A system and method for predicting the adoption or rejection of a therapy.

Abstract

A system for predicting whether an individual will adopt a prescribed treatment plan includes a data repository, a memory storing instructions, and a control system executing the instructions. The data repository is communicatively coupled to a network and includes a plurality of storage devices for storing data. The control system receives at least a portion of the data stored in the data repository. The at least a portion of the data is associated with the individual. The control system processes the received at least a portion of the data using a machine learning adoption prediction algorithm to determine a likelihood that the individual will adopt the prescribed treatment plan. The control system generates a personalized treatment adoption plan for the individual based at least in part on (i) the prescribed treatment plan and (ii) the likelihood determination that the individual will adopt the prescribed treatment plan.

Description

[Technical Field]

[0001] Cross-reference of related applications This application claims the benefit and priority of U.S. Provisional Patent Application No. 62 / 908,528, filed on 30 September 2019. The entire said document is incorporated herein by reference.

[0002] This disclosure generally relates to systems and methods for predicting the likelihood that an individual will modify their personal behavior to gain health benefits, and more specifically, to predicting the likelihood that an individual will adopt a prescribed treatment plan. [Background technology]

[0003] Treatment plans for individuals are formulated and prescribed daily by healthcare professionals (doctors, nurses, caregivers, etc.) for each individual (patient, etc.). However, there are many cases where individuals do not adopt the prescribed treatment plan, or do not adopt the entire treatment plan as prescribed. Non-adoption of a prescribed treatment plan can occur for various reasons. For example, a prescribed treatment plan may involve therapy using devices that are difficult for the individual to use. Alternatively, a prescribed treatment plan may involve taking medications with side effects that the individual dislikes or cannot cope with. Alternatively, a prescribed treatment plan may involve surgery that the individual does not want to undergo. This disclosure aims to address these issues and other problems. [Overview of the project]

[0004] According to some implementations of this disclosure, a method includes receiving data associated with an individual. A machine learning adoption prediction algorithm is used to process at least a portion of the received data and to determine the likelihood that the individual will adopt a prescribed treatment plan. An individualized treatment adoption plan is generated for the individual, at least in part, based on (i) the prescribed treatment plan and (ii) the likelihood determination that the individual will adopt the prescribed treatment plan.

[0005] According to some implementations of this disclosure, a system that predicts whether an individual will adopt a prescribed treatment plan includes a data repository, memory, and a control system. The data repository is communicably connected to a network and includes multiple storage devices that store data. The memory stores machine-readable instructions and a machine learning adoption prediction algorithm. The control system includes one or more processors and is configured to execute machine-readable instructions to receive at least a portion of the data stored in the data repository. At least a portion of the data is associated with the individual. The control system uses the machine learning adoption prediction algorithm to process at least a portion of the received data and determine the likelihood that the individual will adopt the prescribed treatment plan. The control system generates an individualized treatment adoption plan for the individual, at least in part, based on (i) the prescribed treatment plan and (ii) the likelihood determination that the individual will adopt the prescribed treatment plan.

[0006] According to some implementations of this disclosure, a method for predicting whether an individual will adopt a prescribed treatment plan includes receiving at least a portion of data stored in a data repository. At least a portion of the data is associated with that individual. This data repository is communicably connected to a network and includes multiple storage devices that store the data. A machine learning-based adoption prediction algorithm is used to process at least a portion of the received data to determine the likelihood that the individual will adopt the prescribed treatment plan. An individualized treatment adoption plan is generated for that individual, at least in part, based on (i) the prescribed treatment plan and (ii) the likelihood determination of adopting the prescribed treatment plan.

[0007] According to some implementations of the present disclosure, a system includes a data repository, a memory, and a control system. The memory stores machine-readable instructions and a machine learning-based adoption prediction algorithm. The control system includes one or more processors configured to execute the machine-readable instructions to accumulate data. The data includes past data and current data. The past data is associated with multiple adopters of one or more treatment plans. The current data is associated with an individual. The control system trains the machine learning-based adoption prediction algorithm with the past data such that the machine learning-based adoption prediction algorithm is configured to: (i) receive, as input information, at least a portion of the current data and the prescribed treatment plan for the individual, and (ii) determine, as output information, the likelihood that the individual will adopt the prescribed treatment plan.

[0008] The above summary is not intended to represent each implementation or every aspect of the present disclosure. Further features and advantages of the present disclosure will become apparent from the following detailed description and the figures.

Brief Description of the Drawings

[0009] [Figure 1] FIG. 1 is a block diagram of a system for predicting the likelihood that an individual will adopt a prescribed treatment plan according to some implementations of the present disclosure. [Figure 2] FIG. 2 is a flowchart of a process for predicting the likelihood that an individual will adopt a prescribed treatment plan according to some implementations of the present disclosure. [Figure 3] FIG. 3 represents an exemplary time series of a sleep session according to some implementations of the present disclosure. [Figure 4] FIG. 4 represents an exemplary sleep progression diagram associated with the sleep session of FIG. 3 according to some implementations of the present disclosure.

