70 may each operate from a patient location geographically separate from the location of the assistant interface 94. For example, the patient interface 50 and the therapy devices 70 may be used as part of a home rehabilitation system, which may be remotely assisted by using the assistant interface 94 at a centralized location, such as a clinic or call center.

[0118] In some embodiments, assistant interface 94 may be one of several different terminals (e.g., computing devices) that may be grouped together, for example, in one or more call centers or in one or more clinician offices. In some embodiments, multiple assistant interfaces 94 may be geographically distributed. In some embodiments, a person may work as a healthcare provider remotely from any traditional office infrastructure. Such teleworking may be implemented, for example, when assistant interface 94 takes the form of a computer and / or telephone. This teleworking functionality may enable teleworking arrangements that may include part-time and / or flexible work hours for healthcare providers.

[0119] 2-3 illustrate one embodiment of a therapy device 70. More specifically, FIG. 2 generally illustrates the therapy device 70 in the form of a stationary cycling machine 100, which may be shortened to a stationary bike. The stationary cycling machine 100 includes a set of pedals 102, each attached to a pedal arm 104 for rotation about an axis 106. In some embodiments, as generally illustrated in FIG. 2, the pedals 102 are movable on the pedal arms 104 to adjust the range of motion used by the patient when pedaling. For example, positioning the pedal inward toward the axis 106 corresponds to a smaller range of motion than when the pedal is positioned outward away from the axis 106. A pressure sensor 86 is attached to or embedded in one of the pedals 102 to measure the amount of force applied by the patient to the pedal 102. The pressure sensor 86 may communicate wirelessly to the therapy device 70 and / or to the patient interface 50.

[0120] 4 generally illustrates a person (patient) using the treatment device of FIG. 2 and shows sensors and various data parameters connected to a patient interface 50. An exemplary patient interface 50 is a tablet computer or smartphone, such as an iPad, iPhone, Android device, or Surface tablet (each a registered trademark), or a phablet, manually held by the patient. In some other embodiments, the patient interface 50 may be embedded in or attached to the treatment device 70.

[0121] Figure 4 generally illustrates the patient wearing the gait sensor 82 on their wrist, and the note reading "Steps Today 1355" indicates that the gait sensor 82 is recording and transmitting that step count to the patient interface 50. Figure 4 also generally illustrates the patient wearing the goniometer 84 on their right knee, and the note reading "Knee Angle 72°" indicates that the goniometer 84 is measuring and transmitting that knee angle to the patient interface 50. Figure 4 also generally illustrates that the right side of one of the pedals 102 having a pressure sensor 86 reads "12.5 lbs. force," indicating that the right pedal pressure sensor 86 is measuring and transmitting that force measurement to the patient interface 50.

[0122] FIG. 4 also generally illustrates that the left side of one of the pedals 102 having a pressure sensor 86 indicates "27 lbs. force," indicating that the left pedal pressure sensor 86 is measuring and transmitting that force measurement to the patient interface 50. FIG. 4 also generally illustrates other patient data, such as an indicator of "Session Time 0:04:13," indicating that the patient has been using the therapy device 70 for 4 minutes and 13 seconds. This session time may be determined by the patient interface 50 based on information received from the therapy device 70. FIG. 4 also generally illustrates an indicator indicating "Pain Level 3." Such a pain level may be obtained from the patent in response to a prompt, such as a question, presented on the patient interface 50.

[0123] 5 is an exemplary embodiment of an overview display 120 of the assistant interface 94. Specifically, the overview display 120 presents several different controls and interfaces for a healthcare provider to remotely assist a patient using the patient interface 50 and / or therapy device 70. This remote assistance functionality may also be referred to as telemedicine or telehealth.

[0124] In particular, the overview display 120 includes a patient profile display 130 that presents historical information about the patient using the treatment device 70. The patient profile display 130 may take the form of a portion or area of the overview display 120, as generally illustrated in Figure 5, although the patient profile display 130 may take other forms, such as a separate screen or a pop-up window.

[0125] In some embodiments, the patient profile display 130 may include a limited subset of the patient's biographical information. More specifically, the data presented on the patient profile display 130 may depend on the healthcare provider's need for that information. For example, a healthcare provider assisting a patient with a medical problem may be provided with medical history information about the patient, whereas a technician troubleshooting a problem with the treatment device 70 may be provided with a more limited set of information about the patient. For example, the technician may be provided with only the patient's name.

[0126] The patient profile display 130 may include depersonalized and / or anonymized data or may use any privacy-enhancing techniques to prevent sensitive patient data from being communicated in a manner that may violate patient confidentiality requirements. Such privacy-enhancing techniques may enable compliance with laws, regulations, or other governance rules, such as, but not limited to, the Health Insurance Portability and Accountability Act (HIPAA) or the General Data Protection Regulation (GDPR), in which patients may be considered "data subjects."

[0127] In some embodiments, the patient profile display 130 may present information regarding a treatment plan to be followed by the patient when using the treatment device 70. Such treatment plan information may be restricted to healthcare providers. For example, a healthcare provider assisting a patient with issues regarding a treatment regimen may be provided with treatment plan information, whereas a technician troubleshooting an issue with the treatment device 70 may not be provided with any information regarding the patient's treatment plan.

[0128] In some embodiments, one or more recommended and / or excluded treatment plans may be presented to the healthcare provider on the patient profile display 130. The one or more recommended and / or excluded treatment plans may be generated by the artificial intelligence engine 11 of the server 30 and may be received in real time from the server 30, particularly during a telemedicine or telehealth session. An example of presenting one or more recommended and / or excluded treatment plans is described below with reference to FIG. 7.

[0129] The exemplary overview display 120, generally illustrated in Figure 5, also includes a patient status display 134 that presents status information regarding a patient using a therapy device. The patient status display 134 may take the form of a portion or area of the overview display 120, as generally illustrated in Figure 5, although the patient status display 134 may take other forms, such as a separate screen or a pop-up window.

[0130] The patient status display 134 includes sensor data 136 from one or more of the external sensors 82, 84, 86 and / or from one or more internal sensors 76 of the therapy device 70. In some embodiments, the patient status display 134 may include sensor data from one or more sensors of one or more wearable devices worn by the patient while using the therapy device 70. The one or more wearable devices may include a watch, bracelet, necklace, chest band, etc. The one or more wearable devices may be configured to monitor the patient's heart rate, temperature, blood pressure, one or more vital signs, etc. while the patient is using the therapy device 70. In some embodiments, the patient status display 134 may present other data 138 about the patient, such as last reported pain level or progress within a treatment plan.

[0131] User access controls may be used to restrict access to any or all of the user interfaces 20, 50, 90, 92, 94 of system 10, including what data is available to view and / or modify. In some embodiments, user access controls may be used to control what information is available to any given person using system 10. For example, the data presented on assistant interface 94 may be controlled by user access controls, and permissions may be set depending on the needs and / or entitlements of the healthcare provider / user to view that information.

[0132] The exemplary overview display 120, generally illustrated in Figure 5, also includes a help data display 140 that presents information for use by a healthcare provider in assisting a patient. The help data display 140 may take the form of a portion or area of the overview display 120, as generally illustrated in Figure 5. The help data display 140 may also take other forms, such as a separate screen or a pop-up window. The help data display 140 may include, for example, presenting answers to frequently asked questions regarding use of the patient interface 50 and / or the therapy device 70.

[0133] Help data display 140 may also include research data or best practices. In some embodiments, help data display 140 may present answer or explanation scripts in response to patient questions. In some embodiments, help data display 140 may present flowcharts or walkthroughs for use by healthcare providers in determining the root cause and / or solution to a patient's problem.

[0134] In some embodiments, the assistant interface 94 may present two or more help data displays 140, which may be the same or different, to simultaneously present help data for use by a healthcare provider. For example, a first help data display may be used to present a troubleshooting flowchart for determining the root of a patient's problem, and a second help data display may present script information, which is information for the healthcare provider to read to the patient, preferably including instructions for the patient to perform some action, that may help narrow down or resolve the problem. In some embodiments, the second help data display may automatically populate the script information based on input into the troubleshooting flowchart in the first help data display.

[0135] The exemplary overview display 120 illustrated generally in FIG. 5 also includes patient interface controls 150 for presenting information related to the patient interface 50 and / or modifying one or more settings of the patient interface 50. The patient interface controls 150 may take the form of a portion or region of the overview display 120, as illustrated generally in FIG. 5. The patient interface controls 150 may take other forms, such as a separate screen or a pop-up window. The patient interface controls 150 may present information communicated to the assistant interface 94 via one or more of the interface monitor signals 98b.

[0136] 5, the patient interface controls 150 include a display feed 152 of the display presented by the patient interface 50. In some embodiments, the display feed 152 may include a live copy of the display screen currently being presented to the patient by the patient interface 50. In other words, the display feed 152 may present an image of what is presented on the display screen of the patient interface 50.

[0137] In some embodiments, the display feed 152 may include summary information about the display screen currently being presented by the patient interface 50, such as the screen name or screen number. The patient interface controls 150 may include patient interface setting controls 154 that allow a healthcare provider to adjust or control one or more settings or aspects of the patient interface 50. In some embodiments, the patient interface setting controls 154 may cause the assistant interface 94 to generate and / or transmit interface control signals 98 to control functions or settings of the patient interface 50.

[0138] In some embodiments, the patient interface settings control 154 may include collaborative or co-browsing capabilities for a healthcare provider to remotely view and / or control the patient interface 50. For example, the patient interface settings control 154 may allow the healthcare provider to remotely enter text into one or more text entry fields on the patient interface 50 and / or remotely control a cursor on the patient interface 50 using a mouse or touchscreen of the assistant interface 94.

[0139] In some embodiments, the patient interface settings controls 154 may allow a healthcare provider to change settings that cannot be changed by the patient using the patient interface 50. For example, the patient interface 50 may be prevented from accessing the language setting to prevent the patient from inadvertently switching the language used for displays on the patient interface 50, whereas the patient interface settings controls 154 may allow the healthcare provider to change the language setting of the patient interface 50. In another example, the patient interface 50 may not allow the font size setting to be changed to a smaller size to prevent the patient from inadvertently switching the font size used for displays on the patient interface 50 such that the displays become unreadable to the patient, whereas the patient interface settings controls 154 may provide for the healthcare provider to change the font size setting of the patient interface 50.

[0140] 5 also includes an interface communication display 156 that indicates the status of communications between the patient interface 50 and one or more other devices 70, 82, 84, such as the therapy device 70, the gait sensor 82, and / or the goniometer 84. The interface communication display 156 may take the form of a portion or region of the overview display 120, as generally illustrated in FIG.

[0141] The interface communication display 156 may take other forms, such as a separate screen or a pop-up window. The interface communication display 156 may include controls for a healthcare provider to remotely modify communication with one or more of the other devices 70, 82, 84. For example, a healthcare provider may remotely instruct the patient interface 50 to reset communication with one of the other devices 70, 82, 84 or to establish communication with a new one of the other devices 70, 82, 84. This functionality may be used, for example, if the patient has a problem with one of the other devices 70, 82, 84 or if the patient receives a new or replacement one of the other devices 70, 82, 84.

[0142] The exemplary overview display 120 generally illustrated in FIG. 5 also includes device controls 160 for the healthcare provider to view and / or control information related to the therapy device 70. The device controls 160 may take the form of a portion or area of the overview display 120, as generally illustrated in FIG. 5. The device controls 160 may take other forms, such as a separate screen or a pop-up window. The device controls 160 may include a device status display 162 having information regarding the current status of the device. The device status display 162 may present information communicated to the assistant interface 94 via one or more of the device monitor signals 99b. The device status display 162 may indicate whether the therapy device 70 is currently communicating with the patient interface 50. The device status display 162 may present other current and / or historical information regarding the status of the therapy device 70.

[0143] The device controls 160 may include device setting controls 164 that allow the healthcare provider to adjust or control one or more aspects of the therapy device 70. The device setting controls 164 may cause the assistant interface 94 to generate and / or transmit device control signals 99 (e.g., which, as described, may be referred to as treatment plan inputs) to change the operating parameters and / or one or more characteristics of the therapy device 70 (e.g., pedal radius setting, resistance setting, target RPM, other suitable characteristics of the therapy device 70, or a combination thereof).

[0144] The device setting controls 164 may include a mode button 166 and a position control 168, which may be used in conjunction to allow a healthcare provider to place the actuator 78 of the treatment device 70 in manual mode and then use the position control 168 to change settings such as the position or speed of the actuator 78. The mode button 166 may provide settings such as position for switching between automatic and manual modes.

[0145] In some embodiments, one or more settings may be adjustable at any time and without an associated automatic / manual mode. In some embodiments, a healthcare provider may change an operating parameter of the therapy device 70, such as a pedal radius setting, while the patient is actively using the therapy device 70. Such "on the fly" adjustments may or may not be available to the patient using the patient interface 50.

[0146] In some embodiments, the device settings control 164 may allow the healthcare provider to change settings that the patient cannot change using the patient interface 50. For example, the patient interface 50 may be prevented from changing pre-configured settings, such as the height or tilt settings of the treatment device 70, whereas the device settings control 164 may provide for the healthcare provider to change the height or tilt settings of the treatment device 70.

[0147] The exemplary overview display 120 generally illustrated in FIG. 5 may also include patient communication controls 170 for controlling an audio or audiovisual communication session with the patient interface 50. The communication session with the patient interface 50 may include a live feed from the assistant interface 94 for presentation by an output device of the patient interface 50. The live feed may take the form of an audio feed and / or a video feed. In some embodiments, the patient interface 50 may be configured to provide two-way audio or audiovisual communication with a person using the assistant interface 94. Specifically, the communication session with the patient interface 50 may include a bidirectional (two-way) video or audiovisual feed, with the patient interface 50 and the assistant interface 94 each presenting video of the other.

[0148] In some embodiments, the patient interface 50 may present video from the assistant interface 94, while the assistant interface 94 presents only audio, or the assistant interface 94 presents no live audio or visual signals from the patient interface 50. In some embodiments, the assistant interface 94 may present video from the patient interface 50, while the patient interface 50 presents only audio, or the patient interface 50 presents no live audio or visual signals from the assistant interface 94.

[0149] In some embodiments, an audio or audiovisual communication session with the patient interface 50 may occur, at least in part, while the patient is performing a rehabilitation regimen for a body part. The patient communication control 170 may take the form of a portion or area of the overview display 120, as generally illustrated in Figure 5. The patient communication control 170 may also take other forms, such as a separate screen or a pop-up window.

[0150] The audio and / or audiovisual communications may be processed and / or directed by the assistant interface 94 and / or by one or more other devices, such as a telephone system or a videoconferencing system used by the healthcare provider while the healthcare provider is using the assistant interface 94. Alternatively or additionally, the audio and / or audiovisual communications may include communications with a third party. For example, the system 10 may enable the healthcare provider to initiate a three-way conversation with the patient and a subject matter expert, such as a healthcare provider or specialist, regarding the use of a particular piece of hardware or software. The exemplary patient communication controls 170, generally illustrated in FIG. 5, include a call control 172 for use by the healthcare provider in managing various aspects of audio or audiovisual communications with the patient. The call control 172 includes a hang-up button 174 for the healthcare provider to end the audio or audiovisual communication session. The call control 172 also includes a mute button 176 for temporarily muting audio or audiovisual signals from the assistant interface 94. In some embodiments, the call control 172 may include other functions, such as a hold button (not shown).

[0151] The call control 172 also includes one or more record / playback controls 178, such as record, play, and pause buttons, for controlling the recording and / or playback of audio and / or video from the conference call session on the patient interface 50. The call control 172 also includes a video feed display 180 for presenting still and / or video images from the patient interface 50, and a self-video display 182 showing a current image of the healthcare provider using the assistant interface 94. The self-video display 182 may be presented as a picture-in-picture format within a section of the video feed display 180, as generally illustrated in FIG. 5. Alternatively or additionally, the self-video display 182 may be presented separately and / or independently from the video feed display 180.

[0152] The exemplary overview display 120 illustrated generally in Figure 5 also includes a third-party communication control 190 for use in conducting audio and / or audiovisual communication with a third party. The third-party communication control 190 may take the form of a portion or area of the overview display 120, as illustrated generally in Figure 5. The third-party communication control 190 may take other forms, such as a separate on-screen display or a pop-up window.

[0153] The third party communication controls 190 may include one or more controls, such as a contact list and / or a button or control, for contacting a third party, e.g., a subject matter expert such as a healthcare provider or specialist, regarding use of a particular piece of hardware or software. The third party communication controls 190 may include teleconferencing capabilities for a third party to simultaneously communicate with both a healthcare provider via the assistant interface 94 and with a patient via the patient interface 50. For example, the system 10 may provide for a healthcare provider to initiate a three-way conversation with a patient and a third party.

[0154] 6 generally illustrates an exemplary block diagram for training a machine learning model 13 to output a treatment plan 602 for a patient based on data 600 about the patient, according to the present disclosure. Data about other patients may be received by the server 30. The other patients may be implementing the treatment plan using different treatment devices.

[0155] The data may include characteristics of other patients, details of treatment plans implemented by other patients, and / or results of implementing the treatment plans (e.g., the rate of recovery of a part of the patient's body, the amount of recovery of a part of the patient's body, the amount of increase or decrease in muscle strength of a part of the patient's body, the amount of increase or decrease in range of motion of a part of the patient's body, etc.).

[0156] As depicted, the data is assigned to various cohorts. Cohort A includes data of patients with a similar first characteristic, a first treatment plan, and a first outcome. Cohort B includes data of patients with a similar second characteristic, a second treatment plan, and a second outcome. For example, Cohort A may include a first characteristic of patients in their twenties without any medical conditions who underwent surgery for a broken limb, and the treatment plan for these patients may include a particular treatment protocol (e.g., use of the treatment device 70 for 30 minutes, five times per week for three weeks, with the value of a property, configuration, and / or setting of the treatment device 70 set to X (where X is a number) for the first two weeks and Y (where Y is a number) for the last week).

[0157] Cohort A and Cohort B may be included in a training data set used to train machine learning model 13. Machine learning model 13 may be trained to match patterns between characteristics of each cohort and output a treatment plan that provides results. Thus, when new patient data 600 is input into trained machine learning model 13, trained machine learning model 13 may match characteristics included in data 600 with characteristics of either Cohort A or Cohort B and output an appropriate treatment plan 602. In some embodiments, machine learning model 13 may be trained to output one or more excluded treatment plans that should not be performed by the new patient.

[0158] 7 generally illustrates one embodiment of an overview display 120 of the assistant interface 94 that presents recommended and ruled-out treatment plans in real time during a telemedicine session in accordance with the present disclosure. As depicted, the overview display 120 only includes sections of the patient profile 130 and the video feed display 180, including the self-video display 182. Any suitable configuration of the controls and interfaces of the overview display 120 described with reference to FIG. 5 may be presented in addition to or instead of the patient profile 130, the video feed display 180, and the self-video display 182.