Modes for Carrying Out the Invention

[0010] While various modifications and alternative forms are possible with respect to this disclosure, specific implementations are shown as examples in the drawings and are described in detail herein. However, it should be understood that this is not intended to limit this disclosure to any particular form, but rather to encompass all modifications, equivalents, and alternatives that fall within the spirit and scope of this disclosure as defined by the appended claims.

[0011] A prescribed treatment plan is one that a physician (or other professional) deems necessary as the optimal treatment for an individual (e.g., a CPAP device user or patient). This disclosure uses a machine learning-based adoption prediction algorithm to process data stored in a data repository and predict the likelihood that an individual will adopt a prescribed treatment plan. Based on this likelihood assessment, an individualized treatment plan is generated. If the likelihood of an individual adopting a prescribed treatment plan is determined to be, for example, 80% or higher, the individualized treatment plan may become that prescribed treatment plan. However, if the likelihood of an individual adopting a prescribed treatment plan is determined to be, for example, less than 80%, the individualized treatment plan should be formulated to be different from that prescribed treatment plan (e.g., one or more modifications to the prescribed treatment plan).

[0012] For example, even if a treatment plan is prescribed that specifies the use of a CPAP device in a first pressure range (e.g., between 12 cmH2O and 16 cmH2O), if the likelihood of the individual adopting that treatment plan is 20% or less, then an individualized treatment adoption plan can be created in which the individual begins treatment by using a mandibular repositioning device (MRD), then begins using the CPAP device in a second pressure range (e.g., lower than the first pressure range), and then gradually increases the CPAP device pressure to the prescribed treatment plan over time.

[0013] Referring to Figure 1, the system 100 includes a data repository 200, a memory 300, a control system 400, and one or more terminal devices 500 (hereinafter referred to as terminal devices 500). As described herein, the system 100 is typically used to predict whether an individual (e.g., a patient) will adopt a treatment plan prescribed (e.g., by a physician / prescriber). In some implementations, if the system 100 determines that the likelihood of an individual adopting the prescribed treatment plan is low (e.g., the likelihood judgment falls below a predetermined threshold), the system 100 may formulate and / or propose one or more modifications to the prescribed treatment plan to facilitate the individual's adoption of the treatment. In such implementations, the goal of the one or more modifications is to ultimately get the individual to adopt the prescribed treatment plan without modification (one or more). In this specification, a modified prescribed treatment plan is referred to as an individualized treatment adoption plan. System 100 is shown as including various elements, but may include any part and / or subset of the elements expressly and described herein, and / or one or more additional elements not specifically shown in Figure 1.

[0014] The data repository 200 is communicatively connected to the network 250. In some implementations, the data repository 200 is communicatively connected to one or more of the control systems 400 and / or terminal devices 500 via the network 250.

[0015] The data repository 200 includes multiple storage devices for storing data. In some implementations of this disclosure, the data repository 200 includes a social media database 210, an electronic medical record database 220, a wearable technology database 230, or any combination thereof. Although the data repository 200 is shown to include various storage devices, it may include any subset of the elements expressly and described herein and / or one or more additional elements not specifically shown in Figure 1.

[0016] The data stored in the data repository 200 may include data of various types and / or content. For example, in some implementations, the data stored in the data repository 200 may include personal data associated with multiple individuals. Alternatively, in some implementations, this data may include adherence data associated with multiple individuals similar to that individual. Alternatively, in some implementations, this data may include a summary of past events that led the individual to a sleep-related diagnosis. Alternatively, in some implementations, this data may include an indication of the type of person who provided the individual with a sleep-related diagnosis. Alternatively, in some implementations, this data may include a determination of whether the individual experiences difficulty breathing during sleep. Alternatively, in some implementations, this data may include information about the individual's kinship. Alternatively, in some implementations, this data may include web searches performed by the individual. Alternatively, in some implementations, this data may include a determination of whether the individual is likely to exhibit binge eating behavior, whether the individual is likely to change their behavior, or both. As an alternative, in some implementations, this data includes a summary of at least a portion of past descriptions of the clinical behaviors the individual has changed. As an alternative, in some implementations, this data includes one or more daily health assessments, including the occurrence and / or frequency of headaches and / or migraines the individual experiences. As an alternative, in some implementations, this data includes the individual's dependent information. As an alternative, in some implementations, this data includes the individual's enrollment in a mobile-based or web-based health management application, social media information associated with the individual, support group information regarding the use of respiratory devices, or any combination thereof. As an alternative, in some implementations, this data includes a determination of whether the individual has a tendency to adopt technology early. As an alternative, in some implementations, this data includes treatment plans prescribed to the individual.As an alternative example, in some implementations, this data may include information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof. It should be understood that the data stored in the data repository 200 may include any combination of the above types of data and / or other types of data not specifically described herein. As an alternative example, in some implementations, this data may include information such as age, sex, BMI, health information, whether the individual is a smoker or non-smoker, whether the individual drinks alcohol, or any combination thereof. As an alternative example, in some implementations, this data may include information such as daytime sleepiness, snoring, fatigue, exercise level (duration, intensity, type), self-reported distress points such as difficulty maintaining sleep, or any combination thereof.