[0159] A healthcare provider using the assistant interface 94 (e.g., a computing device) during a telemedicine session may be presented with a self-video 182 in a portion of the overview display 120 (e.g., a user interface presented on the display screen 24 of the assistant interface 94) that also presents video from the patient on the video feed display 180. Additionally, the video feed display 180 may also include a graphical user interface (GUI) object 700 (e.g., a button) that allows the healthcare provider to share recommended and / or ruled-out treatment plans with the patient on the patient interface 50 in real time or near real time during the telemedicine session. The healthcare provider may select the GUI object 700 to share the recommended and / or ruled-out treatment plans. As depicted, another portion of the overview display 120 includes a patient profile display 130.

[0160] The patient profile display 130 presents two exemplary recommended treatment plans 600 and one exemplary excluded treatment plan 602. As described herein, treatment plans may be recommended taking into account the characteristics of the patient being treated. Patterns between the characteristics of the patient being treated and a cohort of other people who have used the treatment device 70 to implement the treatment plan may be matched by one or more machine learning models 13 of the artificial intelligence engine 11 to generate the recommended treatment plan 600 for the patient to follow to achieve a desired outcome. Each of the recommended treatment plans may be generated based on a different desired outcome.

[0161] For example, as depicted, the patient profile display 130 presents, "Patient characteristics match those of use in Cohort A. The following treatment plans are recommended for the patient based on the patient's characteristics and desired results." The patient profile display 130 then presents recommended treatment plans from Cohort A, each providing a different result.

[0162] As depicted, treatment plan "A" indicates, "Patient X should use the treatment device for 30 minutes per day for four days to achieve a Y% increase in range of motion; Patient X has type 2 diabetes; and Patient X should be prescribed drug Z for pain management during the treatment plan (drug Z is approved for people with type 2 diabetes)." Thus, the generated treatment plan achieves a Y% increase in range of motion. As can be appreciated, the treatment plan also includes a recommended drug (e.g., drug Z) to prescribe to the patient to manage pain taking into account the patient's known medical condition (e.g., type 2 diabetes). That is, the recommended patient drug not only does not conflict with the patient's medical condition, but also thereby improves the likelihood of a good patient outcome. This particular example, and all such examples elsewhere herein, are not intended to limit the generated treatment plan in any way to recommending multiple drugs or addressing the identification, interpretation, diagnosis, and / or treatment of co-occurring conditions or diseases.

[0163] Recommended treatment plan "B" may specify different treatment plans, including different treatment protocols for treatment devices, different drug regimens, etc., based on different desired outcomes of the treatment plans.

[0164] As depicted, the patient profile display 130 may also present excluded treatment plans 602. These types of treatment plans are shown to the healthcare provider using the assistant interface 94 to alert the healthcare provider not to recommend certain portions of the treatment plan to the patient. For example, an excluded treatment plan may specify: "Patient X should not use a treatment device for more than 30 minutes per day due to heart disease, and Patient X has type 2 diabetes, and Patient X should not be prescribed drug M for pain management during the treatment plan (in this scenario, drug M may cause complications in people with type 2 diabetes)." Specifically, the excluded treatment plan may point out a restriction in the treatment protocol that, due to heart disease, Patient X should not exercise for more than 30 minutes per day. The excluded treatment plan may also point out that drug M should not be prescribed to Patient X because it conflicts with the medical condition of type 2 diabetes.

[0165] The healthcare provider may select a treatment plan for the patient on the overview display 120. For example, the healthcare provider may use an input peripheral (e.g., a mouse, touch screen, microphone, keyboard, etc.) to select from the patient's treatment plans 600. In some embodiments, during the telemedicine session, the healthcare provider may discuss the advantages and disadvantages of the recommended treatment plan 600 with the patient.

[0166] In either case, the healthcare provider may select a treatment plan for the patient to follow to achieve the desired results. The selected treatment plan may be transmitted to the patient interface 50 for presentation. The patient may view the selected treatment plan on the patient interface 50. In some embodiments, the healthcare provider and patient may discuss details (e.g., treatment protocol using the treatment device 70, dietary regimen, drug regimen, etc.) in real time or near real time during the telemedicine session. In some embodiments, the server 30 may control the treatment device 70 as the user uses it based on the selected treatment plan and during the telemedicine session.

[0167] 8 generally illustrates one embodiment of a summary display 120 of the assistant interface 94 presenting a recommended treatment plan that has changed as a result of changes in patient data in real time during a telemedicine session in accordance with the present disclosure. As can be appreciated, the treatment device 70 and / or any computing device (e.g., the patient interface 50) may transmit data while the patient is using the treatment device 70 to implement the treatment plan. The data may include updated patient characteristics and / or other treatment data. For example, the updated characteristics may include new performance information and / or measurement information. The performance information may include the speed of a portion of the treatment device 70, the range of motion achieved by the patient, the force exerted on a portion of the treatment device 70, the patient's heart rate, the patient's blood pressure, the patient's respiratory rate, etc.

[0168] In some embodiments, the data received at the server 30 may be input into the trained machine learning model 13, which may determine that the characteristics indicate that the patient is on track with the current treatment plan. Determining that the patient is on track with the current treatment plan may cause the trained machine learning model 13 to adjust parameters of the treatment device 70. The adjustments may be based on next steps in the treatment plan to further improve patient performance.

[0169] In some embodiments, the data received at the server 30 may be input into a trained machine learning model 13, which may determine that the characteristics indicate that the patient is not on track with the current treatment plan (e.g., behind schedule, unable to maintain speed, unable to achieve a specific range of motion, too much pain, etc.) or is ahead of the schedule of the current treatment plan (e.g., exceeding a specific speed, exercising for longer than a specified time without pain, exerting more force than specified, etc.).

[0170] The trained machine learning model 13 may determine that the patient's characteristics no longer match those of patients in the cohort to which the patient is assigned. Accordingly, the trained machine learning model 13 may reassign the patient to another cohort that includes the characteristics of the qualifying patients. Accordingly, the trained machine learning model 13 may select a new treatment plan from the new cohort and control the treatment device 70 based on the new treatment plan.

[0171] In some embodiments, before controlling the therapy device 70, the server 30 may provide a new treatment plan 800 to the assistant interface 94 for presentation in the patient profile 130. As depicted, the patient profile 130 indicates, "Patient characteristics have changed to match those of use in Cohort B. Based on the patient's characteristics and desired outcomes, the following treatment plan is recommended for the patient." The patient profile 130 then presents the new treatment plan 800 ("Patient X would benefit from using the therapy device 10 minutes per day for 3 days to achieve an L% increase in range of motion"). The healthcare provider may select the new treatment plan 800, and the server 30 may receive the selection. The server 30 may control the therapy device 70 based on the new treatment plan 800. In some embodiments, the new treatment plan 800 may be transmitted to the patient interface 50 so that the patient may view details of the new treatment plan 800.

[0172] In some embodiments, the server 30 may receive therapy data about the patient while the patient is implementing the therapy plan using the therapy device 70. As described, the therapy plan may correspond to a rehabilitation therapy plan, a pre-operative rehabilitation therapy plan, an exercise therapy plan, or other suitable therapy plan. The therapy data may include various characteristics of the patient (e.g., such as those described herein), various measurement information about the patient while the patient is using the therapy device 70 (e.g., such as those described herein), various characteristics of the therapy device 70 (e.g., such as those described herein), the therapy plan, other suitable data, or a combination thereof.

[0173] In some embodiments, at least a portion of the therapy data may include sensor data 136 from one or more of the external sensors 82, 84, 86 and / or from one or more internal sensors 76 of the therapy device 70. In some embodiments, at least a portion of the therapy data may include sensor data from one or more sensors of one or more wearable devices worn by the patient while using the therapy device 70. The one or more wearable devices may include a watch, a bracelet, a necklace, a chest strap, a head sweatband, a wrist sweatband, any other suitable sweatband, any other suitable wearable, or a combination thereof. While the patient is using the therapy device 70, the one or more wearable devices may be configured to monitor the patient's heart rate, temperature, blood pressure, one or more vital signs, etc.

[0174] In some embodiments, the server 30 may generate treatment information using the treatment data. The treatment information may include a formatted summary of the user's implementation of the treatment plan while using the treatment device so that the treatment data is presentable on a computing device of a healthcare provider responsible for the user's implementation of the treatment plan. In some embodiments, the patient profile display 120 may include and / or display the treatment information.

[0175] Server 30 may be configured to provide the treatment information in overview display 120. For example, server 30 may store the treatment information for access by overview display 120 and / or communicate the treatment information to overview display 120. In some embodiments, server 30 may provide the treatment information to patient profile display 130, or other suitable section, portion, or component of overview display 120, or any other suitable display or interface.

[0176] In some embodiments, a healthcare provider assisting the patient while using the treatment device 70 may review the treatment information and determine whether to modify the treatment plan and / or one or more characteristics of the treatment device 70. For example, the healthcare provider may review the treatment information and compare it to the treatment plan being implemented by the patient.

[0177] While the patient uses the treatment device 70, the healthcare provider may compare one or more parts or portions of predicted information regarding the patient's ability to implement the treatment plan with one or more corresponding parts or portions of measured information about the patient (e.g., as indicated by the treatment information) while the patient uses the treatment device 70 to implement the treatment plan. The predicted information may include one or more vital signs of the user, the user's respiratory rate, the user's heart rate, the user's body temperature, the user's blood pressure, other suitable information about the user, or a combination thereof. The healthcare provider may determine that the treatment plan is having the desired effect if one or more parts or portions of the measured information are within an acceptable range of one or more corresponding parts or portions of the predicted information. Conversely, the healthcare provider may determine that the treatment plan is not having the desired effect if one or more parts or portions of the measured information are outside an acceptable range of one or more corresponding parts or portions of the predicted information.

[0178] In some embodiments, while the patient is using the treatment device 70 to implement the treatment plan, the healthcare provider may compare each predicted characteristic of the treatment device 70 with the corresponding characteristic of the treatment device 70 indicated by the treatment information. For example, the healthcare provider may compare the predicted resistance setting of the treatment device 70 with the actual resistance setting of the treatment device 70 indicated by the treatment information.

[0179] The healthcare provider may determine that the patient is properly implementing the treatment plan if the actual characteristics of the treatment device 70 indicated by the treatment information are within the range of expected characteristics of the treatment device 70. Conversely, the healthcare provider may determine that the patient is not properly implementing the treatment plan if the actual characteristics of the treatment device 70 indicated by the treatment information are outside the range of expected characteristics of the treatment device 70.

[0180] If the healthcare provider determines that the treatment information indicates that the patient is properly implementing the treatment plan and / or that the treatment plan is having the desired effect, the healthcare provider may decide not to modify the treatment plan or one or more characteristics of the treatment device 70. Conversely, if the healthcare provider determines that the treatment information indicates that the patient is not properly implementing the treatment plan and / or that the treatment plan is not having the desired effect, the healthcare provider may decide to modify the treatment plan and / or one or more characteristics of the treatment device 70 while the user is using the treatment device 70 to implement the treatment plan.

[0181] In some embodiments, the server 30 may receive subsequent treatment data regarding the patient while the patient is implementing the modified treatment plan using the treatment device 70. For example, after a healthcare provider provides input to modify the treatment plan and / or control one or more characteristics of the treatment device 70, the patient may continue to implement the modified treatment plan using the treatment device 70. The subsequent treatment data may correspond to treatment data generated while the user is implementing the modified treatment plan using the treatment device 70. In some embodiments, the subsequent treatment data may correspond to treatment data generated while the patient continues to implement the treatment plan using the treatment device 70 after a healthcare provider receives the treatment information and decides not to modify the treatment plan and / or control one or more characteristics of the treatment device 70.

[0182] The server 30 may further modify the treatment plan and / or control one or more characteristics of the treatment device 70 based on subsequent treatment plan input received from the overview display 120. The subsequent treatment plan input may correspond to input provided by the healthcare provider in the overview display 120 in response to receiving and / or reviewing subsequent treatment information corresponding to the subsequent treatment data. It should be understood that the server 30 may continuously and / or periodically provide treatment information to the patient profile display 130 and / or other sections, portions, or components of the overview display 120 based on the treatment data received on a continuous and / or periodic basis.

[0183] A healthcare provider may continuously or periodically receive and / or review the treatment information while the user is implementing the treatment plan using the treatment device. The healthcare provider may determine whether to modify the treatment plan and / or control one or more characteristics of the treatment device based on one or more trends indicated by the continuously and / or periodically received treatment information. For example, the one or more trends may indicate an increase in heart rate or other applicable trend change that indicates the user is not properly implementing the treatment plan and / or that the user's implementation of the treatment plan is not having the desired effect.

[0184] FIG. 9 is a flow diagram generally illustrating a method 900 for monitoring the implementation of a treatment plan by a user using a treatment device and selectively modifying one or more characteristics of the treatment plan and treatment device, according to the present disclosure. Method 900 is performed by processing logic, which may include hardware (circuitry, dedicated logic, etc.), software (such as those executed on a general-purpose computer system or dedicated machine), or a combination of both. Method 900 and / or each of its individual functions, routines, subroutines, or operations may be performed by one or more processors of a computing device (e.g., any component of FIG. 1 , such as server 30 executing artificial intelligence engine 11). In some embodiments, method 900 may be performed by a single processing thread. Alternatively, method 900 may be performed by two or more processing threads, each thread implementing one or more individual functions, routines, subroutines, or operations of the method.

[0185] For ease of explanation, method 900 is depicted and described as a series of acts. However, acts in accordance with the present disclosure may be performed in various orders and / or simultaneously and / or with other acts not shown and described herein. For example, acts depicted in method 900 may be performed in combination with any other acts of any other method disclosed herein. Moreover, not all illustrated acts may be required to implement method 900 in accordance with the disclosed subject matter. Additionally, those skilled in the art will understand and appreciate that method 900 may alternatively be represented as a series of interrelated states via a state diagram or events.

[0186] At 902, the processing device may receive treatment data regarding a user implementing a treatment plan using a treatment device, such as treatment device 70. The treatment data may include characteristics of the user, measurement information about the user while the user is using treatment device 70, characteristics of treatment device 70, the treatment plan, other suitable data, or a combination thereof.

[0187] At 904, the processing device may generate treatment information using the treatment data. The treatment information may include a summary of the user's implementation of the treatment plan while using the treatment device 70. The treatment information may be formatted so that the treatment data is presentable on a computing device of a healthcare provider responsible for the user's implementation of the treatment plan.

[0188] At 906, the processing device may be configured to provide (e.g., store for access, make available, make accessible, transmit, etc.) the treatment information at the healthcare provider's computing device. At 908, the processing device may be configured to provide the treatment information at an interface of the healthcare provider's computing device. For example, the processing device may store the treatment information for access by the healthcare provider's computing device and / or communicate (e.g., transmit) the treatment information to the healthcare provider's computing device for display in the patient profile display 130 of the overview display 120. As described, the overview display 120 may be configured to receive input, such as a treatment plan input, indicating one or more modifications to the treatment plan and / or one or more characteristics of the treatment device 70. The healthcare provider may interact with various controls, input fields, and other aspects of the overview display 120 to provide the treatment plan input.

[0189] At 910, the processing device may modify the treatment plan in response to receiving the treatment plan input including at least one modification to the treatment plan. For example, the processing device may modify various features and characteristics of the treatment plan based on the at least one modification indicated by the treatment plan input.

[0190] At 912, the processing device may selectively control the therapy device 70 using the modified treatment plan. For example, the processing device may modify one or more characteristics of the therapy device 70 based on the modifications to the treatment plan. Additionally or alternatively, the processing device may adapt, modify, adjust, or otherwise control one or more characteristics based on the treatment plan input. For example, the treatment plan input may indicate at least one modification to one or more characteristics of the therapy device 70. The processing device may modify one or more characteristics of the therapy device 70 based on the at least one modification indicated by the treatment plan input.

[0191] 10 is a flow diagram generally illustrating an alternative method 1000 for monitoring the implementation of a treatment plan by a user using a treatment device and selectively modifying one or more characteristics of the treatment plan and the treatment device in accordance with the present disclosure. Method 1000 includes operations performed by a processor of a computing device (e.g., any component of FIG. 1 , such as server 30 executing artificial intelligence engine 11). In some embodiments, one or more operations of method 1000 are implemented in computer instructions stored on a memory device and executed by a processing device. Method 1000 may be performed in the same or similar manner as described above with respect to method 900. The operations of method 1000 may be performed in any combination with the operations of any of the methods described herein.

[0192] At 1002, the processing device may receive first treatment data regarding a user implementing a treatment plan using a treatment device, such as treatment device 70, during a telemedicine session. The first treatment data includes at least measurement information related to the user while the user implements the treatment plan using treatment device 70. The first treatment data may correspond to sensor data, such as sensor data 136, from one or more external sensors, such as external sensors 82, 84, 86, and / or from one or more internal sensors, such as internal sensor 76 of treatment device 70.

[0193] In some embodiments, at least a portion of the first therapy data may include sensor data from one or more sensors associated with one or more corresponding wearable devices worn by the user while using the therapy device 70. The one or more wearable devices may include a watch, a bracelet, a necklace, a chest strap, a head sweatband, a wrist sweatband, any other suitable sweatband, and other suitable wearable devices, or combinations thereof. The one or more wearable devices may be configured to monitor the user's heart rate, body temperature, blood pressure, one or more vital signs, etc. while the user is using the therapy device 70.

[0194] At 1004, the processing device may generate first treatment information using the first treatment data. The first treatment information may include a summary of the user's implementation of the treatment plan while using the treatment device 70. The first treatment information may be formatted such that the first treatment data is presentable on a computing device of a healthcare provider responsible for the user's implementation of the treatment plan.

[0195] At 1006, the processing device may be configured to write the first treatment information to an associated memory for access at the healthcare provider's computing device and / or provide the first treatment information at the healthcare provider's computing device. At 1008, the processing device may be configured to provide the first treatment information in an interface of the healthcare provider's computing device. For example, the processing device may be configured to provide the first treatment information in a patient profile display 130 of the overview display 120. As described, the overview display 120 may be configured to receive input, such as a treatment plan input, indicating one or more modifications to the treatment plan and / or one or more characteristics of the treatment device 70. The healthcare provider may interact with various controls, input fields, and other aspects of the overview display 120 to provide the treatment plan input.

[0196] At 1010, the processing device may receive a first treatment plan input in response to the first treatment information. The first treatment plan input may indicate at least one modification to the treatment plan. In some embodiments, the first treatment plan input may be provided by a healthcare provider, as described. In some embodiments, based on the first treatment information, the artificial intelligence engine 11 may generate the first treatment plan input.

[0197] At 1012, the processing device may modify the treatment plan in response to receiving the first treatment plan input including at least one modification to the treatment plan. For example, the processing device may modify various features and characteristics of the treatment plan based on the at least one modification indicated by the first treatment plan input.

[0198] At 1014, the processing device may selectively control the therapy device 70 using the modified treatment plan. For example, the processing device may modify one or more characteristics of the therapy device 70 based on the modifications to the treatment plan. Additionally or alternatively, the processing device may adapt, modify, adjust, or otherwise control one or more characteristics based on the first treatment plan input. For example, the first treatment plan input may indicate at least one modification to one or more characteristics of the therapy device 70. The processing device may modify one or more characteristics of the therapy device 70 based on the at least one modification indicated by the first treatment plan input.

[0199] At 1016, the processing device may receive a second treatment plan input in response to second treatment information generated using the second treatment data. For example, the processing device may receive second treatment data related to the user while the user is using the treatment device 70. The second treatment data may include treatment data received by the processing device after the first treatment data. In some embodiments, the second treatment data may relate to the user while the user is using the treatment device 70 to implement a revised treatment plan.

[0200] In some embodiments, the second treatment data may pertain to the user while the user is implementing the treatment plan using the treatment device 70 (e.g., when the healthcare provider does not modify the treatment plan, as described). The processing device may generate second treatment information based on the second treatment data. The processing device may receive second treatment plan input indicating at least one modification to the treatment plan.

[0201] As described, the processing device may be configured to provide the second treatment information to the patient profile display 130 and / or any other suitable section, portion, or component of the summary display 120, or any other suitable display or interface. The healthcare provider (e.g., and / or the artificial intelligence engine 11) may review the second treatment information and determine whether to modify and / or further revise the treatment plan based on the second treatment information.

[0202] At 1018, using the second treatment plan input, the processing device may modify the treatment plan. For example, the processing device may further modify (e.g., if the processing device has already modified the treatment plan) and / or modify (e.g., if the processing device has not previously modified the treatment plan) various features and characteristics of the treatment plan based on at least one modification indicated by the second treatment plan input.

[0203] At 1020, using the modified treatment plan, the processing device may selectively control the treatment device 70. For example, based on the modifications to the treatment plan, the processing device may modify one or more characteristics of the treatment device 70. Additionally or alternatively, the processing device may adapt, modify, adjust, or otherwise control one or more characteristics based on a second treatment plan input. For example, the second treatment plan input may indicate at least one modification to one or more characteristics of the treatment device 70. The processing device may modify one or more characteristics of the treatment device 70 based on the at least one modification indicated by the second treatment plan input.

[0204] 11 is a flow diagram generally illustrating an alternative method 1100 for monitoring the implementation of a treatment plan by a user using a treatment device and selectively modifying one or more characteristics of the treatment plan and the treatment device in accordance with the present disclosure. Method 1100 includes operations performed by a processor of a computing device (e.g., any component of FIG. 1 , such as server 30 executing artificial intelligence engine 11). In some embodiments, one or more operations of method 1100 are implemented in computer instructions stored on a memory device and executed by a processing device. Method 1100 may be performed in the same or similar manner as described above with respect to methods 900 and / or 1000. The operations of method 1100 may be performed in any combination with the operations of any of the methods described herein.

[0205] At 1102, the processing device may receive therapy data regarding a user implementing a therapy regimen using a therapy device, such as therapy device 70. The therapy data may include any of the data described herein. The therapy data may correspond to sensor data, such as sensor data 136, from one or more external sensors, such as external sensors 82, 84, 86, and / or from one or more internal sensors, such as internal sensor 76 of therapy device 70. In some embodiments, at least a portion of the therapy data may include sensor data from one or more sensors associated with one or more corresponding wearable devices worn by the user while using therapy device 70. The one or more wearable devices may include a watch, a bracelet, a necklace, a chest strap, a head sweatband, a wrist sweatband, any other suitable sweatband, and any other suitable wearable device, or a combination thereof. The one or more wearable devices may be configured to monitor the user's heart rate, body temperature, blood pressure, one or more vital signs, etc., while the user is using therapy device 70.

[0206] At 1104, the processing device may generate treatment information using the treatment data. The treatment information may include a summary of the user's implementation of the treatment plan while using the treatment device 70. The treatment information may be formatted so that the treatment data is presentable on a computing device of a healthcare provider responsible for the user's implementation of the treatment plan.

[0207] At 1106, the processing device may be configured to provide the treatment information to at least one of a healthcare provider's computing device and a machine learning model executed by the artificial intelligence engine 11.

[0208] At 1108, the processing device may receive a treatment plan input in response to the treatment information. The treatment plan input may indicate at least one modification to the treatment plan. In some embodiments, the treatment plan input may be provided by a healthcare provider, as described. In some embodiments, based on the treatment information, the artificial intelligence engine 11 executing a machine learning model may generate the treatment plan input.

[0209] At 1110, the processing device determines whether the treatment plan input indicates at least one modification to the treatment plan. If the processing device determines that the treatment plan input does not indicate at least one modification to the treatment plan, the processing device returns to 1102 and continues receiving treatment data for the user while the user implements the treatment plan using the treatment device 70. If the processing device determines that the treatment plan input indicates at least one modification to the treatment plan, the processing device continues at 1112.

[0210] At 1112, using the treatment plan input, the processing device may modify the treatment plan. For example, using at least one modification to the treatment plan indicated by the treatment plan input, the processing device may modify the treatment plan. Based on the at least one modification indicated by the treatment plan input, the treatment device may modify various features and characteristics of the treatment plan.

[0211] At 1114, using the modified treatment plan, the processing device may selectively control the treatment device 70. For example, based on at least one modification to the treatment plan, the processing device may modify one or more characteristics of the treatment device 70. Additionally or alternatively, the processing device may adapt, modify, adjust, or otherwise control one or more characteristics based on the treatment plan input. For example, the treatment plan input may indicate at least one modification to one or more characteristics of the treatment device 70. Based on the at least one modification indicated by the treatment plan input, the processing device may modify one or more characteristics of the treatment device 70. The processing device may return to 1102 and continue to receive treatment data about the user while the user implements the treatment plan using the treatment device 70.

[0212] 12 generally illustrates an exemplary computer system 1200 capable of performing any one or more of the methods described herein, according to one or more aspects of the present disclosure. In one example, computer system 1200 includes a computing device and may correspond to assistance interface 94, reporting interface 92, supervisory interface 90, clinician interface 20, server 30 (including AI engine 11), patient interface 50, gait sensor 82, goniometer 84, treatment device 70, pressure sensor 86, or any suitable component of FIG. 1 . Computer system 1200 may be capable of executing instructions implementing one or more machine learning models 13 of artificial intelligence engine 11 of FIG. 1 . The computer system may be connected (e.g., networked) to other computer systems within a LAN, an intranet, an extranet, or the Internet, including via a cloud or peer-to-peer network.

[0213] The computer system may operate in the capacity of a server in a client-server network environment. The computer system may be a personal computer (PC), a tablet computer, a wearable (e.g., a wristband), a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a camera, a video camera, an Internet of Things (IoT) device, or any device capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by the device. Furthermore, while only a single computer system is illustrated, the term "computer" shall also be taken to include any collection of computers individually or collectively executing an instruction set (or sets) to perform any one or more of the methodologies discussed herein.

[0214] The computer system 1200 includes a processing device 1202, a main memory 1204 (e.g., read-only memory (ROM), flash memory, solid-state drive (SSD), dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM)), a static memory 1206 (e.g., flash memory, solid-state drive (SSD), static random access memory (SRAM)), and a data storage device 1208, which communicate with each other via a bus 1110.

[0215] Processing device 1202 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, etc. More specifically, processing device 1202 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor implementing other instruction sets or a combination of instruction sets. Processing device 1402 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a system-on-a-chip, a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, etc. Processing device 1402 is configured to execute instructions to perform any of the operations and steps discussed herein.

[0216] Computer system 1200 may further include a network interface device 1212. Computer system 1200 may also include a video display 1214 (e.g., a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), a quantum LED, a cathode ray tube (CRT), a shadow mask CRT, an aperture grill CRT, a monochrome CRT), one or more input devices 1216 (e.g., a keyboard and / or mouse, or game-like controls), and one or more speakers 1218 (e.g., speakers). In one exemplary embodiment, video display 1214 and input device 1216 may be combined into a single component or device (e.g., an LCD touchscreen).

[0217] The data storage device 1216 may include a computer-readable medium 1220 having stored thereon instructions 1222 that embody any one or more of the methods, operations, or functions described herein. The instructions 1222 may also reside, completely or at least partially, within the main memory 1204 and / or within the processing device 1202 during execution of the instructions 1222 by the computer system 1200. Thus, the main memory 1204 and the processing device 1202 also constitute computer-readable media. The instructions 1222 may further be transmitted or received over a network via the network interface device 1212.

[0218] Although the computer-readable storage medium 1220 is generally illustrated in the exemplary embodiments as being a single medium, the term "computer-readable storage medium" should be taken to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store one or more sets of instructions. The term "computer-readable storage medium" should also be taken to include any medium that can store, encode, or carry a set of instructions for execution by a machine and cause the machine to perform any one or more of the methodologies of the present disclosure. Accordingly, the term "computer-readable storage medium" should be taken to include, but is not limited to, solid-state memory, optical media, and magnetic media.

[0219] Determining an optimal treatment plan for a patient with particular characteristics (e.g., demographic, geographic, diagnostic, measurement-based or test-based, medical history, etiological, cohort-related, differential diagnosis, surgical, physical therapy, pharmacological, and recommended other treatments, etc.) can be a technically challenging problem. For example, a large amount of information may be considered when determining a treatment plan, which can lead to inefficiency and inaccuracy in the treatment plan selection process. In a rehabilitation setting, some of the large amount of information considered may include the patient's type of injury, the type of medical treatment available to be performed, the treatment regimen, the drug regimen, and patient characteristics. Patient characteristics may be broad and may include the patient's medications, the patient's previous injuries, previous medical treatments performed on the patient, patient measurements (e.g., body fat, weight, etc.), the patient's allergies, the patient's medical condition, patient historical information, the patient's vital signs (e.g., temperature, blood pressure, heart rate), the patient's symptoms, the patient's family's medical information, etc.

[0220] Furthermore, in addition to the information described above, it may be desirable to consider additional historical information, such as clinical information regarding the results of treatment plans implemented on other people using the treatment device. Clinical information may include clinical studies, clinical trials, evidence-based guidelines, journal articles, meta-analyses, etc. Clinical information may be written by people with particular professional status (e.g., medical doctor, osteopathic doctor, physical therapist, etc.), certifications, etc. Clinical information may be obtained from any suitable data source.

[0221] In some embodiments, the clinical information may describe people seeking treatment for a particular ailment (e.g., an injury, a disease, any applicable medical condition, etc.). The clinical information may describe that a particular result will be obtained if people implement or when implement a particular treatment plan (e.g., a medical procedure, a treatment protocol using a treatment device, a drug regimen, a dietary regimen, etc.) for the people. The clinical information may also include particular characteristics of the described people. Direct or indirect references may be made to the values of the characteristics in the clinical information. It may be desirable to compare the patient's characteristics with the characteristics of the people in the clinical information to determine what the patient's optimal treatment plan is so that the patient can achieve the desired result. Processing this historical information may be computationally cumbersome, inefficient, and / or impractical using conventional techniques.

[0222] Accordingly, embodiments of the present disclosure relate to recommending optimal treatment plans using real-time and historical data correlation with patient cohort-equivalent databases. In some embodiments, an artificial intelligence engine can be trained to recommend optimal treatment plans based on patient characteristics and clinical information. For example, the artificial intelligence engine can be trained to match patterns between patient and population characteristics in various clinical information. Based on the patterns, the artificial intelligence engine can generate a treatment plan for the patient, and whether such treatment plan produced a desired outcome for a similarly matched person or similarly matched people's clinical information. In that sense, the generated treatment plan can be "optimal" based on the desired outcome (e.g., speed, effectiveness, both speed and effectiveness, life expectancy, etc.). In other words, based on the patient's characteristics, there may be specific medical procedures, specific medications, specific rehabilitation exercises, etc. that should be included in the optimal treatment plan to achieve the desired outcome.

[0223] Depending on what outcome is desired, the artificial intelligence engine can be trained to output several optimal or optimized treatment plans. For example, one outcome may include recovery to a threshold level (e.g., 75% range of motion) in the fastest amount of time, while another outcome may include full recovery (e.g., 100% range of motion) regardless of the amount of time. Clinical information may indicate that a first treatment plan provides a first outcome for people with similar characteristics to the patient's, and that a second treatment plan provides a second outcome for people with similar characteristics to the patient.

[0224] Additionally, the artificial intelligence engine may also be trained to output treatment plans that are not optimal for a patient (referred to as "precluded treatment plans"). For example, if a patient has diabetes, a particular medication may not be approved or suitable for the patient, and that medication may be flagged as a precluded treatment plan for the patient.

[0225] As discussed above, processing patient and clinical information in real time may be impractical using conventional techniques, particularly due to the volume of data to be processed. Accordingly, in some embodiments, received clinical and / or patient information may be converted into a medical description language. A medical description language may refer to a coding configured to be efficiently processed by an artificial intelligence engine. For example, clinical test results may be received and interpreted, optionally with the addition of an attribute grammar, and keywords related to the target information may then be searched for. Values of the target information may be identified. A canonical form defined by the medical description language may be defined and / or generated, including tags that identify values of the target information and, optionally, tags that implement the attribute grammar of the medical description language.

[0226] A medical description language may be extensible and include any properties of object-oriented or artificial intelligence programming languages. A medical description language may define other methods or procedures. A medical description language may implement the concept of an "object," which can contain data in the form of fields (often known as attributes or properties) and code in the form of procedures (often known as methods). A medical description language may encapsulate data and functions that manipulate the data to protect it from interference and misuse. A medical description language may also implement data hiding or obfuscation, which prevents certain aspects of data or functions from being accessible to another component. A medical description language may implement inheritance, which arranges components as an "is a type of" relationship, such that if a first component can be a kind of a second component, the first component inherits the functions and data of the second component. A medical description language may also implement polymorphism, which is the provision of a single interface to different types of components.

[0227] The clinical information may be converted into a medical description language before the artificial intelligence engine determines the optimal treatment plan and / or the excluded treatment plan. The artificial intelligence engine may be trained by using the medical description language that represents the clinical information so that the artificial intelligence engine can more efficiently determine the optimal treatment plan without using the initial data format in which the clinical information is received. Furthermore, the artificial intelligence engine may receive the clinical information continuously or intermittently, and the clinical information may be included in the training data to update the artificial intelligence engine.

[0228] In some embodiments, the optimal treatment plan and / or the rejected treatment plan may be presented to a healthcare professional. The healthcare professional may select a particular optimal treatment plan and have that treatment plan transmitted to the patient. In some embodiments, an artificial intelligence engine may receive and / or operate remotely from the source of clinical information and / or remotely from the patient to facilitate telehealth or telemedicine applications, including remote diagnosis, treatment plan determination, and rehabilitation and / or pharmacological prescription. In such cases, the recommended treatment plan and / or the rejected treatment plan may be presented simultaneously with a video of the patient in real time during the telemedicine or telehealth session on the user interface of the healthcare professional's computing device. The video may also be accompanied by audio, text, and other multimedia information. Real time may refer to less than two seconds.

[0229] Presenting the treatment plan generated by the artificial intelligence engine simultaneously with the presentation of the patient video may provide an enhanced user interface because the healthcare professional can continue to visually and / or otherwise communicate with the patient while also reviewing the treatment plan on the same user interface. The enhanced user interface may improve the healthcare professional's experience using the computing device and encourage the healthcare professional to reuse the user interface. Such technology may also reduce computing resources (e.g., processing, memory, network) because the healthcare professional does not need to switch to a separate user interface screen and enter a query for a recommended treatment plan based on patient characteristics. The artificial intelligence engine dynamically provides optimal and rejected treatment plans on the fly.

[0230] In some embodiments, the therapy device may be adaptive and / or personalized, such that the properties, configuration, and location of the therapy device may be adapted to the needs of a particular patient. For example, pedals may be dynamically adjusted on the fly (e.g., based on programmed configuration via a telemedicine session or in response to the detection of specific measurements) to increase or decrease range of motion to comply with a therapy plan designed for the user. Such adaptive properties may improve patient recovery outcomes.

[0231] Clause 1. A method comprising: receiving treatment data regarding a user implementing a treatment plan using a treatment device, the treatment data including at least one of characteristics of the user, measurement information about the user while the user uses the treatment device, characteristics of the treatment device, and at least one aspect of the treatment plan; generating treatment information using the treatment data; writing the treatment information to an associated memory for access at a healthcare provider's computing device; communicating at the healthcare provider's computing device with an interface, the interface configured to receive treatment plan input; and modifying at least one aspect of the treatment plan in response to receiving the treatment plan input including at least one modification to at least one aspect of the treatment plan.

[0232] Clause 2. The method of any clause herein, further comprising controlling the treatment device based on the modified at least one aspect of the treatment plan while the user is using the treatment device.

[0233] Clause 3. The method of any clause herein, further comprising controlling the treatment device based on the modified at least one aspect of the treatment plan while the user is using the treatment device during the telemedicine session.

[0234] Clause 4. The method of any clause herein, wherein the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

[0235] Clause 5. The method of any clause herein, wherein at least a portion of the therapy data corresponds to sensor data from a sensor associated with the therapy device.

[0236] Clause 6. The method of any clause herein, wherein at least a portion of the therapeutic data corresponds to sensor data from a sensor associated with a wearable device worn by the user while using the therapeutic device.

[0237] Clause 7. The method of any clause herein, further comprising receiving subsequent treatment data about the user while the user is implementing the treatment plan using the treatment device.

[0238] Clause 8. The method of any clause herein, further comprising modifying the modified treatment plan in response to receiving a subsequent treatment plan input including at least one further modification to the modified at least one aspect of the treatment plan, wherein the subsequent treatment plan input is based on at least one of the treatment data and the subsequent treatment data.

[0239] Clause 9. A tangible, non-transitory computer-readable medium storing instructions that, when executed, cause a processing device to: receive treatment data about a user implementing a treatment plan using a treatment device, the treatment data including at least one of characteristics of the user, measurement information about the user while the user uses the treatment device, characteristics of the treatment device, and at least one aspect of the treatment plan; generate treatment information using the treatment data; write the treatment information to an associated memory for access at a healthcare provider's computing device; and communicate at the healthcare provider's computing device with an interface, the interface configured to receive treatment plan input; and modify at least one aspect of the treatment plan in response to receiving the treatment plan input including at least one modification to the treatment plan.

[0240] Clause 10. The computer-readable medium of any clause herein, wherein the processing device is further configured to control the treatment device based on at least one aspect of the modified treatment plan while the user is using the treatment device.