[0017] The data stored in the data repository 200 may include training data associated with multiple individuals. In some such implementations, the control system 400 executes machine-readable instructions (stored in memory 300, another memory, or both) to train a machine learning-based adoption prediction algorithm 330 (stored in memory 300, another memory, or both) with the training data. The machine learning-based adoption prediction algorithm 330 is configured to use this training data to receive at least a portion of the data stored in the data repository 200 associated with an individual as input information and to determine the likelihood that the individual will adopt a prescribed treatment plan as output information. As described herein, based on the likelihood of adoption by the individual, the prescribed treatment plan can be implemented, or one or more aspects of the prescribed treatment plan can be modified to determine an individualized treatment adoption plan for that individual.

[0018] In some implementations, the control system 400 executes machine-readable commands 320 to receive feedback associated with the individual's level of compliance with a prescribed treatment plan and / or individualized treatment adoption plan. The control system 400 is further configured to generate a second individualized treatment adoption plan for the individual, at least in part, based on the prescribed treatment plan, a first individualized treatment adoption plan, the feedback, or any combination thereof. This feedback may include, for example, the individual's answers to one or more questions, data generated by one or more sensors, or both. In some such implementations, this one or more sensors may include flow sensors and / or pressure sensors of a CPAP device / respiratory therapy device, a microphone of a mobile device, a motion sensor, an activity sensor (for measuring the individual's activity level, e.g., steps), a sonar sensor, an ultra-wideband radio frequency sensor, an RF sensor, a temperature sensor for measuring the individual's core temperature and / or surface temperature and / or ambient temperature, an audio or flow sensor for monitoring snoring, or any combination thereof. This one or more sensor may be included in a wearable device worn by the individual, one or more stationary devices in the individual's living area, or a combination thereof.

[0019] In some implementations of this disclosure, the received feedback is used by the machine learning adoption prediction algorithm 330 to learn from errors it makes in order to improve the performance of the system 100. For example, in one instance, the machine learning adoption prediction algorithm 330 learns through feedback (manual input or automated judgment) that in a given case, it might have predicted that the individual would adopt the prescribed treatment plan with a 90% probability, but in reality, the individual did not adopt it. In such an instance, the machine learning adoption prediction algorithm 330 can be fine-tuned to increase the likelihood of lowering the relative percentage likelihood in future instances, which could lead to different outcomes (for example, creating an individualized treatment adoption plan instead of prescribing the prescribed treatment plan to the individual).

[0020] One or more terminal devices 500 can be associated with an individual and configured to receive one or more notifications from a control system 400. In some implementations, these notifications are based on a generated individualized treatment plan for that individual. One or more terminal devices 500 may include a personal computer 510, a mobile device 520, a respiratory treatment device 530 such as a CPAP device, or any combination thereof.

[0021] In some implementations of the system 100 that include a respiratory therapy device 530, notifications received from the control system 400 may include commands and / or instructions to adjust one or more settings of the respiratory therapy device 530. For example, the pressure setting or specified pressure range of the respiratory therapy device 530 can be changed during use to increase or decrease the pressure provided. Changes to the respiratory therapy device 530 may be based at least in part on an individualized treatment plan, feedback received from the individual during the implementation of the individualized treatment plan and / or prescribed treatment plan, a portion of the data stored in the data repository 200, or any combination thereof. One or more terminal devices 500 are shown as including various terminal devices, but may include any subset of the elements expressly and described herein and / or one or more additional elements not specifically shown in Figure 1.

[0022] In some implementations, memory 300 stores machine-readable instructions 320 and a machine learning-based predictive algorithm 330. The control system 400 is communicatively connected to memory 300. Memory 300 may include one or more physically separate memory devices, one or more of which can be connected to and / or embedded in any one of the terminal devices 500. In some implementations, memory 300 includes non-volatile memory, battery-powered static RAM, volatile RAM, EEPROM memory, NAND flash memory, or any combination thereof. In some implementations, memory 300 is a removable form of memory (e.g., a memory card).

[0023] The control system 400 includes one or more processors 410 (hereinafter, processor 410). The control system 400 is generally used to control (e.g., operate) various components of system 100 and / or to analyze data acquired and / or generated by the components of system 100. The processor 410 executes machine-readable instructions 320 stored in the memory device 300 and may be a general-purpose or special-purpose processor or microprocessor. Although Figure 1 shows one processor 410, the control system 400 may include any appropriate number of processors (e.g., one processor, two processors, five processors, ten processors, etc.). The memory 300 may be any appropriate computer-readable storage device or media, such as a random or serial access memory device, a hard drive, a solid-state drive, or a flash memory device. The control system 400 and / or the memory 300 may be coupled to and / or housed in one or more housings of terminal devices 500. The control system 400 and / or memory 300 can be centralized (within one housing) or distributed (within two or more physically separate housings).