[0241] Clause 11. The computer-readable medium of any clause herein, wherein the processing device is further configured to control the treatment device based on at least one aspect of the modified treatment plan while the user uses the treatment device during the telemedicine session.

[0242] Clause 12. A computer-readable medium as described in any clause herein, wherein the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

[0243] Clause 13. The computer-readable medium of any clause herein, wherein at least a portion of the treatment data corresponds to sensor data from a sensor associated with a treatment device.

[0244] Clause 14. The computer-readable medium of any clause herein, wherein at least a portion of the therapeutic data corresponds to sensor data from a sensor associated with a wearable device worn by a user while using the therapeutic device.

[0245] Clause 15. The computer-readable medium of any clause herein, wherein the processing device is further configured to receive subsequent treatment data about the user while the user implements the treatment plan using the treatment device.

[0246] Clause 16. A computer-readable medium as described in any clause herein, wherein the processing device is further configured to modify at least one aspect of the modified treatment plan in response to receiving a subsequent treatment plan input including at least one further modification to the treatment plan, the subsequent treatment plan input being based on at least one of the treatment data and the subsequent treatment data.

[0247] Clause 17. A system comprising: a memory device storing instructions; and a processing device communicatively coupled to the memory device, the processing device executing the instructions to receive treatment data about a user implementing a treatment plan using a treatment device, the treatment data including at least one of characteristics of the user, measurement information about the user while the user uses the treatment device, characteristics of the treatment device, and at least one aspect of the treatment plan; generate treatment information using the treatment data; write the treatment information to an associated memory for access at a healthcare provider's computing device; and communicate with an interface at the healthcare provider's computing device, the interface configured to receive treatment plan input; and modify at least one aspect of the treatment plan in response to receiving the treatment plan input including at least one modification to the treatment plan.

[0248] Clause 18. The system of any clause herein, wherein the processing device is further configured to control the treatment device based on at least one aspect of the modified treatment plan while the user is using the treatment device.

[0249] Clause 19. The system of any clause herein, wherein the processing device is further configured to control the treatment device based on at least one aspect of the modified treatment plan while the user uses the treatment device during the telemedicine session.

[0250] Clause 20. A system described in any clause herein, wherein the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

[0251] Clause 21. The system of any clause herein, wherein at least a portion of the treatment data corresponds to sensor data from a sensor associated with the treatment device.

[0252] Clause 22. The system of any clause herein, wherein at least a portion of the therapeutic data corresponds to sensor data from a sensor associated with a wearable device worn by the user while using the therapeutic device.

[0253] Clause 23. The system of any clause herein, wherein the processing device is further configured to receive subsequent treatment data about the user while the user implements the treatment plan using the treatment device.

[0254] Clause 24. The system of any clause herein, wherein the processing device is further configured to modify at least one of the modified at least one aspect of the treatment plan and any other aspects in response to receiving a subsequent treatment plan input including at least one further modification to the treatment plan, wherein the subsequent treatment plan input is based on at least one of the treatment data and the subsequent treatment data.

[0255] Method and system for describing and recommending optimal treatment plans in an adaptive telemedicine or other context FIG. 13 shows a block diagram of a computer-implemented system 2010 for managing a treatment plan, hereafter referred to as the “system.” Managing a treatment plan may include using an artificial intelligence engine to recommend an optimal treatment plan and / or eliminate treatment plans that should not be recommended for the patient. A treatment plan may include one or more treatment protocols, each including one or more treatment sessions. Each treatment session includes several session periods, each including specific activities for treating a body part of the patient. For example, a treatment plan for post-operative rehabilitation after knee surgery may include an initial treatment protocol with two stretching sessions per day for the first three days after surgery and a more intensive treatment protocol with active exercise sessions performed four times per day starting on the fourth day after surgery. The treatment plan may also include information regarding medical procedures to be performed on the patient, the patient's treatment protocol using a treatment device, the patient's dietary regimen, the patient's drug regimen, the patient's sleep regimen, supplemental regimens, or any combination thereof.

[0256] The system 2010 also includes a server 2030 configured to store and provide data related to managing the treatment plan. The server 2030 may include one or more computers and may take the form of one or more distributed and / or virtualized computers. The server 2030 also includes a first communication interface 2032 configured to communicate with the clinician interface 2020 via a first network 2034. In some embodiments, the first network 2034 may include a wired and / or wireless network connection, such as Wi-Fi, Bluetooth, ZigBee, near field communication (NFC), a cellular data network, or the like. The server 2030 includes a first processor 2036 and a first machine-readable storage memory 2038, which may be referred to for short as “memory,” and which retains first instructions 2040 for carrying out various actions of the server 2030 for execution by the first processor 2036. The server 2030 is configured to store data related to the treatment plan. For example, memory 2038 includes a system data store 2042 configured to hold system data, such as data regarding a treatment plan for treating one or more patients. Server 2030 is also configured to store data regarding patient performance according to the treatment plan. For example, memory 2038 includes a patient data store 2044 configured to hold patient data, such as data regarding one or more patients, including data describing each patient's performance within the treatment plan.

[0257] Additionally, characteristics of people, the treatment plans they follow, their level of compliance with the treatment plans, and the outcomes of the treatment plans may be used to separate the treatment plans into databases corresponding to different patient cohorts within the patient data store 2044 using correlations and other statistical or probabilistic measures. For example, data for a first cohort of first patients having a first similar injury, a first similar medical condition, a first similar medical procedure performed, a first treatment plan followed by the first patient, and a first outcome of the treatment plan may be stored in a first patient database. Data for a second cohort of second patients having a second similar injury, a second similar medical condition, a second similar medical procedure performed, a second treatment plan followed by the second patient, and a second outcome of the treatment plan may be stored in a second patient database. Any combination of characteristics may be used to separate patient cohorts. In some embodiments, different cohorts of patients may be stored in different partitions or volumes of the same database.

[0258] This characteristic data, treatment plan data, and outcome data may be obtained from clinical information describing characteristics of people who have undergone particular treatment plans and the results of those treatment plans. The characteristic data, treatment plan data, and outcome data may be correlated in a patient-cohort database in patient data store 2044. The characteristics of people may include medications prescribed for people, injuries to people, medical procedures performed on people, measurements of people, allergies to people, medical conditions of people, historical information of people, vital signs of people, symptoms of people, medical information of people's family, other information of people, or some combination thereof.

[0259] In addition to historical information about other people stored in patient cohort-equivalent databases, real-time information about the current patient being treated based on current patient characteristics may be stored in appropriate patient cohort-equivalent databases. Patient characteristics may include patient medications, patient injuries, medical procedures performed on the patient, patient measurements, patient allergies, patient medical conditions, patient historical information, patient vital signs, patient symptoms, medical information of the patient's family, other patient information, or any combination thereof.

[0260] In some embodiments, the server 2030 may implement an artificial intelligence (AI) engine 2011 that uses one or more machine learning models 2013 to implement at least one of the embodiments disclosed herein. The server 2030 may include a training engine 209 that can generate the one or more machine learning models 2013. The machine learning models 2013 may be trained to generate and recommend optimal treatment plans using, among other things, real-time and historical data correlations, including those representing patient cohorts. The one or more machine learning models 2013 may be generated by the training engine 209 and implemented in computer instructions executable by the training engine 209 and / or one or more processing devices of the server 2030. To generate the one or more machine learning models 2013, the training engine 209 may train the one or more machine learning models 2013. The one or more machine learning models 2013 may be used by the artificial intelligence engine 2011.

[0261] The training engine 209 may be a rack-mounted server, a router computer, a personal computer, a portable digital assistant, a smartphone, a laptop computer, a tablet computer, a netbook, a desktop computer, an Internet of Things (IoT) device, any other desired computing device, or any combination of the above. The training engine 9 may also be a cloud-based or real-time software platform and may include privacy and / or security software or protocols.

[0262] To train one or more machine learning models 2013, the training engine 209 may identify clinical information using a training dataset of a corpus of keywords representing the target information. The training dataset may also include a corpus of clinical information (e.g., clinical trials, meta-analyses, evidence-based guidelines, journal articles, etc.) having a first data format. The clinical information may include, among other things, characteristics of people, treatment plans followed by people, and outcomes of the treatment plans. The training dataset may also include an example medical description language including tags of the target information, telemedicine information, and values embedded with the tags. One or more machine learning models may be trained to convert the clinical information from the first data format to a machine description language having a canonical (e.g., tag-value pair and / or attribute grammar) format. Training may be performed by identifying keywords of the target information, identifying values of the keywords, and generating canonical values including the tags of the target information and the values of the target information.

[0263] One or more machine learning models 2013 may also be trained to convert patient characteristics received in real time (e.g., from an electronic medical record (EMR) system) into a medical description language for storage in an appropriate patient cohort equivalent database. One or more machine learning models 2013 may be trained to match patterns of patient characteristics described by the medical description language with characteristics of other people described by medical description languages representing clinical information. In some embodiments, the medical description languages representing clinical information may be stored in various patient cohort equivalent databases in the patient data store 2044. Thus, in some embodiments, one or more machine learning models 2013 may access the patient cohort equivalent databases when training or when recommending optimal treatment plans for patients. Computing resources, processing efficiency, accuracy, and error minimization may be enhanced by using a medical description language in canonical form, as opposed to the full body of text and / or EMR records. In particular, precision may be improved and errors minimized through the use of formal medical description language that can be interpreted to have one meaning, whereas informal descriptions may result in two or more, potentially semantically overloaded and unresolvable meanings.

[0264] Different machine learning models 2013 may be trained to recommend different optimal treatment plans for different desired outcomes. For example, one machine learning model may be trained to recommend an optimal treatment plan for the most effective recovery, while another machine learning model may be trained to recommend an optimal treatment plan based on speed of recovery.

[0265] Using training data including training inputs and corresponding target outputs, one or more machine learning models 2013 may reference model artifacts created by the training engine 209. The training engine 209 may find patterns in the training data that map training inputs to target outputs and generate machine learning models 2013 that capture these patterns. In some embodiments, the artificial intelligence engine 2011, database 2033, and / or training engine 209 may reside in another component depicted in FIG. 13 (e.g., assistant interface 2094, clinician interface 2020, etc.).

[0266] As described in more detail below, the one or more machine learning models 2013 may include, for example, a single level of linear or nonlinear operations (e.g., a support vector machine (SVM)), or the machine learning model 2013 may be a deep network, i.e., a machine learning model that includes multiple levels of nonlinear operations. Examples of deep networks are neural networks (e.g., each neuron may transmit its output signal to the input of the remaining neurons and to itself), including generative adversarial networks, convolutional neural networks, recurrent neural networks with one or more hidden layers, and fully connected neural networks. For example, a machine learning model may include multiple layers and / or hidden layers that perform calculations (e.g., dot products) using various neurons.

[0267] The system 2010 also includes a patient interface 2050 configured to communicate information to and receive feedback from the patient. Specifically, the patient interface includes an input device 2052 and an output device 2054, which may be collectively referred to as a patient user interface 2052, 2054. The input device 2052 may include one or more devices, such as a keyboard, a mouse, a touchscreen input, a gesture sensor, and / or a microphone and processor configured for voice recognition. The output device 2054 may take one or more different forms, including, for example, a computer monitor or display screen on a tablet, smartphone, or smartwatch. The output device 2054 may include other hardware and / or software components, such as a projector, virtual reality capabilities, augmented reality capabilities, etc. The output device 2054 may incorporate a variety of different visual, audio, or other presentation technologies. For example, output device(s) 2054 may include non-visual displays, such as audio signals that may include speech and / or other sounds, such as tones, chimes, and / or melodies, that may signal various conditions and / or directions. Output device(s) 2054 may comprise one or more different display screens that present various data and / or interfaces or controls for use by the patient. Output device(s) 2054 may also include graphics, which may be presented by a web-based interface and / or by a computer program or application (app).

[0268] 13 , the patient interface 2050 includes a second communication interface 2056, which may also be referred to as a remote communication interface, configured to communicate with the server 2030 and / or the clinician interface 2020 via a second network 2058. In some embodiments, the second network 2058 may include a local area network (LAN), such as an Ethernet network. In some embodiments, the second network 2058 may include the Internet, and communications between the patient interface 2050 and the server 2030 and / or the clinician interface 2020 may be secured via encryption, such as by using a virtual private network (VPN). In some embodiments, the second network 2058 may include wired and / or wireless network connections, such as Wi-Fi, Bluetooth, ZigBee, near field communication (NFC), cellular data networks, etc. In some embodiments, the second network 2058 may be the same as the first network 2034 and / or may be operatively coupled to the first network 2034.

[0269] The patient interface 2050 includes a second processor 2060 and a second machine-readable storage memory 2062 that holds second instructions 2064 for execution by the second processor 2060 to perform various actions of the patient interface 2050. The second machine-readable storage memory 2062 also includes a local data store 2066 configured to hold patient data, such as data related to a treatment plan and / or data representative of the patient's performance within the treatment plan. The patient interface 2050 also includes a local communication interface 2068 configured to communicate with various devices for use by the patient in proximity of the patient interface 2050. The local communication interface 2068 may include wired and / or wireless communication. In some embodiments, the local communication interface 2068 may include a local wireless network, such as Wi-Fi, Bluetooth, ZigBee, near field communication (NFC), a cellular data network, or the like.

[0270] The system 2010 also includes a therapy device 2070 configured to be operated by the patient and / or to manipulate a body part of the patient to perform activities according to the therapy plan. In some embodiments, the therapy device 2070 may take the form of an exercise and rehabilitation device configured to administer and / or assist in administering a rehabilitation regimen, which may be an orthopedic rehabilitation regimen, and the therapy includes rehabilitation of a body part of the patient, such as a joint, bone, or muscle group. The body part may include, for example, the spine, hand, foot, knee, or shoulder. The body part may include a portion of a joint, bone, or muscle group, such as one or more vertebrae, tendons, or ligaments. As shown in FIG. 13 , the therapy device 2070 includes a controller 2072, which may include one or more processors, computer memory, and / or other components. The therapy device 2070 also includes a fourth communication interface 2074 configured to communicate with the patient interface 2050 via the local communication interface 2068. The treatment device 2070 also includes one or more internal sensors 2076 and an actuator 2078, such as a motor, which may be used, for example, to move a body part of the patient and / or to resist forces exerted by the patient.

[0271] The internal sensor 2076 may measure one or more motion characteristics of the treatment device 2070, such as, for example, force, position, speed, and / or velocity. In some embodiments, the internal sensor 2076 may include a position sensor configured to measure at least one of linear or angular motion of a patient's body part. For example, the internal sensor 2076 in the form of a position sensor may measure a distance that a patient can move a portion of the treatment device 2070, and such distance may correspond to a range of motion that the patient's body part can achieve. In some embodiments, the internal sensor 2076 may include a force sensor configured to measure a force applied by the patient. For example, the internal sensor 2076 in the form of a force sensor may measure a force or load that a patient can apply to the treatment device 2070 using a particular body part.

[0272] 13 also includes an gait sensor 2082 that communicates with the server 2030 via the local communication interface 2068 of the patient interface 2050. The gait sensor 2082 may track and store the number of steps taken by the patient. In some embodiments, the gait sensor 2082 may take the form of a wristband, a wristwatch, or a smartwatch. In some embodiments, the gait sensor 2082 may be integrated into a phone, such as a smartphone.

[0273] 13 also includes a goniometer 2084 that communicates with the server 2030 via the local communication interface 2068 of the patient interface 2050. The goniometer 2084 measures the angle of a patient's body part. For example, the goniometer 2084 may measure the angle of flexion of the patient's knee, elbow, or shoulder.

[0274] 13 also includes a pressure sensor 2086 in communication with the server 2030 via the local communication interface 68 of the patient interface 2050. The pressure sensor 2086 measures the amount of pressure or load exerted by a body part of the patient. For example, the pressure sensor 2086 may measure the amount of force exerted by the patient's feet when pedaling a stationary bicycle.

[0275] 13 also includes a supervisory interface 2090, which may be similar to or identical to clinician interface 2020. In some embodiments, supervisory interface 2090 may have enhanced functionality than that provided in clinician interface 2020. Supervisory interface 2090 may be configured for use by someone responsible for treatment planning, such as an orthopedic surgeon.

[0276] The system 2010 shown in FIG. 13 also includes a reporting interface 2092, which may be similar or identical to the clinician interface 2020. In some embodiments, the reporting interface 2092 may have less functionality than that provided in the clinician interface 2020. For example, the reporting interface 2092 may not have the ability to modify a treatment plan. Such a reporting interface 2092 may be used, for example, by a biller to determine use of the system 2010 for billing purposes. In another example, the reporting interface 2092 may not have the ability to display patient-identifiable information and may present only depersonalized and / or anonymized data for certain data fields related to the data subject and / or for certain data fields related to the data subject's quasi-identifiers. Such a reporting interface 2092 may be used, for example, by researchers to determine the varying effects of treatment plans on various patients.

[0277] The system 2010 includes an assistant interface 2094 for an assistant, such as a doctor, nurse, physical therapist, or technician, to remotely communicate with the patient interface 2050 and / or the therapy device 2070. Such remote communication may allow the assistant to provide assistance or guidance to a patient using the system 2010. More specifically, the assistant interface 2094 is configured to communicate telemedicine signals 2096, 2097, 2098a, 2098b, 2099a, 2099b with the patient interface 2050 via a network connection, such as via the first network 2034 and / or the second network 2058. The telemedicine signals 2096, 2097, 2098a, 2098b, 2099a, 2099b include one of an audio signal 2096, an audiovisual signal 2097, an interface control signal 2098a for controlling a function of the patient interface 2050, an interface monitor signal 2098b for monitoring a status of the patient interface 2050, an device control signal 2099a for altering an operating parameter of the therapy device 2070, and / or an device monitor signal 2099b for monitoring a status of the therapy device 2070. In some embodiments, each of the control signals 2098a, 2099a is unidirectional and may communicate a command from the assistant interface 2094 to the patient interface 2050. In some embodiments, an acknowledgement message may be sent from the patient interface 2050 to the assistant interface 2094 in response to successfully receiving the control signal 2098a, 2099a and / or communicating successful and / or unsuccessful implementation of the requested control action. In some embodiments, each of the monitor signals 2098b, 2099b can be a one-way status information command from the patient interface 2050 to the assistant interface 2094. In some embodiments, an acknowledgement message can be sent from the assistant interface 2094 to the patient interface 2050 in response to successfully receiving one of the monitor signals 2098b, 2099b.

[0278] In some embodiments, the patient interface 2050 can be configured as a pass-through for device control signals 2099a and device monitor signals 2099b between the therapy device 2070 and one or more other devices, such as the assistant interface 2094 and / or the server 2030. For example, the patient interface 2050 can be configured to transmit the device control signal 2099a in response to the device control signal 2099a in the telemedicine signals 2096, 2097, 2098a, 2098b, 2099a, 2099b from the assistant interface 2094.

[0279] In some embodiments, the assistant interface 2094 can be presented on a shared physical device as the clinician interface 2020. For example, the clinician interface 2020 can include one or more screens that implement the assistant interface 2094. Alternatively or additionally, the clinician interface 2020 can include additional hardware components, such as a video camera, a speaker, and / or a microphone, for implementing aspects of the assistant interface 2094.

[0280] In some embodiments, one or more portions of the telemedicine signals 2096, 2097, 2098a, 2098b, 2099a, 2099b may be generated from a pre-recorded source (e.g., an audio recording, a video recording, or an animation) for presentation by the output device 2054 of the patient interface 2050. For example, a tutorial video may be streamed from the server 2030 and presented on the patient interface 2050. Content from a pre-recorded source may be requested by the patient via the patient interface 2050. Alternatively, via controls on the assistant interface 2094, the assistant may play content from a pre-recorded source on the patient interface 2050.

[0281] Assistant interface 2094 includes assistant input device 2022 and assistant display 2024, which may collectively be referred to as assistant user interface 2022, 2024. Assistant input device 2022 may include, for example, one or more of a phone, a keyboard, a mouse, a trackpad, or a touchscreen. Alternatively or additionally, assistant input device 2022 may include one or more microphones. In some embodiments, the one or more microphones may take the form of a phone handset, a headset, or one or more wide-range microphones configured for the assistant to speak to the patient via patient interface 2050. In some embodiments, assistant input device 2022 may have hardware and / or software configured to interpret commands spoken by the assistant using the one or more microphones and be configured to provide voice-based functionality. Assistant input device 2022 may include functionality provided by or similar to existing voice-based assistants such as Apple's Siri, Amazon's Alexa, Google Assistant, or Samsung's Bixby. Assistant input device 2022 may include other hardware and / or software components. Assistant input devices 2022 may include one or more general-purpose and / or specialized devices.

[0282] Assistant display 2024 may take one or more different forms, including, for example, a computer monitor or display screen on a tablet, smartphone, or smartwatch. Assistant display 2024 may include other hardware and / or software components, such as a projector, virtual reality capabilities, or augmented reality capabilities. Assistant display 2024 may incorporate a variety of different visual, audio, or other presentation technologies. For example, assistant display 2024 may include non-visual displays, such as audio signals, which may include speech and / or other sounds, such as tones, chimes, melodies, and / or songs, that may signal various conditions and / or directions. Assistant display 2024 may comprise one or more different display screens that present various data and / or interfaces or controls for use by the assistant. Assistant display 2024 may include graphics, which may be presented by a web-based interface and / or by a computer program or application (app).

[0283] In some embodiments, the system 2010 may provide computerized translation of language from the assistant interface 2094 to the patient interface 2050, and / or vice versa. The computerized translation of language may include computerized translation of speech and / or computerized translation of text. Additionally or alternatively, the system 2010 may provide speech recognition of text and / or speech sounds. For example, the system 2010 may convert speech to printed text and / or the system 2010 may audibly recite words from printed text. The system 2010 may be configured to recognize words spoken by any or all of the patient, clinician, and / or assistant. In some embodiments, the system 2010 may be configured to recognize and react to requests or commands spoken by the patient. For example, the system 2010 may automatically initiate a telemedicine session in response to a verbal command by the patient (which may be given in any one of several different languages).

[0284] In some embodiments, server 2030 can generate aspects of assistant display 2024 for presentation by assistant interface 2094. For example, server 2030 can include a web server configured to generate display screens for presentation on assistant display 2024. For example, artificial intelligence engine 2011 can generate recommended optimal treatment plans and / or excluded treatment plans for a patient and generate display screens including the recommended optimal treatment plans and / or excluded treatment plans for presentation on assistant display 2024 of assistant interface 2094. In some embodiments, assistant display 2024 can be configured to present a virtualized desktop hosted by server 2030. In some embodiments, server 2030 can be configured to communicate with assistant interface 2094 via a first network 2034. In some embodiments, first network 2034 can include a local area network (LAN), such as an Ethernet network. In some embodiments, the first network 2034 may include the Internet, and communications between the server 2030 and the assistant interface 2094 may be secured through privacy-enhancing techniques, such as by using encryption via a virtual private network (VPN). Alternatively or additionally, the server 2030 may be configured to communicate with the assistant interface 2094 through one or more networks independent of the first network 2034 and / or other communication means, such as direct wired or wireless communication channels. In some embodiments, the patient interface 2050 and the therapy device 2070 may each operate from a patient location geographically separate from the location of the assistant interface 2094. For example, the patient interface 2050 and the therapy device 2070 may be used as part of a home rehabilitation system, which may be remotely assisted by using the assistant interface 2094 at a centralized location, such as a clinic or call center.

[0285] In some embodiments, assistant interface 2094 may be one of several different terminals (e.g., computing devices) that may be grouped together, for example, in one or more call centers or in one or more clinician offices. In some embodiments, multiple assistant interfaces 2094 may be geographically distributed. In some embodiments, a person may work as an assistant remotely from any traditional office infrastructure. Such remote work may be implemented, for example, when assistant interface 94 takes the form of a computer and / or a telephone. This remote work functionality may enable telecommuting arrangements that may include part-time and / or flexible work hours for the assistant.

[0286] 14-15 illustrate one embodiment of a therapy device 2070. More specifically, FIG. 14 illustrates the therapy device 2070 in the form of a stationary cycling machine 2100, which may be referred to for short as a stationary bike. The stationary cycling machine 2100 includes a set of pedals 2102, each attached to a pedal arm 2104 for rotation about an axle 2106. In some embodiments, as shown in FIG. 14, the pedals 2102 are movable on the pedal arms 2104 to adjust the range of motion used by the patient when pedaling. For example, positioning the pedal inward toward the axle 2106 corresponds to a smaller range of motion than when the pedal is positioned outward away from the axle 2106. A pressure sensor 2086 is attached to or embedded in one of the pedals 2102 to measure the amount of force the patient applies to the pedal 2102. The pressure sensor 2086 may communicate wirelessly to the therapy device 2070 and / or to the patient interface 2050.

[0287] FIG. 16 shows a person (patient) using the therapy device of FIG. 14 and illustrates sensors and various data parameters connected to the patient interface 2050. The exemplary patient interface 2050 is a tablet computer or smartphone, such as an iPad, iPhone, Android device, or Surface tablet, or a phablet, manually held by the patient. In some other embodiments, the patient interface 2050 may be embedded in or attached to the therapy device 2070. FIG. 16 shows the patient wearing an gait sensor 2082 on the patient's wrist, and the annotation "Steps Today 21355" indicates that the gait sensor 2082 has recorded and transmitted its step count to the patient interface 2050. FIG. 16 also shows the patient wearing a goniometer 2084 on the patient's right knee, and the annotation "Knee Angle 72°" indicates that the goniometer 2084 is measuring and transmitting its knee angle to the patient interface 2050. FIG. 16 also shows that the right side of one of the pedals 2102 having a pressure sensor 2086 reads "12.5 lbs. force," indicating that the right pedal pressure sensor 2086 is measuring and transmitting that force measurement to the patient interface 2050. FIG. 16 also shows that the left side of one of the pedals 2102 having a pressure sensor 2086 reads "27 lbs. force," indicating that the left pedal pressure sensor 2086 is measuring and transmitting that force measurement to the patient interface 2050. FIG. 16 also shows other patient data, such as an indicator "Session Time 0:04:13," indicating that the patient has been using the therapy device 2070 for 4 minutes and 13 seconds. This session time may be determined by the patient interface 2050 based on information received from the therapy device 2070. FIG. 16 also shows an indicator reading "Pain Level 3." Such a pain level may be obtained from a patent in response to a request, such as a question, presented on the patient interface 2050.

[0288] 17 is an example embodiment of an overview display 2120 of the assistant interface 2094. Specifically, the overview display 2120 presents several different controls and interfaces for the assistant to remotely assist the patient using the patient interface 2050 and / or therapy device 2070. This remote assistance functionality may also be referred to as telemedicine or telehealth.

[0289] Specifically, the overview display 2120 includes a patient profile display 2130 that presents historical information about a patient using the therapy device 2070. The patient profile display 2130 may take the form of a portion or region of the overview display 2120, as shown in FIG. 17 , although the patient profile display 2130 may take other forms, such as a separate screen or a pop-up window. In some embodiments, the patient profile display 2130 may include a limited subset of the patient's historical information. More specifically, the data presented on the patient profile display 2130 may depend on the assistant's need for that information. For example, a medical professional assisting a patient with a medical problem may be provided with medical history information about the patient, whereas a technician troubleshooting a problem with the therapy device 2070 may be provided with a more limited set of information about the patient. For example, the technician may be provided with only the patient's name. The patient profile display 2130 may include depersonalized and / or anonymized data or may use any privacy-enhancing techniques to prevent sensitive patient data from being communicated in a manner that may violate patient confidentiality requirements. Such privacy-enhancing techniques may enable compliance with laws, regulations, or other governance rules, such as, but not limited to, the Health Insurance Portability and Accountability Act (HIPAA) or the General Data Protection Regulation (GDPR), where patients may be considered "data subjects."

[0290] In some embodiments, the patient profile display 2130 may present information regarding a treatment plan to be followed by the patient when using the treatment device 2070. Such treatment plan information may be limited to assistant healthcare professionals, such as physicians or physical therapists. For example, a healthcare professional assisting a patient with issues regarding a treatment regimen may be provided with treatment plan information, whereas a technician troubleshooting an issue with the treatment device 2070 may not be provided with any information regarding the patient's treatment plan.

[0291] In some embodiments, one or more recommended optimal treatment plans and / or excluded treatment plans may be presented to the assistant on the patient profile display 2130. The one or more recommended optimal treatment plans and / or excluded treatment plans may be generated by the artificial intelligence engine 2011 of the server 2030 and may be received in real time from the server 2030, particularly during a telemedicine or telehealth session. An example of presenting one or more recommended optimal treatment plans and / or excluded treatment plans is described below with reference to FIG. 18.

[0292] 17 also includes a patient status display 2134 that presents status information about a patient using a therapy device. The patient status display 2134 may take the form of a portion or area of the overview display 2120, as shown in FIG. 17, although the patient status display 2134 may take other forms, such as a separate screen or a pop-up window. The patient status display 2134 includes sensor data 2136 from one or more of the external sensors 2082, 2084, 2086 and / or from one or more internal sensors 2076 of the therapy device 2070. In some embodiments, the patient status display 2134 may present other data 2138 about the patient, such as last reported pain level or progress within a treatment plan.

[0293] User access controls may be used to restrict access to any or all of the user interfaces 2020, 2050, 2090, 2092, 2094 of system 2010, including what data is available to view and / or modify. In some embodiments, user access controls may be used to control what information is available to any given person using system 2010. For example, the data presented on assistant interface 2094 may be controlled by user access controls, and permissions may be set depending on the assistant / user's needs and / or entitlements to view that information.

[0294] The example overview display 2120 shown in FIG. 17 also includes a help data display 2140 that presents information for the assistant to use in assisting the patient. The help data display 2140 may take the form of a portion or region of the overview display 2120, as shown in FIG. 17. The help data display 2140 may take other forms, such as a separate screen or a pop-up window. The help data display 2140 may include, for example, presenting answers to frequently asked questions about using the patient interface 2050 and / or the therapy device 2070. The help data display 2140 may also include research data or best practices. In some embodiments, the help data display 2140 may present a script for an answer or explanation in response to a patient question. In some embodiments, the help data display 2140 may present a flowchart or walkthrough for the assistant to use in determining the root cause and / or solution to the patient's problem. In some embodiments, the assistant interface 2094 may present two or more help data displays 2140, which may be the same or different, to simultaneously present help data for use by the assistant. For example, a first help data display may be used to present a troubleshooting flowchart for determining the root of a patient's problem, and a second help data display may present script information, which is information for the assistant to read to the patient, preferably including instructions for the patient to perform some action, that may help narrow down or resolve the problem. In some embodiments, the second help data display may automatically populate the script information based on input into the troubleshooting flowchart in the first help data display.

[0295] The exemplary overview display 2120 shown in FIG. 17 also includes patient interface controls 2150 for presenting information related to the patient interface 2050 and / or modifying one or more settings of the patient interface 2050. The patient interface controls 2150 may take the form of a portion or region of the overview display 2120, as shown in FIG. 17. The patient interface controls 2150 may take other forms, such as a separate screen or a pop-up window. The patient interface controls 2150 may present information communicated to the assistant interface 2094 via one or more of the interface monitor signals 2098b. As shown in FIG. 17, the patient interface controls 2150 include a display feed 2152 of displays presented by the patient interface 2050. In some embodiments, the display feed 2152 may include a live copy of the display screen currently being presented to the patient by the patient interface 2050. In other words, the display feed 2152 may present an image of what is presented on the display screen of the patient interface 2050. In some embodiments, the display feed 2152 may include summary information about the display screen currently being presented by the patient interface 2050, such as the screen name or screen number. The patient interface controls 2150 may include patient interface setting controls 2154 for an assistant to adjust or control one or more settings or aspects of the patient interface 2050. In some embodiments, the patient interface setting controls 2154 may cause the assistant interface 2094 to generate and / or transmit interface control signals 2098 to control functions or settings of the patient interface 2050.

[0296] In some embodiments, the patient interface settings controls 2154 may include collaborative or co-browsing capabilities for an assistant to remotely view and / or control the patient interface 2050. For example, the patient interface settings controls 2154 may allow an assistant to remotely enter text into one or more text entry fields on the patient interface 2050 and / or remotely control a cursor on the patient interface 2050 using a mouse or touch screen of the assistant interface 2094.

[0297] In some embodiments, using the patient interface 2050, the patient interface settings control 2154 may allow an assistant to change settings that the patient cannot change. For example, the patient interface 2050 may be prevented from accessing the language setting to prevent the patient from inadvertently switching the language used for displays on the patient interface 2050, whereas the patient interface settings control 2154 may allow the assistant to change the language setting of the patient interface 2050. In another example, the patient interface 2050 may not allow the font size setting to be changed to a smaller size to prevent the patient from inadvertently switching the font size used for displays on the patient interface 2050 such that the displays become unreadable to the patient, whereas the patient interface settings control 154 may provide for the assistant to change the font size setting of the patient interface 2050.

[0298] 17 also includes an interface communication display 2156 that indicates the status of communications between the patient interface 2050 and one or more other devices 2070, 2082, 2084, such as a therapy device 2070, a gait sensor 2082, and / or a goniometer 2084. The interface communication display 2156 may take the form of a portion or region of the overview display 2120, as shown in FIG. 17. The interface communication display 2156 may take other forms, such as a separate screen or a pop-up window. The interface communication display 2156 may include controls for the assistant to remotely modify communications with one or more of the other devices 2070, 2082, 2084. For example, the assistant may remotely instruct the patient interface 2050 to reset communication with one of the other devices 2070, 2082, 2084 or to establish communication with a new one of the other devices 2070, 2082, 2084. This functionality may be used, for example, if the patient has a problem with one of the other devices 2070, 2082, 2084 or if the patient receives a new or replacement one of the other devices 2070, 2082, 2084.

[0299] The exemplary overview display 2120 shown in FIG. 17 also includes a device control 2160 for the assistant to view information about and / or control the therapy device 2070. The device control 2160 may take the form of a portion or area of the overview display 2120, as shown in FIG. 17. The device control 2160 may take other forms, such as a separate screen or a pop-up window. The device control 2160 may include a device status display 2162 with information about the current status of the device. The device status display 2162 may present information communicated to the assistant interface 2094 via one or more of the device monitor signals 2099b. The device status display 2162 may indicate whether the therapy device 2070 is currently communicating with the patient interface 2050. The device status display 2162 may present other current and / or historical information regarding the status of the therapy device 2070.

[0300] The device controls 2160 may include a device setting control 2164 that allows an assistant to adjust or control one or more aspects of the therapy device 2070. The device setting control 2164 may cause the assistant interface 2094 to generate and / or transmit device control signals 2099 to change operating parameters of the therapy device 2070 (e.g., pedal radius setting, resistance setting, target RPM, etc.). The device setting control 2164 may include a mode button 2166 and a position control 2168, which may be used in conjunction to allow an assistant to place the actuator 2078 of the therapy device 2070 in manual mode and then use the position control 2168 to change a setting, such as the position or speed of the actuator 2078. The mode button 2166 may provide settings, such as position, for switching between automatic and manual modes. In some embodiments, one or more settings may be adjustable at any time and without an associated automatic / manual mode. In some embodiments, an assistant may change operating parameters of the therapy device 2070, such as pedal radius settings, while the patient is actively using the therapy device 2070. Such “on the fly” adjustments may or may not be available to the patient using the patient interface 2050. In some embodiments, the device settings control 2164 may allow the assistant to change settings that the patient cannot change using the patient interface 2050. For example, the patient interface 2050 may be prevented from changing preconfigured settings, such as height or tilt settings of the therapy device 2070, while the device settings control 2164 may provide for the assistant to change the height or tilt settings of the therapy device 2070.

[0301] The example overview display 2120 shown in FIG. 17 may also include patient communication controls 2170 for controlling an audio or audiovisual communication session with the patient interface 2050. The communication session with the patient interface 2050 may include a live feed from the assistant interface 2094 for presentation by an output device of the patient interface 2050. The live feed may take the form of an audio feed and / or a video feed. In some embodiments, the patient interface 2050 may be configured to provide two-way audio or audiovisual communication with a person using the assistant interface 2094. Specifically, the communication session with the patient interface 2050 may include a bidirectional (two-way) video or audiovisual feed, with each of the patient interface 2050 and the assistant interface 2094 presenting video of the other. In some embodiments, the patient interface 2050 may present video from the assistant interface 2094, while the assistant interface 2094 presents only audio, or the assistant interface 2094 presents no live audio or visual signals from the patient interface 2050. In some embodiments, the assistant interface 2094 may present video from the patient interface 2050, while the patient interface 2050 presents only audio, or the patient interface 2050 presents no live audio or visual signals from the assistant interface 2094.