[0024] In some implementations, the control system 400 is a dedicated electronic circuit. In some implementations, the control system 400 is an application-specific integrated circuit. In some implementations, the control system 400 includes discrete electronic components. The control system 400 can receive input information (one or more) (e.g., signals, generated data, instructions, etc.) from any of the other elements of system 100. The control system 400 can provide output signals (one or more) to trigger one or more actions in system 100. In some implementations, the control system 400 or a part of it (e.g., at least one processor of the control system 400) may reside in the cloud (e.g., integrated into a server, integrated into an Internet of Things (IoT) device, connected to the cloud, and subject to edge cloud processing), on one or more servers (e.g., remote servers, local servers, etc.), or any combination thereof.

[0025] In some implementations of this disclosure, the processor 410 is configured to execute machine-readable instructions 320 to receive at least a portion of the data stored in the data repository 200. In some such implementations, the portion of the received data is associated with the individual. A machine learning-based adoption prediction algorithm 330 processes the received data or a portion of it to determine the likelihood that the individual will adopt a prescribed treatment plan. In some implementations, if the likelihood of adoption is below a threshold (e.g., less than 95%, less than 90%, less than 80%), the processor 410 executes machine-readable instructions 320 to generate a personalized treatment adoption plan for the individual that differs from the prescribed treatment plan. This personalized treatment adoption plan may be based on the prescribed treatment plan but may include one or more modifications, additions, deletions, or any combination thereof.

[0026] For example, a machine learning-based adoption prediction algorithm 330 can set a threshold for determining the likelihood that an individual will adopt a prescribed treatment plan. In some implementations, the likelihood is determined to meet a first threshold if the likelihood of an individual adopting a prescribed treatment plan is less than 80%. In some implementations, the prescribed treatment plan includes a first recommendation that the individual begin treatment using the respiratory therapy device 530 within a first pressure range. In some such implementations, the individualized treatment adoption plan (e.g., a modified version of the prescribed treatment plan) includes a second modified recommendation that the individual begin treatment using the respiratory therapy device 530 within a second pressure range different from the first pressure range (e.g., the second pressure range is relatively low and / or more tolerable for the individual).

[0027] In some implementations, the prescribed treatment plan includes a first recommendation that the individual initiate treatment using the respiratory treatment device 530. In some such implementations, the individualized treatment plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation that the individual initiate treatment using the mandibular repositioning device and not the respiratory treatment device 530.

[0028] In some implementations, the prescribed treatment plan includes a first recommendation that the individual begin treatment using the respiratory therapy device 530. In some such implementations, the individualized treatment adoption plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation that the individual begin treatment by engaging with a coaching program (virtual or in person) that provides hints, facts, information, benefits, challenges, etc., regarding the use of the respiratory therapy device 530. In some such implementations, the system 100 can use feedback to measure the individual's progress from coaching and determine when to recommend the next treatment step (e.g., actual use of the respiratory therapy device 530, use of MRD, etc.).

[0029] In some implementations, the prescribed treatment plan includes a first recommendation that the individual initiate treatment using the respiratory therapy device 530 within a first pressure range. In some such implementations, the individualized treatment plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation that the individual initiate treatment by undergoing surgery, rather than starting with the respiratory therapy device 530. In some such implementations, the recommended surgery may include, for example, bariatric surgery, oral surgery, liposuction, or any combination thereof.

[0030] Oral and maxillofacial surgery (OMFS or OMS) specifically includes surgery of the face, mouth, and jaw. Such OMS procedures may include, for example, alveolar bone surgery (removal of impacted teeth, difficult tooth extractions, extractions in diseased patients, bone grafting, or pre-prosthetic surgery to improve tissue for placement of implants, dentures, or other dental prostheses). Other OMS procedures may include osseointegrated dental implants, as well as surgeries to insert maxillofacial implants for the placement of craniofacial prostheses and bone-fixed hearing aids. Other OMS procedures may include cosmetic surgery of the head and neck (wrinkle skin removal / facelift, eyebrow shaping, blepharoplasty / Asian blepharoplasty, ear shaping, rhinoplasty, septoplasty, buccal shaping, jaw shaping, oculoplasty, neck liposuction, hair transplantation, lip augmentation, Botox, fillers, platelet-rich plasma, stem cells, chemical epidermal peeling, mesotherapy, and other injectable cosmetic procedures). OMS procedures may also include orthognathic surgery, surgical treatment / correction of odontofacial deformities, management of facial trauma, and treatment of sleep apnea.

[0031] In some implementations, the prescribed treatment plan includes a first recommendation that the individual begin treatment using the respiratory treatment device 530 within a first pressure range. In some such implementations, an individualized treatment adoption plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation that the individual begin treatment by adopting a diet, adopting an exercise plan, or a combination thereof. For example, a personal trainer may be assigned to create a training schedule that improves the individual's quality of life rather than fatigues them. Alternatively, the training schedule may be designed to avoid requiring excessive exercise from the individual, as this could worsen sleep quality (e.g., increase snoring). The trainer may also assist with training specific muscles to help avoid sleep-related breathing problems (such as sleep apnea).

[0032] In some implementations, the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device. In some such implementations, the individualized treatment adoption plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation for the individual to begin treatment using an adjustable bed-related device. Adjustable bed-related devices can help address positional problems such as postural obstructive sleep apnea (OSA) and positional snoring. In some implementations, adjustable bed-related devices include adjustable pillows, adjustable mattresses, adjustable bed frames, adjustable bedding, or any combination thereof.

[0033] In some implementations, the prescribed treatment plan includes a first recommendation that the individual begin treatment using the respiratory treatment device 530. In some such implementations, the individualized treatment adoption plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation that the individual begin treatment using the nasal strip.

[0034] The above examples of modifications made to prescribed treatment plans to create individualized treatment adoption plans are described in a specific order and / or relationship, but the above exemplary modifications are intended to be combinable in any order and / or combination to create an individualized treatment adoption plan for each person.

[0035] For example, in some implementations, the prescribed treatment plan includes a first recommendation that the individual initiate treatment using the respiratory treatment device 530. In some such implementations, the individualized treatment plan (e.g., a modified version of the prescribed treatment plan) includes a second recommendation that the individual initiate treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier during sleep, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof.

[0036] In some implementations, before any treatment is administered to that individual, the system 100 provides the individual with an individualized treatment adoption plan (for example, via one or more terminal devices 500). A modified version of the prescribed treatment plan is provided to the individual based at least in part on a likelihood assessment that the individual will adopt the prescribed treatment plan.

[0037] In some implementations, the machine learning-based adoption prediction algorithm 330 is configured to determine that the likelihood of an individual adopting a prescribed treatment plan satisfies a second threshold (for example, that the likelihood is greater than a predetermined amount). Based on this determination, the generated individualized treatment adoption plan for that person becomes the prescribed treatment plan. For example, the likelihood of an individual adopting a prescribed treatment plan satisfies the second threshold if the likelihood is 80 percent or greater, 85 percent or greater, 90 percent or greater, 95 percent or greater, or any other arbitrary percentage likelihood.

[0038] In some implementations of this disclosure, a control system 400 receives user input information from an individual via one or more terminal devices 500. This user input information can be processed using a machine learning-based adoption prediction algorithm 330. In some implementations, the user input information includes one or more videos depicting at least a portion of an individual, one or more images depicting at least a portion of an individual, or a combination thereof.

[0039] In some implementations, the machine learning-based adoption prediction algorithm 330 can process this user input information by analyzing it to determine the individual's risk of sleep disorders. (For example, it can analyze the individual's image data to determine facial color, eye data, etc.) The machine learning-based adoption prediction algorithm 330 is configured to predict the individual's risk of sleep apnea based on this analysis. The calculated risk of sleep apnea can be included in the likelihood determination of the individual adopting the prescribed treatment plan. For example, if the individual is determined to be at risk of sleep apnea or actually has sleep apnea, the machine learning-based adoption prediction algorithm 330 may predict that the individual is likely to adopt the prescribed treatment plan. Similarly, if the machine learning-based adoption prediction algorithm 330 determines that the risk of sleep apnea is low, it may determine that the individual is unlikely to adopt the prescribed treatment plan because they are unlikely to receive any benefits or the benefits will not outweigh the inconvenience of treatment.

[0040] The processing of user input information can, as an alternative and / or additional method, be used to assist in determining the effectiveness of currently prescribed treatments. System 100 can generate one or more modifications to the current treatment plan based on its effectiveness or lack thereof, thereby helping to increase the likelihood that the individual will continue to adopt and / or adhere to the treatment plan in the long term and not discontinue treatment (for example, within one or two months).

[0041] As described in relation to Figure 1, the system 100 may include one or more sensors for collecting information. These one or more sensors may include a pressure sensor that outputs pressure data that can be stored in the memory 300 and / or analyzed by the processor 410 of the control system 400. In some implementations, this pressure sensor is an air pressure sensor (e.g., an atmospheric pressure sensor) that generates sensor data indicating the respiration (e.g., inspiration and / or expiration) of the user of the respiratory therapy device 530 and / or ambient pressure. This pressure sensor may be, for example, a capacitive sensor, an electromagnetic sensor, a piezoelectric sensor, a strain gauge sensor, an optical sensor, a potentiometric sensor, or any combination thereof.