[0302] In some embodiments, an audio or audiovisual communication session with the patient interface 2050 can occur, at least in part, while the patient is performing a rehabilitation regimen on a body part. The patient communication controls 2170 can take the form of a portion or region of the overview display 2120, as shown in FIG. 17 . The patient communication controls 2170 may take other forms, such as a separate screen or a pop-up window. The audio and / or audiovisual communication can be processed and / or directed by the assistant interface 2094 and / or by one or more other devices, such as a telephone system or a videoconferencing system used by the assistant while the assistant uses the assistant interface 2094. Alternatively or additionally, the audio and / or audiovisual communication can include communication with a third party. For example, the system 2010 can enable the assistant to initiate a three-way conversation with the patient and a subject matter expert, such as a healthcare professional or specialist, regarding the use of a particular piece of hardware or software. 17 includes call controls 2172 for use by a healthcare provider in managing various aspects of audio or audiovisual communications with a patient. The call controls 2172 include a hang up button 2174 for an assistant to end an audio or audiovisual communication session. The call controls 2172 also include a mute button 2176 for temporarily silencing audio or audiovisual signals from the assistant interface 2094. In some embodiments, the call controls 2172 may include other functions, such as a hold button (not shown). The call controls 2172 also include one or more record / playback controls 2178, such as record, play, and pause buttons, for controlling the recording and / or playback of audio and / or video from the conference call session on the patient interface 2050.The call control unit 2172 also includes a video feed display 2180 for presenting still and / or video images from the patient interface 2050 and a self-video display 2182 showing a current image of the assistant using the assistant interface. The self-video display 2182 may be presented as a picture-in-picture format within a section of the video feed display 2180, as shown in FIG. 17. Alternatively or additionally, the self-video display 2182 may be presented separately and / or independently from the video feed display 2180.

[0303] The example overview display 2120 shown in FIG. 17 also includes a third-party communication control 2190 for use in conducting audio and / or audiovisual communication with a third party. The third-party communication control 2190 may take the form of a portion or region of the overview display 2120, as shown in FIG. 17. The third-party communication control 2190 may take other forms, such as a separate on-screen display or a pop-up window. The third-party communication control 2190 may include one or more controls, such as a contact list and / or a button or control, for contacting a third party, e.g., a subject matter expert, such as a healthcare professional or specialist, regarding use of a particular piece of hardware or software. The third-party communication control 2190 may include teleconferencing capabilities for a third party to simultaneously communicate with both the assistant via the assistant interface 2094 and with the patient via the patient interface 2050. For example, the system 2010 may provide for the assistant to initiate a three-way conversation with the patient and a third party.

[0304] 18 shows an example embodiment of an overview display 2120 of the assistant interface 2094 that presents recommended optimal and excluded treatment plans in real time during a telemedicine session in accordance with the present disclosure. As depicted, the overview display 2120 only includes sections of the patient profile 2130 and the video feed display 2180, including a self-video display 2182. Any suitable configuration of the controls and interfaces of the overview display 2120 described with reference to FIG. 17 may be presented in addition to or instead of the patient profile 2130, the video feed display 2180, and the self-video display 2182.

[0305] An assistant (e.g., a healthcare professional) using the assistant interface 2094 (e.g., a computing device) during a telemedicine session may be presented with a self-video 2182 in a portion of the overview display 2120 (e.g., a user interface presented on the display screen 2024 of the assistant interface 2094) that also presents video from the patient on a video feed display 2180. As depicted, another portion of the overview display 2120 includes a patient profile display 2130.

[0306] The patient profile display 2130 presents two exemplary optimal treatment plans 2600 and one exemplary excluded treatment plan 2602. As described herein, treatment plans may be recommended taking into account various clinical information and characteristics of the patient being treated. Clinical information may include information about the characteristics of other people, the treatment plans followed by other people, and the results of the treatment plans. Patterns between the characteristics of the patient being treated and other people may be matched by one or more machine learning models 2013 of the artificial intelligence engine 2011 to generate a recommended optimal treatment plan 2600 for the patient to follow to achieve a desired outcome. Each recommended optimal treatment plan may be generated based on a different desired outcome.

[0307] For example, assume the following: Treatment plan "A" indicates that "Patient X should use the treatment device for 30 minutes per day for four days to achieve an increased range of motion of Y%, and Patient X has type 2 diabetes. Patient X should be prescribed drug Z for pain management during the treatment plan (drug Z is approved for people with type 2 diabetes)." Therefore, the generated optimal treatment plan achieves an increased range of motion of Y%. As can be appreciated, the optimal treatment plan also includes a recommended drug (e.g., drug Z) to prescribe to the patient to manage pain taking into account the patient's known medical condition (e.g., type 2 diabetes). That is, the recommended patient drug not only does not conflict with the patient's medical condition, but also improves the likelihood of a good patient outcome.

[0308] The recommended optimal treatment plan "B" may specify different treatment plans, including different treatment protocols of the treatment device, different drug regimens, etc., based on different desired outcomes of the treatment plans.

[0309] As depicted, the patient profile display 2130 may also present excluded treatment plans 2602. These types of treatment plans are shown to the assistant using the assistant interface 2094 to alert the assistant not to recommend certain portions of the treatment plan to the patient. For example, an excluded treatment plan may specify: "Patient X should not use a treatment device for more than 30 minutes per day due to heart disease, and Patient X has type 2 diabetes, and Patient X should not be prescribed drug M for pain management during the treatment plan (in this scenario, drug M may cause complications in people with type 2 diabetes)." Specifically, the excluded treatment plan points out a restriction in the treatment protocol that, due to heart disease, Patient X should not exercise for more than 30 minutes per day. The excluded treatment plan also points out that drug M should not be prescribed to Patient X because it conflicts with the medical condition of type 2 diabetes.

[0310] The assistant may select an optimal treatment plan for the patient on the overview display 2120. For example, the assistant may use an input peripheral (e.g., a mouse, touch screen, microphone, keyboard, etc.) to select from the patient's optimal treatment plans 2600. In some embodiments, during the telemedicine session, the assistant may discuss the advantages and disadvantages of the recommended optimal treatment plan 2600 with the patient.

[0311] In either case, the assistant may select an optimal treatment plan for the patient to follow to achieve the desired results. The selected optimal treatment plan may be transmitted to the patient interface 2050 for presentation. The patient may view the selected optimal treatment plan on the patient interface 2050. In some embodiments, the assistant and patient may discuss details (e.g., treatment protocol using treatment device 2070, dietary regimen, drug regimen, etc.) in real time during the telemedicine session.

[0312] 19 shows an exemplary embodiment of a server 2030 that converts clinical information 2700 into a medical description language 2702 for processing by an artificial intelligence engine 2011 according to the present disclosure. The clinical information 2700 may be written by a person with a particular professional qualification, license, or status. In the illustrated example, the clinical information 2700 includes a portion of a meta-analysis for a clinical trial entitled "EFFECT OF USING TREATMENT PLAN FOR HIP OSTEOARTHRITIS PAIN." This portion includes a "Results" section and a "Conclusions" section. For clarity of illustration, many other portions of the clinical information 2700 (e.g., details of the trial procedures, subject biographies, etc.) may not be depicted.

[0313] One or more machine learning models 2013 may be trained to interpret bodies of structured or unstructured text (e.g., clinical information 700) in search of a corpus of keywords representing target information. The target information may be included in one or more portions of clinical information 2700. The target information may refer to any suitable information of interest, such as characteristics of people (e.g., vital signs, medical conditions, medical procedures, allergies, family medical information, measurements, etc.), treatment regimens people follow, results of treatment regimens, clinical trial information, treatment devices used in treatment regimens, etc.

[0314] Using tags representing the target information and values associated with the tags, one or more machine learning models 2013 may generate a canonical form defined by a medical description language. The values may be numbers, letters, alphanumeric characters, strings, sequences, etc., and are derived from portions of the clinical information 2700 (including the target information). The target information may be organized in a parent-child relationship based on the structure, organization, and / or relationships of the information. For example, the keyword "results" may be identified and determined to be a parent-level tag because results encompasses child target information such as tests, subjects, treatment plans, treatment devices, subject characteristics, and conclusions. Thus, " <results>The parent level tag for " is " <trials> 」、「 <subjects>","<treatment plan> ","<treatment apparatus> ","<subject characteristics> " and " <conclusions>" child level tags. Each tag may contain a corresponding end tag (e.g., " <results> …< / results> ").

[0315] Consider now an embodiment of the operations that the trained machine learning model 2013 performs to encode a portion of clinical information 2700 in medical description language 2702. The trained machine learning model 2013 has identified the keywords "treatment plan" and "treatment device" in the portion of clinical information 2700. Once identified, the trained machine learning model 2013 may analyze words in the vicinity (e.g., to the left and right) of the keywords to determine whether the word matches a recognized context based on the training data. The trained machine learning model 2013 may also determine whether a word is recognized as associated with the keyword based on the training data and based on attributes of the data. In FIG. 19 , the trained machine learning model may determine that the word "range of motion (ROM)" fits the context of the keyword "treatment device" and is likely recognizable as being associated with the keyword "treatment device." Thus, the value "ROM" is used to encode the tag representing the target information.<treatment apparatus> "and"< / treatment apparatus> ". Other tags representing target information in the canonical form of the medical description language 2702 may be populated in a similar manner. The medical description language 2702 representing portions of the clinical information 2700 may be stored in the patient data store 2044 in a database corresponding to the appropriate patient cohort.

[0316] FIG. 20 illustrates an exemplary embodiment of a method 2800 for recommending an optimal treatment plan according to the present disclosure. Method 2800 is performed by processing logic, which may include hardware (circuitry, dedicated logic, etc.), software (such as those running on a general-purpose computer system or dedicated machine), or a combination of both. Method 2800 and / or each of its individual functions, routines, subroutines, or operations may be performed by one or more processors of a computing device (e.g., any component of FIG. 13 , such as server 2030 running artificial intelligence engine 2011). In certain implementations, method 2800 may be performed by a single processing thread. Alternatively, method 2800 may be performed by two or more processing threads, each thread implementing one or more individual functions, routines, subroutines, or operations of the method.

[0317] For ease of explanation, method 2800 is depicted and described as a series of acts. However, acts in accordance with the present disclosure may be performed in various orders and / or concurrently and / or with other acts not shown and described herein. For example, acts depicted in method 2800 may be performed in combination with any other acts of any other method disclosed herein. Moreover, not all illustrated acts may be required to implement method 2800 in accordance with the disclosed subject matter. Additionally, those skilled in the art will understand and appreciate that method 2800 may alternatively be represented as a series of interrelated states via a state diagram or events.

[0318] At 2802, the processing device may receive clinical information 2700 from a data source 2015 regarding the results of implementing a particular treatment regimen for people with particular characteristics using a treatment device 2070. The clinical information has a first data format, which may include natural language text in the form of words arranged in sentences further arranged in paragraphs. The first data format may be a report or description, which may include information about clinical trials, medical studies, meta-analyses, evidence-based guidelines, journals, etc. The first data format may include information arranged in an unstructured manner and may have a first data size (e.g., bytes, kilobytes, etc.).

[0319] The specific characteristics of the people may include medications prescribed to the people, injuries to the people, medical procedures performed on the people, measurements of the people, allergies to the people, medical conditions of the people, first historical information of the people, vital signs of the people, symptoms of the people, medical information of the people's family, or some combination thereof. These characteristics may also include the following information about the people: demographic, geographic, diagnostic, measurement or test-based, medical history, etiological, cohort-related, differential diagnosis, surgical, physical therapy, pharmacological, and other treatment recommendations.

[0320] At 2804, the processing device may convert a portion of the clinical information from the first data format to a medical description language 2702 used by the artificial intelligence engine 2011. The medical description language 2702 may include a second data format that structures the unstructured data of the clinical information 2700. For example, the medical description language 2702 may include using tag-value pairs, where the tags identify the type of value stored between the tags. The medical description language 2702 may have a second data size (e.g., bits) that is smaller than the first data size of the clinical information 2700. The medical description language may include telemedical data.

[0321] At 2806, the processing device may determine an optimal treatment plan 2600 to follow when the patient uses the treatment device 2070 to achieve a desired outcome based on the portions of the clinical information 2700 described by the medical description language 2702 and a set of patient-related characteristics. One or more machine learning models 2013 of the artificial intelligence engine 2011 may be trained to output the optimal treatment plan 2600. For example, one machine learning model 2013 may be trained to match patterns between the portions of the clinical information described by the medical description language 2702 with a set of patient characteristics. In some embodiments, the set of patient characteristics is also represented in the medical description language. The patterns are associated with an optimal treatment plan that may produce the desired outcome.

[0322] In some embodiments, the optimal treatment plan may include information regarding medical procedures to be performed on the patient, the patient's treatment protocol using the treatment device 2070, the patient's dietary regimen, the patient's drug regimen, the patient's sleep regimen, additional regimens, or any combination thereof.

[0323] The desired outcome may include achieving a particular result within a particular time period, which may include the range of motion the patient achieves using the treatment device 2070, the amount of force the patient exerts on a portion of the treatment device 2070, the amount of time the patient exercises using the treatment device 2070, the distance the patient travels using the treatment device 2070, the level of pain the patient experiences when using the treatment device 2070, or some combination thereof.

[0324] In some embodiments, the processing device may determine a second optimal treatment plan for the patient to follow to achieve a second desired outcome using the treatment device 2070 based on a portion of the clinical information described by the medical description language and a set of patient-related characteristics. The desired outcome may relate to a recovery outcome, and the second desired outcome may relate to a recovery time. The recovery outcome may include achieving a specific threshold of functionality, mobility, range of motion, etc. of a specific body part. The recovery time may include achieving a specific threshold of functionality, mobility, movement, range of motion, etc. of a specific body part within a specific threshold period of time. For example, some people may prefer to recover to a specific level of mobility as quickly as possible without fully recovering. As discussed above, different machine learning models 2013 may be trained using different clinical information to provide different recommended treatment plans that may produce different desired outcomes.

[0325] In some embodiments, the processing device may determine, based on a portion of the clinical information described by the medical description language and a set of patient-related characteristics, excluded treatment plans 2602 that should not be recommended for the patient to follow when achieving a desired result using the treatment device 2070. In some embodiments, as depicted in FIG. 18 , the optimal treatment plan 2600 and the excluded treatment plans 2602 may be simultaneously presented in a first portion of the user interface (e.g., the patient profile display 2130), while at least video or other multimedia data from the patient engaged in the telemedicine session may be presented in another portion (e.g., the video feed display 2180).

[0326] In some embodiments, the optimal treatment plan 2600 and the excluded treatment plan 2602 may be presented simultaneously while the healthcare professional is not engaged in a telemedicine session. For example, the optimal treatment plan 2600 and the excluded treatment plan 2602 may be presented in a user interface before the telemedicine session begins or after the telemedicine session ends.

[0327] At 2808, the processing device may provide an optimal treatment plan to be presented on a user interface (e.g., overview display 2120) on the healthcare professional's computing device (e.g., assistant interface 2094). In addition, any other generated optimal treatment plans 2600 may be provided to the healthcare professional's computing device. For example, different optimal treatment plans that result in different outcomes may be presented to the healthcare professional. The processing device may receive a selected treatment plan of any of the presented treatment plans. In some embodiments, the healthcare professional may select an optimal treatment plan based on the patient's outcome preferences. For example, an athlete may want to optimize for performance, while a retiree may want to optimize for pain-free quality of life. The selected treatment plan may be transmitted to the patient's computing device for presentation on the user interface. In some embodiments, the optimal treatment plan may be provided to the healthcare professional's computing device during a telemedicine session, such that the optimal treatment plan is presented in real time on a first portion of the user interface, while video and optionally other multimedia of the patient are simultaneously presented on a second portion of the user interface. The selected treatment plan may be presented on the patient's computing device during the telemedicine session so that the medical professional can explain the selected treatment plan to the patient.

[0328] 21 illustrates an exemplary embodiment of a method 2900 for converting clinical information into a medical description language according to the present disclosure. Method 2900 includes operations performed by a processor of a computing device (e.g., any component of FIG. 13 , such as server 2030 executing artificial intelligence engine 2011). In some embodiments, one or more operations of method 2900 are implemented in computer instructions stored on a memory device and executed by a processing device. Method 2900 may be performed in the same or similar manner as described above with respect to method 2800. The operations of method 2900 may be performed in any combination with the operations of any of the methods described herein.

[0329] Method 2900 may include operation 2804 from previous method 2800 depicted in Figure 20. For example, at 2804 of method 2600, the processing device may convert a portion of the clinical information from a first data format to a medical description language used by the artificial intelligence engine.

[0330] 21 includes operations 2902, 2904, and 2906. Operations 2902, 2904, and 2906 may be performed by one or more trained machine learning models 2013 of the artificial intelligence engine 2011.

[0331] At 2902, the processing device may interpret the clinical information. At 2904, the processing device may identify portions of the clinical information having values associated with the target information based on keywords in the clinical information that describe the target information. At 2906, the processing device may generate a canonical form defined by the medical description language. The canonical form may include tags that identify values of the target information. The tags may be attributes that describe specific characteristics of the target information. The specific characteristics may include which cohort class the person is placed in, the person's age, semantic information, association with a specific cohort, family history, etc. In some embodiments, the specific characteristics may include any information or indication that the person is at risk.

[0332] The canonical form may enable more efficient processing of portions of clinical information represented by the medical description language when training a machine learning model to generate an optimal treatment plan for a patient using the trained machine learning model. Additionally, the canonical form may enable more efficient processing by the trained machine learning model when matching patterns between patient characteristics with portions of clinical information represented by the medical description language.

[0333] FIG. 22 illustrates an exemplary computer system 21000 capable of implementing any one or more of the methods described herein, according to one or more aspects of the present disclosure. In one example, the computer system 21000 includes a computing device and may correspond to the assistance interface 2094, the reporting interface 2092, the supervisory interface 2090, the clinician interface 2020, the server 2030 (including the AI engine 2011), the patient interface 2050, the gait sensor 2082, the goniometer 2084, the therapy device 2070, the pressure sensor 2086, or any suitable component of FIG. 13 . The computer system 21000 may be capable of executing instructions implementing one or more machine learning models 2013 of the artificial intelligence engine 2011 of FIG. 13 . The computer system may be connected (e.g., networked) to other computer systems within a LAN, an intranet, an extranet, or the Internet, including via a cloud or peer-to-peer network. The computer system may operate in the capacity of a server in a client-server network environment. The computer system may be a personal computer (PC), a tablet computer, a wearable (e.g., a wristband), a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a camera, a video camera, an Internet of Things (IoT) device, or any device capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by the device. Further, although only a single computer system is illustrated, the term "computer" shall also be taken to include any collection of computers individually or collectively executing an instruction set (or sets) to perform any one or more of the methodologies discussed herein.

[0334] The computer system 21000 includes a processing device 21002, a main memory 21004 (e.g., read-only memory (ROM), flash memory, solid-state drive (SSD), dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM)), a static memory 21006 (e.g., flash memory, solid-state drive (SSD), static random access memory (SRAM)), and a data storage device 21008, which communicate with each other via a bus 1010.

[0335] The processing device 21002 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, etc. More specifically, the processing device 21002 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor implementing another instruction set or a combination of instruction sets. The processing device 21002 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a system-on-a-chip, a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, etc. The processing device 21002 is configured to execute instructions to perform any of the operations and steps discussed herein.