[0042] This one or more sensors may include a flow sensor that outputs flow data. In some implementations, this flow sensor is used to determine the airflow from the respiratory therapy device 530, the airflow through the tubing of the respiratory therapy device 530, the airflow through the mask of the respiratory therapy device 530, or any combination thereof. The flow sensor may be a mass flow sensor such as a rotary flow meter (e.g., a Hall effect flow meter), a turbine flow meter, an orifice flow meter, an ultrasonic flow meter, a hot-wire sensor, an eddy current sensor, a membrane sensor, or any combination thereof.

[0043] This one or more sensors may include a temperature sensor that outputs temperature data. In some implementations, this temperature sensor generates temperature data indicating the individual's core temperature, their skin temperature, the temperature of the air flowing from the respiratory therapy device 530, the ambient temperature, or any combination thereof. This temperature sensor may be, for example, a thermocouple sensor, a thermistor sensor, a silicon bandgap temperature sensor or semiconductor-based sensor, a resistance temperature detector, or any combination thereof.

[0044] This one or more sensors may include a microphone that outputs audio data. This audio data generated by the microphone can be reproduced as one or more sounds during a sleep session. The audio data from the microphone can also be used to identify events experienced by the user during a sleep session (for example, using the control system 400), as further detailed herein. This microphone can be linked to or integrated with any one or more of the terminal devices 500.

[0045] One or more of these sensors may include a speaker that emits sound waves audible to an individual. This speaker can be used, for example, as an alarm clock, or to play an alert or message to the individual (for example, in response to an event). In some implementations, this speaker can be used to transmit audio data generated by a microphone. The speaker can be connected to or integrated with one or more of the terminal devices 500.

[0046] The microphone and speaker can be used as separate devices. In some implementations, the microphone and speaker can be incorporated into an acoustic sensor, for example, as described in WO2018 / 050913, which is entirely incorporated herein by reference. In such an implementation, the speaker generates or emits sound waves at predetermined intervals, and the microphone detects reflections of the sound waves emitted from the speaker. The sound waves generated or emitted by the speaker have frequencies inaudible to the human ear (e.g., less than 20 Hz or greater than about 18 kHz) so as not to disturb the individual's sleep. Based at least in part on the data from the microphone and / or speaker, the control system 400 can determine the individual's location and / or one or more of the parameters described herein.

[0047] This one or more sensors may include a radio frequency (RF) transmitter that generates and / or emits radio waves having a predetermined frequency and / or amplitude (e.g., within a high-frequency band, within a low-frequency band, long-wave signal, short-wave signal, etc.). The RF receiver detects reflections of radio waves emitted from the RF transmitter. This data can be analyzed by the control system 400 to determine the location of the individual and / or one or more of the various parameters or measurements described herein. The RF receiver may also be used for wireless communication in system 100. In some implementations, the RF receiver and RF transmitter are combined as part of a radio frequency (RF) sensor. In some such implementations, the RF sensor includes a control circuit. Specific forms of RF communication may include WiFi and Bluetooth®, etc.

[0048] In some implementations, RF sensors are part of a mesh system. One example of a mesh system is a WiFi mesh system, which may include mesh nodes, mesh routers(s), and mesh gateways(s), each of which may be mobile / movable or fixed. In such an implementation, the WiFi mesh system includes a WiFi router and / or WiFi controller and one or more satellites (e.g., access points), each of which includes an RF sensor. The WiFi routers and satellites communicate with each other in constant communication using WiFi signals. The WiFi mesh system can be used to generate motion data based on changes in the WiFi signal (e.g., differences in received signal strength) between the routers and satellites(s), caused by the movement of objects or people partially interfering with the signal. This motion data may represent motion, breathing, heart rate, walking, falls, behavior, or any combination thereof.

[0049] This one or more sensors may include a camera that outputs image data that can be reproduced as one or more images (e.g., still images, videos, thermal images, or a combination thereof) that can be stored in memory 300. The image data from the camera can be used by the control system 400 to determine one or more of the various parameters for predicting the adoption of therapy as described herein. For example, the image data from the camera can be used to identify the location of an individual, determine the time the individual goes to bed, determine the time the individual wakes up, and determine whether the individual interacts with the respiratory therapy device 530.

[0050] This one or more sensors may include an infrared (IR) sensor that outputs infrared image data that can be reproduced as one or more infrared images (e.g., still images, videos, or both) that can be stored in memory 300. The infrared data from the IR sensor can be used to determine one or more parameters during a sleep session, including the individual's body temperature and / or movement. This IR sensor can also be used in combination with a camera to measure the individual's presence, location, and / or movement. The IR sensor can detect infrared light with wavelengths from, for example, about 700 nm to about 1 mm, while the camera can detect visible light with wavelengths from about 380 nm to about 740 nm.

[0051] This one or more sensors may include a PPG sensor that outputs physiological data associated with the individual, which can be used to determine one or more parameters, such as heart rate, heart rate variability, cardiac cycle, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-to-expiratory ratio, estimated blood pressure parameters (one or more), or any combination thereof. The PPG sensor can be worn by the individual, embedded in clothing and / or fabrics worn by the individual, embedded in and / or connected to any one of the terminal devices 500, etc.

[0052] This one or more sensors may include an electrocardiogram (ECG) sensor that outputs physiological data associated with the electrical activity of the individual's heart. In some implementations, this ECG sensor includes one or more electrodes positioned on or around a portion of the individual during a sleep session. The physiological data from this ECG sensor can be used, for example, to determine one or more of the parameters described herein.

[0053] These one or more sensors may include an electroencephalogram (EEG) sensor that outputs physiological data associated with the electrical activity of the user's brain 210. In some implementations, this EEG sensor includes one or more electrodes positioned on or around the individual's scalp during a sleep session. The physiological data from this EEG sensor can be used, for example, to determine the individual's sleep state at a given time during a sleep session. In some implementations, this EEG sensor can be integrated into any one of the terminal devices 500.

[0054] The one or more sensors may include a capacitive sensor that outputs data that can be stored in memory 300 and used by the control system 400 to determine one or more parameters described herein, a force sensor, and a strain gauge sensor. An electromyography (EMG) sensor included in the one or more sensors may output physiological data associated with electrical activity produced by one or more muscles. An oxygen sensor included in the one or more sensors may output oxygen data indicating the oxygen concentration of a gas (e.g., in the tubing of the respiratory therapy device 530 and / or in the mask used with the respiratory therapy device 530). The oxygen sensor may be, for example, an ultrasonic oxygen sensor, an electro-oxygen sensor, a chemical oxygen sensor, an optical oxygen sensor, or any combination thereof. In some implementations, the one or more sensors may also include a galvanic skin response (GSR) sensor, a blood flow sensor, a respiratory sensor, a pulse sensor, a blood pressure sensor, an oximetry sensor, or any combination thereof.

[0055] One or more of these sensors may include analyte sensors that can be used to detect the presence or absence of an analyte in the exhaled breath of the individual. The data output by the analyte sensors can be stored in memory 300, and the control system 400 can use this information to determine the identity and concentration of any analyte in the individual's breath, which may be useful in determining whether the individual should adopt a treatment plan. Individuals dependent on a particular substance may be redirected to a different treatment plan based on the adoption success rate of individuals in similar situations. In some implementations, the analyte sensor is positioned near the individual's mouth to detect an analyte in the breath exhaled from the individual's mouth. The analyte sensor can be positioned near the individual's nose to detect an analyte in the breath exhaled from the user's nose. In some implementations, the analyte sensor is a volatile organic compound (VOC) sensor that can be used to detect carbonaceous chemicals or compounds.

[0056] One or more of these sensors may include a moisture sensor that outputs data that can be stored in memory 300 and used by the control system 400. The moisture sensor can be used to detect moisture in various areas surrounding the individual (e.g., inside the tubing of the respiratory therapy device 530 or inside the mask used with the respiratory therapy device 530, near the individual's face, etc.). Therefore, in some implementations, the moisture sensor can be connected to or integrated with any one of the terminal devices 500. The moisture sensor can also be used to monitor the humidity of the surrounding environment around the individual, such as the air in a bedroom.

[0057] One or more sensors may include a LiDAR (Light Detection and Ranging) sensor for depth sensing. This type of optical sensor (e.g., a laser sensor) can be used to detect objects and create a three-dimensional (3D) map of the surrounding environment, such as a living space. LiDAR generally uses pulsed lasers to measure time of flight. LiDAR is also called 3D laser scanning. In one use case of such a sensor, a stationary or mobile device (such as a smartphone) with a LiDAR sensor can measure and map an area more than 5 meters away from the sensor. LiDAR data can be fused with point cloud data estimated by, for example, an electromagnetic RADAR sensor. LiDAR sensors can also use artificial intelligence (AI) to automatically create geofencing for a RADAR system by detecting and classifying features in space that may pose problems for the RADAR system, such as glass windows (which may be highly reflective to RADAR). LiDAR can also be used to estimate a person's height, as well as changes in height that occur when a person sits or falls. LiDAR can be used to form a 3D mesh representation of the environment. In further applications, LiDAR can reflect off solid surfaces through which radio waves pass (e.g., radio wave-transparent materials), enabling the classification of different types of obstacles.

[0058] Referring to Figure 2, a flowchart of Method 1100 for predicting the likelihood that an individual will adopt a prescribed treatment plan is shown. One or more steps of Method 1100 described herein can be performed using System 100 (Figure 1). Step 1101 of Method 1100 includes receiving data. The received data may be a portion of data stored in a data repository (e.g., Data Repository 200). As described above, this data may be associated with the individual and / or several other individuals. Step 1102 of Method 1100 determines the likelihood that the individual will adopt a prescribed treatment plan. This determination can be made using a machine learning adoption prediction algorithm that processes the received data.

[0059] In step 1103 of Method 1100, an individualized treatment adoption plan is generated for that person. This individualized treatment adoption plan may be based on the prescribed treatment plan but may include one or more changes, additions, deletions, or any combination thereof.