[0336] The computer system 21000 may further include a network interface device 21012. The computer system 21000 may also include a video display 21014 (e.g., a liquid crystal display (LCD), a light emitting diode (LED), an organic light emitting diode (OLED), a quantum LED, a cathode ray tube (CRT), a shadow mask CRT, an aperture grill CRT, a monochrome CRT), one or more input devices 21016 (e.g., a keyboard and / or mouse, or game-like controls), and one or more speakers 21018 (e.g., speakers). In one exemplary embodiment, the video display 21014 and the input devices 21016 may be combined into a single component or device (e.g., an LCD touchscreen).

[0337] The data storage device 21016 may include a computer-readable medium 21020 having stored thereon instructions 21022 that embody any one or more of the methods, operations, or functions described herein. The instructions 21022 may also reside, completely or at least partially, within the main memory 21004 and / or within the processing device 21002 during execution of the instructions 21022 by the computer system 21000. Thus, the main memory 21004 and the processing device 21002 also constitute computer-readable media. The instructions 21022 may further be transmitted or received over a network via the network interface device 21012.

[0338] While the computer-readable storage medium 21020 is shown in the exemplary embodiment to be a single medium, the term "computer-readable storage medium" should be taken to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated caches and servers) that store one or more sets of instructions. The term "computer-readable storage medium" should also be taken to include any medium that can store, encode, or carry a set of instructions for execution by a machine and cause the machine to perform any one or more of the methodologies of the present disclosure. Accordingly, the term "computer-readable storage medium" should be taken to include, but is not limited to, solid-state memory, optical media, and magnetic media.

[0339] Clause 25. A method for providing an optimal treatment plan for use with a treatment device by an artificial intelligence engine, comprising: receiving, from a data source, clinical information regarding results of implementing a particular treatment regimen for people with particular characteristics using a treatment device, the clinical information having a first data format; converting a portion of the clinical information from a first data format into a medical description language used by the artificial intelligence engine; determining an optimal treatment plan for the patient to follow to achieve a desired result using the treatment device based on the portion of the clinical information described in the medical description language and a plurality of characteristics related to the patient; and providing an optimal treatment plan for presentation on a computing device of a healthcare professional.

[0340] Clause 26. Converting the clinical information from a first data format into a medical description language used by the artificial intelligence engine Interpreting clinical information and identifying portions of the clinical information having values related to the target information based on keywords representing the target information in the clinical information; 10. The method of any clause herein, further comprising: generating a canonical form defined by a medical description language, the canonical form including tags that identify values of the target information.

[0341] Clause 27. The method of any clause herein, wherein the tag is an attribute that describes a particular characteristic of the target information.

[0342] Article 28. Providing an optimal treatment plan as presented on the healthcare professional's computing device

[0343] 10. The method of any clause herein, further comprising causing the optimal treatment plan to be presented on a user interface of the healthcare professional's computing device during the telemedicine session, wherein the optimal treatment plan is not presented on a display screen of the computing device, such display screen being configured for use by the patient during the telemedicine session.

[0344] Article 29. Based on the clinical information portion described in the medical description language and a number of characteristics related to the patient, determining excluded treatment plans that should not be recommended for the patient to follow when using the treatment device to achieve the desired results; The method of any clause herein, further comprising: providing the excluded treatment plan for presentation on a computing device of a medical professional.

[0345] Clause 30. Determining a second optimal treatment plan to be followed when the patient uses the treatment device to achieve a second desired result based on the portion of clinical information described in the medical description language and a plurality of characteristics related to the patient, wherein the desired result relates to a recovery outcome, and the second desired result relates to a recovery time; providing a second optimal treatment plan for presentation on a computing device of a healthcare professional; and receiving a selected treatment plan, either the optimal treatment plan or the second optimal treatment plan; 5. The method of any clause herein, further comprising transmitting the selected treatment plan to the patient's computing device for presentation on a user interface of the patient's computing device.

[0346] Clause 31. The desired result includes obtaining a specific result within a specific time period, and the specific result is the range of motion the patient achieves using the treatment device; the amount of force the patient exerts on a portion of the treatment device; the amount of time the patient exercises using the therapy device; the distance the patient travels using the therapy device, or The method according to any clause herein, including any combination thereof.

[0347] Clause 32. The specific characteristics of the people include a first medication prescribed to the people, a first injury of the people, a first medical procedure performed on the people, a first measurement of the people, a first allergy of the people, a first medical condition of the people, a first history information of the people, a first vital sign of the people, a first symptom of the people, a first family medical information of the people, a first demographic information of the people, a first geographic information of the people, a first measurement-based or test-based information of the people, a first medical history information of the people, a first etiological information of the people, a first cohort-related information of the people, a first differential diagnosis information of the people, a first surgical information of the people, a first physiotherapy information of the people, a first pharmacological information of the people, a first other treatment recommended for the people, or any combination thereof; 20. The method of any clause herein, wherein the plurality of patient characteristics comprises a second medication of the patient, a second injury of the patient, a second medical procedure performed on the patient, a second measurement of the patient, a second allergy of the patient, a second medical condition of the patient, a second historical information of the patient, a second vital sign of the patient, a second symptom of the patient, a second family medical information of the patient, second demographic information of the patient, second geographic information of the patient, second measurement-based or test-based information of the patient, second medical historical information of the patient, second etiological information of the patient, second cohort-related information of the patient, second differential diagnosis information of the patient, second surgical information of the patient, second physical therapy information of the patient, second pharmacological information of the patient, a second other treatment recommended for the patient, or any combination thereof.

[0348] Clause 33. The method described in any clause herein, wherein the clinical information is written by a person with specific professional qualifications and includes journal articles, clinical trials, evidence-based guidelines, meta-analyses, or any combination thereof.

[0349] Article 34. Determining the optimal treatment plan to be followed by the patient to achieve the desired result using the treatment device, based on the clinical information portion described in the medical description language and a number of characteristics about the patient, 10. The method of any clause herein, further comprising: matching a pattern between portions of clinical information described by the medical description language with a plurality of patient characteristics, the pattern being associated with an optimal treatment plan leading to a desired outcome.

[0350] Article 35. The optimal treatment plan is medical procedures performed on patients; a treatment protocol for a patient using the treatment device; the patient's dietary regimen, the patient's drug regimen, the patient's sleep regimen, or The method according to any clause herein, including any combination thereof.

[0351] Clause 36. A tangible, non-transitory computer-readable medium storing instructions that, when executed, cause a processing device to: receiving, from a data source, clinical information regarding results of implementing a particular treatment regimen for people with particular characteristics using a treatment device, the clinical information having a first data format; converting a portion of the clinical information from a first data format into a medical description language used by the artificial intelligence engine; determining an optimal treatment plan for the patient to follow to achieve a desired result using the treatment device based on the portion of the clinical information described in the medical description language and a plurality of characteristics related to the patient; and providing an optimal treatment plan to be presented on a computing device of a medical professional.

[0352] Clause 37. Converting portions of clinical information from a first data format into a medical description language used by the artificial intelligence engine includes: Interpreting clinical information and identifying portions of the clinical information having a value for the target information based on keywords representing the target information in the clinical information; The computer-readable medium of any clause herein, further comprising: generating a canonical form defined by a medical description language, the canonical form including tags that identify values of the target information.

[0353] Article 38. Providing an optimal treatment plan as presented on the healthcare professional's computing device The computer-readable medium of any clause herein, further comprising causing the optimal treatment plan to be presented on a user interface of the healthcare professional's computing device during the telemedicine session, wherein the optimal treatment plan is not presented on a user interface of the patient's computing device during the telemedicine session.

[0354] Article 39. The processing device determining a second optimal treatment plan to be followed when the patient uses the treatment device to achieve a second desired result based on the portion of the clinical information described in the medical description language and a plurality of characteristics related to the patient, wherein the desired result is related to a recovery outcome, and the second desired result is related to a recovery time; providing a second optimal treatment plan for presentation on a computing device of a healthcare professional; and receiving a selected treatment plan, either the optimal treatment plan or the second optimal treatment plan; and transmitting the selected treatment plan to the patient's computing device.

[0355] Clause 40. The desired result includes obtaining a specific result within a specific time period, and the specific result is the range of motion the patient achieves using the treatment device; the amount of force the patient exerts on a portion of the treatment device; the amount of time the patient exercises using the therapy device; the distance the patient travels using the therapy device, or A computer-readable medium according to any clause herein, including any combination thereof.

[0356] Clause 41. The specific characteristics of the people include a first medication prescribed to the people, a first injury of the people, a first medical procedure performed on the people, a first measurement of the people, a first allergy of the people, a first medical condition of the people, a first history information of the people, a first vital sign of the people, a first symptom of the people, a first family medical information of the people, a first demographic information of the people, a first geographic information of the people, a first measurement-based or test-based information of the people, a first medical history information of the people, a first etiological information of the people, a first cohort-related information of the people, a first differential diagnosis information of the people, a first surgical information of the people, a first physiotherapy information of the people, a first pharmacological information of the people, a first other treatment recommended for the people, or any combination thereof; 20. The computer-readable medium of any clause herein, wherein the plurality of characteristics of the patient includes a second medication of the patient, a second injury of the patient, a second medical procedure performed on the patient, a second measurement of the patient, a second allergy of the patient, a second medical condition of the patient, a second historical information of the patient, a second vital sign of the patient, a second symptom of the patient, a second family medical information of the patient, second demographic information of the patient, second geographic information of the patient, second measurement-based or test-based information of the patient, second medical historical information of the patient, second etiological information of the patient, second cohort-related information of the patient, second differential diagnosis information of the patient, second surgical information of the patient, second physical therapy information of the patient, second pharmacological information of the patient, a second other treatment recommended for the patient, or any combination thereof.

[0357] Clause 42. The computer-readable medium described in any clause herein, wherein the clinical information is written by a person with specific professional qualifications and includes journal articles, clinical trials, evidence-based guidelines, or any combination thereof.

[0358] Clause 43. A system comprising: a memory device storing instructions; a processing device communicatively coupled to the memory device, the processing device executing instructions to receiving, from a data source, clinical information regarding results of implementing a particular treatment regimen for people with particular characteristics using a treatment device, the clinical information having a first data format; converting a portion of the clinical information from a first data format into a medical description language used by the artificial intelligence engine; determining an optimal treatment plan to be followed by the patient when using the treatment device to achieve a desired result based on the portion of the clinical information described in the medical description language and a plurality of characteristics related to the patient; and providing an optimal treatment plan as presented on a healthcare professional's computing device.

[0359] Clause 44. Converting the clinical information from a first data format into a medical description language used by the artificial intelligence engine includes: Interpreting clinical information and identifying portions of the clinical information having a value for the target information based on keywords representative of the target information described by the clinical information; The system of any clause herein, further comprising: generating a canonical form defined by a medical description language, the canonical form including tags that identify values of the target information.

[0360] Method and system for monitoring user characteristics during a telemedicine session using artificial intelligence Determining a treatment plan for a patient with particular characteristics (e.g., vital signs or other measurements, implementation, demographic, geographic, diagnostic, measurement-based or test-based, medical history, etiological, cohort-related, differential diagnosis, surgical, physical therapy, behavioral, pharmacological, and recommended other treatments, etc.) can be a technically challenging problem. For example, a large amount of information may be considered when determining a treatment plan, which can lead to inefficiency and inaccuracy in the treatment plan selection process. In a rehabilitation setting, some of the large amount of information considered may include patient characteristics, such as personal information, implementation information, and measurement information. Personal information may include demographic, psychological, or other information, such as age, weight, sex, height, body mass index, medical conditions, family medical history, injuries, medical procedures, prescribed medications, behavioral or psychological conditions, or some combination thereof. The implementation information may include, for example, the elapsed time using the treatment device, the amount of force exerted on a portion of the treatment device, the range of motion achieved with the treatment device, the speed of movement of a portion of the treatment device, an indication of multiple pain levels using the treatment device, or some combination thereof. The measurement information may include, for example, vital signs, respiratory rate, heart rate, temperature, blood pressure, glucose level or other biomarkers, or some combination thereof. It may be desirable to process the characteristics of multiple patients, the treatment plans implemented for those patients, and the results of the treatment plans for those patients.

[0361] Yet another technical challenge may involve treating a patient remotely from a location different from where the patient is located via a computing device during a telemedicine or telehealth session. An additional technical challenge is controlling or enabling control of a treatment device used by a patient from a location different from where the patient is located. Often, when a patient undergoes rehabilitation surgery (e.g., knee surgery), a healthcare provider may prescribe the patient a treatment device to be used to implement the treatment protocol at the patient's home or any mobile or temporary location. A healthcare provider may refer to a doctor, physician assistant, nurse, chiropractor, dentist, physical therapist, acupuncturist, physical trainer, coach, personal trainer, etc. A healthcare provider may refer to any person with a credential, license, position, etc. in the fields of medicine, physical therapy, rehabilitation, etc.

[0362] When the healthcare provider is located at a different location than the patient and the treatment device, it can be technically difficult for the healthcare provider to use the treatment device to monitor the patient's actual progress (as opposed to relying on the patient's word about their progress), modify the treatment plan according to the patient's progress, adapt the treatment device to the patient's personal characteristics as the patient implements the treatment plan, etc.

[0363] Therefore, systems and methods such as those described herein that are configured to monitor a patient's actual progress while the patient implements a treatment plan using a treatment device may be desirable. In some embodiments, the systems and methods described herein may be configured to receive treatment data regarding a user implementing a treatment plan using a treatment device. A user may include a patient, user, or person performing various exercises using a treatment device.

[0364] The treatment data may include various characteristics of the user, various baseline measurement information about the user, various measurement information about the user while the user uses the treatment device, various characteristics of the treatment device, a treatment plan, other suitable data, or a combination thereof. In some embodiments, the systems and methods described herein may be configured to receive treatment data during a telemedicine session.

[0365] In some embodiments, at least a portion of the treatment data may correspond to sensor data from sensors configured to sense various characteristics of the treatment device and / or measurements of the user while the user is implementing the treatment plan using the treatment device. Additionally or alternatively, at least a portion of the treatment data may correspond to sensor data from sensors associated with the wearable device configured to sense measurements of the user while the user is implementing the treatment plan using the treatment device.

[0366] The various characteristics of the therapy device may include one or more settings of the therapy device, the current number of rotations per time period (e.g., minute, etc.) of a rotating member (e.g., wheel, etc.) of the therapy device, a resistance setting of the therapy device, other suitable characteristics of the therapy device, or a combination thereof. The baseline information may include one or more vital signs of the user, the user's respiratory rate, the user's heart rate, the user's body temperature, the user's blood pressure, glucose level, or other biomarkers, other suitable measurement information of the user, or a combination thereof, while the user is at rest. The measurement information may include one or more vital signs of the user, the user's respiratory rate, the user's heart rate, the user's body temperature, the user's blood pressure, the user's glucose level, or other suitable measurement information of the user, or a combination thereof, while the user is implementing a treatment plan using the therapy device.

[0367] In some embodiments, the systems and methods described herein may be configured to write the treatment data to an associated memory for access by an artificial intelligence engine. The artificial intelligence engine may be configured to use one or more machine learning models configured to generate one or more predictions using at least a portion of the treatment data. For example, the artificial intelligence engine may use a machine learning model trained using different treatment data corresponding to different users. The machine learning model may be configured to receive the treatment data corresponding to the user. The machine learning model may analyze at least one aspect of the treatment data and generate at least one prediction corresponding to the at least one aspect of the treatment data. The at least one prediction may be indicative of one or more predicted characteristics of the user. The one or more predicted characteristics of the user may include predicted vital signs of the user, a predicted respiratory rate of the user, a predicted heart rate of the user, a predicted body temperature of the user, a predicted blood pressure of the user, predicted performance parameters of a user implementing a treatment plan, a predicted outcome of a treatment plan being implemented by the user, a predicted injury of the user resulting from the user implementing the treatment plan, or any other suitable predicted characteristic of the user.

[0368] In some embodiments, the systems and methods described herein may be configured to receive one or more predictions from an artificial intelligence engine. The systems and methods described herein may be configured to identify thresholds corresponding to each prediction received from the artificial intelligence engine. For example, the systems and methods described herein may identify one or more characteristics of the user indicated by each prediction.

[0369] The systems and methods described herein may be configured to access a database configured to associate thresholds with user characteristics and / or combinations of user characteristics. For example, the database may include information associating a first threshold with a user's blood pressure. Additionally or alternatively, the database may include information associating thresholds with a user's blood pressure and a user's heart rate. It should be understood that the database may include any number of thresholds associated with any of various user characteristics and / or any combination of user characteristics. In some embodiments, the threshold corresponding to each prediction may include a value or range of values, including an upper and lower limit.

[0370] In some embodiments, the systems and methods described herein may be configured to determine whether a prediction received from an artificial intelligence engine falls within a corresponding threshold range. For example, the systems and methods described herein may be configured to compare a prediction to a corresponding threshold. The systems and methods described herein may be configured to determine whether a prediction falls within a predetermined range of the threshold. For example, if the threshold includes a value, the predetermined range may include an upper limit above this value (e.g., a percentage expression of 0.5% or 1%, or for example, 250 or 750 (units of measurement or other suitable numerical value), or other suitable upper limit) and a lower limit below this value (e.g., a percentage expression of 0.5% or 1%, or for example, 250 or 750 (units of measurement or other suitable numerical value), or other suitable lower limit). Similarly, if a threshold value includes a range that includes a first upper limit and a first lower limit (e.g., defining an acceptable range of one or more user characteristics corresponding to a prediction), the predetermined range may include a second upper limit (e.g., a percentage expression of 0.5% or 1%, or for example, 250 or 750 (units of measure or other suitable numerical value), or other suitable numerical value) above the first upper limit, and a second lower limit (e.g., a percentage expression of 0.5% or 1%, or for example, 250 or 750 (units of measure or other suitable numerical value), or other suitable lower limit) below the first lower limit. It is to be understood that threshold values may include any suitable predetermined ranges and may include any suitable formats in addition to or other than those described herein.

[0371] If the systems and methods described herein determine that the prediction is within a threshold range, the systems and methods described herein may be configured to communicate with (e.g., via or over) an interface at the healthcare provider's computing device to provide prediction and treatment data. In some embodiments, the systems and methods described herein may be configured to generate treatment information using the treatment data. The treatment information may include a summary of the user's implementation of the treatment plan while using the treatment device. The summary may be formatted such that the treatment data is presentable on the healthcare provider's computing device. The systems and methods described herein may be configured to communicate the treatment information along with the prediction and / or treatment data to the healthcare provider's computing device. Alternatively, if the systems and methods described herein determine that the prediction is outside a threshold range, the systems and methods described herein may be configured to update the treatment data for the user to indicate the prediction.

[0372] In some embodiments, the systems and methods described herein may modify at least one aspect of the treatment plan and / or one or more characteristics of the treatment device based on the prediction in response to determining that the prediction is within a threshold range.

[0373] In some embodiments, the systems and methods described herein may be configured to control a treatment device while a user is using the treatment device during a telemedicine session based on the generated predictions. For example, the systems and methods described herein may control one or more characteristics of the treatment device based on the predictions and / or treatment plan.

[0374] A healthcare provider may include a medical professional (such as, for example, a doctor, nurse, therapist, etc.), an exercise professional (such as, for example, a coach, trainer, nutritionist, etc.), or another professional who shares at least one of medical and athletic attributes (such as, for example, an exercise physiologist, physical therapist, occupational therapist, etc.) As used herein, without being limited to the foregoing, a "healthcare provider" may be a human, a robot, a virtual assistant, a virtual assistant in virtual reality and / or augmented reality, or an artificial intelligence entity, including a software program, integrated software and hardware, or hardware alone.

[0375] In some embodiments, the interface may include a graphical user interface configured to provide treatment information and receive input from a healthcare provider. The interface may include one or more input fields, such as a text input field, a drop-down selection input field, a radio button input field, a virtual switch input field, a virtual lever input field, an input field that is audio-, haptically, tactilely, biometrically, or otherwise actuated and / or driven, other suitable input fields, or a combination thereof.

[0376] In some embodiments, a healthcare provider may review the treatment information and / or predictions. Based on the review of the treatment information and / or predictions, the healthcare provider may determine whether to modify at least one aspect of the treatment plan and / or one or more characteristics of the treatment device. For example, the healthcare provider may review the treatment information. Based on the review of the treatment information, the healthcare provider may compare the treatment information to the treatment plan being implemented by the user.

[0377] The healthcare provider may compare (i) expected information about the user while the user is using the treatment device to implement the treatment plan with (ii) a prediction about the user while the user is using the treatment device to implement the treatment plan.

[0378] The predicted information may include one or more vital signs of the user, the user's respiratory rate, the user's heart rate, the user's body temperature, the user's blood pressure, other suitable information of the user, or a combination thereof. The healthcare provider may determine that the treatment plan is having the desired effect if the prediction is within an acceptable range associated with one or more corresponding portions or pieces of the predicted information. Alternatively, the healthcare provider may determine that the treatment plan is not having the desired effect if the prediction is outside an acceptable range associated with one or more corresponding portions or pieces of the predicted information.

[0379] For example, the healthcare provider may determine whether the blood pressure values (e.g., systolic blood pressure, diastolic blood pressure, and / or pulse pressure) indicated by the prediction are within an acceptable range of the expected blood pressure values indicated by the forecast information (e.g., a percent expression of plus or minus 1%, plus or minus 5%, plus or minus 1 unit of measure (or other suitable numerical value), or any suitable percentage-based range or numerical range). The healthcare provider may determine that the treatment plan is having the desired effect if the blood pressure values are within the range of expected blood pressure values. Alternatively, the healthcare provider may determine that the treatment plan is not having the desired effect if the blood pressure values are outside the range of expected blood pressure values.

[0380] In some embodiments, while a user is implementing a treatment plan using a treatment device, a healthcare provider may compare the expected characteristics of the treatment device with the characteristics of the treatment device indicated by the treatment information. For example, the healthcare provider may compare the expected resistance setting of the treatment device with the actual resistance setting of the treatment device indicated by the treatment information. The healthcare provider may determine that the user is implementing the treatment plan properly if the actual characteristics of the treatment device indicated by the treatment information are within a corresponding range of the expected characteristics of the treatment device. Alternatively, the healthcare provider may determine that the user is not implementing the treatment plan properly if the actual characteristics of the treatment device indicated by the treatment information are outside a corresponding range of the expected characteristics of the treatment device.

[0381] If the healthcare provider determines that the prediction and / or treatment information indicates that the user is properly implementing the treatment plan and / or that the treatment plan is having the desired effect, the healthcare provider may decide not to modify at least one of the treatment plan and / or one or more characteristics of the treatment device. Alternatively, if, while the user is implementing the treatment plan using the treatment device, the healthcare provider determines that the prediction and / or treatment information indicates that the user is not, or has not been implementing the treatment plan properly and / or that the treatment plan is not, or has not been having the desired effect, the healthcare provider may decide to modify at least one aspect of the treatment plan and / or one or more characteristics of the treatment device.

[0382] In some embodiments, if the healthcare provider decides to modify at least one aspect of the treatment plan and / or modify one or more characteristics of the treatment device, the healthcare provider may interact with the interface to provide a treatment plan input indicating one or more modifications to the treatment plan and / or modify one or more characteristics of the treatment device. For example, the healthcare provider may use the interface to provide an input indicating an increase or decrease in a resistance setting of the treatment device or other suitable modification to one or more characteristics of the treatment device. Additionally or alternatively, the healthcare provider may use the interface to provide an input indicating a modification to the treatment plan. For example, the healthcare provider may use the interface to provide an input indicating an increase or decrease in the amount of time a user is required to use the treatment device according to the treatment plan or other suitable modification to the treatment plan.

[0383] In some embodiments, based on one or more modifications indicated by the treatment plan input, the systems and methods described herein may be configured to modify at least one aspect of the treatment plan and / or one or more characteristics of the treatment device.

[0384] In some embodiments, the systems and methods described herein may be configured to receive subsequent treatment data about a user while the user is implementing a modified treatment plan using a treatment device. For example, after a healthcare provider provides input modifying one or more characteristics of the treatment plan and / or treatment device and / or after an artificial intelligence engine modifies one or more characteristics of the treatment plan and / or treatment device, the user may continue to use the treatment device to implement the modified treatment plan. The subsequent treatment data may correspond to treatment data generated while the user is implementing the modified treatment plan using a treatment device. In some embodiments, the subsequent treatment data may correspond to treatment data generated while the user is continuing to implement the treatment plan using a treatment device after a healthcare provider receives treatment information and determines not to modify one or more characteristics of the treatment plan and / or treatment device and / or after an artificial intelligence engine determines not to modify one or more characteristics of the treatment plan and / or treatment device.

[0385] In some embodiments, the artificial intelligence engine may use one or more machine learning models to generate one or more subsequent predictions based on the subsequent treatment data. The systems and methods described herein may determine whether each subsequent prediction is within a corresponding threshold range. In response to determining that each subsequent prediction is within a threshold range, the systems and methods described herein may communicate the subsequent treatment data, subsequent treatment information, and / or prediction to a healthcare provider's computing device. In some embodiments, based on the subsequent prediction, the systems and methods described herein may modify at least one aspect of the treatment plan and / or one or more characteristics of the treatment device.

[0386] In some embodiments, the systems and methods described herein may be configured to receive subsequent treatment plan input from a healthcare provider's computing device. Based on the subsequent treatment plan input received from the healthcare provider's computing device, the systems and methods described herein may be configured to further modify the treatment plan and / or control one or more characteristics of the treatment device. The subsequent treatment plan input may correspond to input provided by the healthcare provider at the interface in response to receiving and / or reviewing subsequent treatment information and / or subsequent predictions corresponding to the subsequent treatment data. It should be understood that the systems and methods described herein may be configured to continuously and / or periodically generate predictions based on the treatment data. The systems and methods described herein may be configured to continuously and / or periodically provide treatment information to the healthcare provider's computing device based on treatment data continuously and / or periodically received from the sensors described herein or other suitable sources. Additionally or alternatively, the systems and methods described herein may be configured to continuously and / or periodically monitor a user's characteristics while the user is implementing a treatment plan using the treatment device.

[0387] In some embodiments, a healthcare provider and / or the systems and methods described herein may receive and / or review treatment information, treatment data, and / or predictions continuously or periodically while a user implements a treatment plan using a treatment device. Based on one or more trends indicated by the treatment information, treatment data, and / or predictions, a healthcare provider and / or the systems and methods described herein may determine whether to modify the treatment plan and / or whether to modify and / or control one or more characteristics of the treatment device. For example, the one or more trends may indicate an increase in heart rate or other suitable trend that indicates the user is not properly implementing the treatment plan and / or that the user's implementation of the treatment plan is not having the desired effect.

[0388] In some embodiments, the systems and methods described herein may be configured to use artificial intelligence and / or machine learning to assign patients to cohorts and dynamically control treatment devices based on the assignment during an adaptive telemedicine session. In some embodiments, one or more treatment devices may be provided to a patient. The one or more treatment devices may be used by the patient to implement a treatment plan at any suitable location, including the patient's home, gym, rehabilitation center, hospital, patient's place of employment, hotel, conference center, or permanent or temporary residence.

[0389] In some embodiments, the treatment device may be communicatively coupled to a server. Patient characteristics, including treatment data, may be collected before, during, and / or after a patient implements a treatment plan. For example, personal information, performance information, and measurement information may be collected before, during, and / or after a person implements a treatment plan. Results of each exercise implementation (e.g., improved performance or reduced performance) may be collected from the treatment device throughout the treatment plan and after the treatment plan is implemented. Treatment device parameters, settings, configurations, etc. (e.g., pedal position, amount of resistance, etc.) may be collected before, during, and / or after a treatment plan is implemented.

[0390] Each patient characteristic, each outcome, and each parameter, setting, configuration, etc. can be time-stamped and correlated to a particular step in the treatment plan. Such technology may make it possible to determine which steps in the treatment plan are likely to lead to a desired outcome (e.g., improved strength, range of motion, etc.) and which steps are likely to lead to reduced return (e.g., continuing to exercise after 3 minutes actually delays or harms recovery).

[0391] Data may be collected from the treatment device and / or any suitable computing device (e.g., a computing device into which personal information is entered, such as a computing device interface described herein, a clinician interface, a patient interface, etc.) over time as the patient uses the treatment device to implement various treatment regimens. Data that may be collected may include patient characteristics, treatment regimens implemented by the patient, results of the treatment regimens, any of the data described herein, any other suitable data, or a combination thereof.

[0392] In some embodiments, the data can be processed to group specific people into cohorts. People can be grouped by those with specific or selected similar characteristics, treatment plans, and results of implementing the treatment plans. For example, athletes without medical conditions who implement a treatment plan (e.g., using a treatment device 30 minutes per day, 5 times per week for 3 weeks) and fully recover can be grouped into a first cohort. Elderly people classified as obese who implement a treatment plan (e.g., using a treatment plan 10 minutes per day, 3 times per week for 4 weeks) and improve their range of motion by 75 percent can be grouped into a second cohort.

[0393] In some embodiments, the artificial intelligence engine may include one or more machine learning models trained using the cohort. For example, the one or more machine learning models may be trained to receive input of characteristics of a new patient and to output a treatment plan for the patient that will produce a desired outcome. The machine learning models may match patterns between the characteristics of the new patient and at least one of the patients included in the particular cohort. If a pattern is matched, the machine learning models may assign the new patient to the particular cohort and select a treatment plan associated with the at least one patient. The artificial intelligence engine may be configured to remotely control the treatment device based on the treatment plan while the new patient uses the treatment device to implement the treatment plan.

[0394] As can be appreciated, the characteristics of a new patient (e.g., a new user) may change as the new patient uses a treatment device to implement a treatment plan. For example, the patient's performance may improve faster than expected for people in the cohort to which the new patient is currently assigned. Thus, a machine learning model can be trained to dynamically reassign the new patient to a different cohort containing people with similar characteristics to the new patient's currently changed characteristics based on the changed characteristics. For example, a clinically obese patient may lose weight and no longer meet the weight criteria for the initial cohort, resulting in the patient's weight being reassigned to a different cohort with different weight criteria.

[0395] A different treatment plan may be selected for the new patient, and while the new patient is implementing the treatment plan using the treatment device, the treatment device may be remotely (e.g., remotely) controlled based on the different treatment plan. Such technology may provide a technical solution for remotely controlling the treatment device.

[0396] Furthermore, the systems and methods described herein may lead to faster recovery times and / or better outcomes for patients because a treatment plan that most accurately matches the patient's characteristics is selected and implemented in real time at any given time. "Real time" may also refer to near real time, which may be less than 10 seconds. As used herein, the term "result" may refer to a medical result or a medical outcome. Results and outcomes may refer to a response to a medical intervention.

[0397] Depending on what outcomes are desired, the artificial intelligence engine can be trained to output several treatment plans. For example, one outcome may include recovery to a threshold level (e.g., 75% range of motion) in the fastest amount of time, while another outcome may include full recovery (e.g., 100% range of motion) regardless of the amount of time. Data obtained from patients and sorted into cohorts may indicate that a first treatment plan provides a first outcome for people with characteristics similar to those of the patient, and a second treatment plan provides a second outcome for people with characteristics similar to those of the patient.

[0398] Additionally, the artificial intelligence engine may be trained to output treatment plans that are not optimal for the patient, i.e., suboptimal, non-standard, or otherwise excluded (all referred to without limitation as "excluded treatment plans"). For example, if a patient has high blood pressure, a particular exercise may not be approved or suitable for the patient if the exercise may expose the patient to unnecessary risk or even induce a hypertensive crisis, and thus the exercise may be flagged as an excluded treatment plan for the patient. In some embodiments, the artificial intelligence engine may monitor treatment data received while a patient (e.g., a user) with high blood pressure is using a treatment device to implement an appropriate treatment plan, and if the treatment data indicates that the patient is managing the appropriate treatment plan without, for example, worsening the patient's hypertension condition, the artificial intelligence engine may modify the appropriate treatment plan to include features of the excluded treatment plan that may provide beneficial results for the patient.

[0399] In some embodiments, the treatment plan and / or excluded treatment plans may be presented to the healthcare provider during a telemedicine or telehealth session. The healthcare provider may select a particular treatment plan to have that treatment plan transmitted to the patient and / or control the treatment device based on the treatment plan. In some embodiments, an artificial intelligence engine may receive and / or operate remotely from the patient and treatment device to facilitate telehealth or telemedicine applications, including remote diagnosis, treatment plan determination, and rehabilitation and / or pharmacological prescription.

[0400] In such cases, ...

Claims

1. In a computer-implemented system having a user's computing device, an electromechanical machine configured to be operated by the user while the user is performing the treatment plan, the electromechanical machine including at least one pedal; The user's computing device receives treatment data about the user, including measurement information about the user while the user is using the electromechanical machine, at least one characteristic of the user, at least one characteristic of the electromechanical machine, and at least one aspect of the treatment plan, generates treatment information using the treatment data, transmits the treatment information to a healthcare provider's computing device, and also receives treatment plan input from an interface of the healthcare provider's computing device in response to the treatment information, the treatment plan input including a modification of at least one aspect of the treatment plan, and modifies at least one aspect of the treatment plan based on the treatment plan input; 10. A computer-implemented system comprising: at least one characteristic of the user including demographic information about the user; and wherein the treatment information includes the treatment data as a formatted summary presentable on the healthcare provider's computing device.

2. 10. The computer-implemented system of claim 1, wherein the computing device of the user is configured to further control the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine.

3. 10. The computer-implemented system of claim 1, wherein the computing device of the user is further configured to control the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine during a remote treatment session.

4. 2. The computer-implemented system of claim 1, wherein the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

5. 10. The computer-implemented system of claim 1, wherein at least some of the therapy data corresponds to at least some sensor data from a sensor associated with the electromechanical machine.

6. 10. The computer-implemented system of claim 1, wherein at least some of the therapy data corresponds to at least some sensor data from sensors associated with a wearable device worn by the user while the user is using the electromechanical machine.

7. A computer-implemented method comprising the steps of: receiving treatment data about the user, the treatment data including measurement information about the user while the user is using an electromechanical machine, at least one characteristic of the user, at least one characteristic of the electromechanical machine, and at least one aspect of a treatment plan; generating treatment information using the treatment data; transmitting said treatment information to a healthcare provider's computing device; receiving a treatment plan input from an interface of the healthcare provider's computing device responsive to the treatment information; the treatment plan input includes a modification of at least one aspect of the treatment plan, modifying at least one aspect of the treatment plan based on the treatment plan input; and wherein at least one characteristic of the user includes demographic information about the user, and the treatment information includes the treatment data as a formatted summary presentable on the healthcare provider's computing device.

8. 8. The method of claim 7, further comprising controlling the electromechanical machine while the user is using the electromechanical machine based on at least one modified aspect of the treatment plan.

9. 10. The method of claim 7, further comprising controlling the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine during a remote treatment session.

10. 8. The method of claim 7, wherein the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

11. 8. The method of claim 7, wherein at least some of the therapy data corresponds to at least some sensor data from a sensor associated with the electromechanical machine.

12. 8. The method of claim 7, wherein at least some of the therapy data corresponds to at least some sensor data from sensors associated with a wearable device worn by the user while the user is using the electromechanical machine.

13. 8. The method of claim 7, further comprising receiving subsequent treatment data appropriate for the user while the user is using the electromechanical machine to implement the treatment plan.

14. 14. The method of claim 13, further modifying at least one modified aspect of the treatment plan in response to receiving a subsequent treatment plan input that includes at least one further modification of the at least one modified aspect of the treatment plan and is based on at least one of the treatment data and the subsequent treatment data.

15. A tangible, non-transitory computer-readable medium storing instructions that, when executed, cause a processing device to receive treatment data about a user, the treatment data including measurement information about the user while the user is using an electromechanical machine, at least one characteristic of the user, at least one characteristic of the electromechanical machine, and at least one aspect of a treatment plan; generate treatment information using the treatment data; transmit the treatment information to a healthcare provider computing device; receive treatment plan input from an interface of the healthcare provider computing device responsive to the treatment information; and further, the treatment plan input includes a modification of at least one aspect of the treatment plan, modifying at least one aspect of the treatment plan based on the treatment plan input; and The computer-readable medium further comprises: at least one characteristic of the user including demographic information about the user; and the treatment information includes the treatment data as a formatted summary presentable on the healthcare provider's computing device.

16. 16. The computer-readable medium of claim 15, wherein the processing device is further configured to control the electromechanical machine based on modified aspects of at least one of the modified treatment plans while the user is using the electromechanical machine.

17. 16. The computer-readable medium of claim 15, wherein the processing device is further configured to control the electromechanical machine based on at least one modified aspect of the treatment plan while the user is using the electromechanical machine during a remote treatment session.

18. 16. The computer-readable medium of claim 15, wherein the measurement information includes at least one of the user's vital signs, the user's respiratory rate, the user's heart rate, the user's body temperature, and the user's blood pressure.

19. 16. The computer-readable medium of claim 15, wherein at least some of the therapy data corresponds to at least some sensor data from a sensor associated with the electromechanical machine.

20. 16. The computer-readable medium of claim 15, wherein at least some of the therapy data corresponds to at least some sensor data from sensors associated with a wearable device worn by the user while the user is using the electromechanical machine.

Images