[0060] As used herein, sleep sessions can be defined in several ways, for example, based on the initial start and end times. Referring to Figure 3, an exemplary time series 300 of a sleep session is shown. Time series 300 is defined by bedtime (t bed ) and the time of falling asleep (t GTS ) and the time of first sleep onset (t sleep ) and the first minute awakening MA1 and the second minute awakening MA2, and the awakening time (t wake ) and wake-up time (t rise ) and include.

[0061] In this specification, a sleep session can be defined in several ways. For example, a sleep session can be defined by its initial start time and end time. In some implementations, a sleep session is the duration of time a user is asleep; that is, a sleep session has a start time and an end time, and the user does not wake up until the end time during the sleep session. In other words, time the user is awake is not included in the sleep session. From the first definition of a sleep session, if a user wakes up and falls asleep multiple times during the night, each sleep period separated by those periods of wakefulness becomes a sleep session.

[0062] Alternatively, in some implementations, a sleep session has a start time and an end time, and during that sleep session, the user can remain awake without the sleep session ending, as long as the continuous time the user is awake is less than the wakefulness duration threshold. The wakefulness duration threshold can be defined as a percentage of the sleep session. The wakefulness duration threshold could be, for example, about 20 percent of the sleep session, about 15 percent of the sleep session duration, about 10 percent of the sleep session duration, about 5 percent of the sleep session duration, about 2 percent of the sleep session duration, etc., or any other arbitrary threshold percentage. In some implementations, the wakefulness duration threshold is defined as, for example, about 1 hour, about 30 minutes, about 15 minutes, about 10 minutes, about 5 minutes, about 2 minutes, etc., or any other arbitrary amount of time.

[0063] In some implementations, a sleep session is defined as the total time from the time the user first goes to bed at night until the time the user last wakes up the following morning. In other words, a sleep session can be defined as the time that begins at a first time (e.g., 10:00 p.m.) on a first date that can be called the current night (e.g., Monday, January 6, 2020) when the user first goes to bed with the intention of sleeping (not if the user first intends to watch TV or use their smartphone before going to sleep), and ends at a second time (e.g., 7:00 a.m.) on a second date that can be called the following morning (e.g., Tuesday, January 7, 2020) when the user first wakes up with the intention of not going to sleep again the following morning.

[0064] In some implementations, users can manually define the start of a sleep session and / or manually end a sleep session. For example, a user can manually start or end a sleep session by selecting one or more user-selectable elements displayed on the display device 172 of the user device 170 (Figure 1) (for example, by clicking or tapping).

[0065] Referring to FIG. 3, an exemplary time series 300 of a sleep session is shown. The time series 300 includes a bedtime (tbed), a time to fall asleep (t GTS ), a first sleep onset time (t sleep ), a first micro-awakening MA1, a second micro-awakening MA2, an awakening A, an awakening time (t wake ), and a wake-up time (t rise ).

[0066] The bedtime t bed is associated with the time when the user first goes to bed (e.g., the bed 230 in FIG. 2) before falling asleep (e.g., the user lies down or sits on the bed). The bedtime t bed can be specified based on a bedtime threshold duration to distinguish between the time when the user goes to bed to sleep and the time when the user goes to bed for other reasons (e.g., to watch TV). For example, the bedtime threshold duration can be at least about 10 minutes, at least about 20 minutes, at least about 30 minutes, at least about 45 minutes, at least about 1 hour, at least about 2 hours, etc. In this specification, the bedtime t bed is described with reference to the bed, but more generally, the bedtime t bed can represent the time when the user first gets to any place (e.g., a sofa, a chair, a sleeping bag, etc.) to sleep.

[0067] The time to fall asleep (GTS) is associated with the time (t bed ) when the user first attempts to fall asleep after getting into bed. For example, after getting into bed, the user may engage in one or more activities (e.g., reading, watching TV, listening to music, using the user device 170, etc.) to relax before trying to sleep. The first sleep onset time (t sleep ) is the time when the user first falls asleep. For example, the first sleep onset time (t sleep ) can be the time when the user first enters the non-REM sleep stage.

[0068] The awakening time t wakeThis is the time associated with when the user became awake without falling back asleep (for example, instead of waking up in the middle of the night and falling back asleep). After initially falling asleep, the user may experience one of several more unconscious micro-awakenings (e.g., micro-awakenings MA1 and MA2) with short durations (e.g., 5 seconds, 10 seconds, 30 seconds, 1 minute, etc.). The user's wake time t wake Instead, the user goes through micro-awakenings MA1 and MA2 respectively, and then falls asleep again. Similarly, after initially falling asleep, the user may have one or more conscious awakenings (e.g., awakening A) (e.g., getting up to go to the toilet, taking care of a child or pet, sleepwalking, etc.). However, the user falls back asleep after awakening A. Therefore, the awakening time t wake This can be defined, for example, based on the arousal threshold duration (e.g., the user is awake for at least 15 minutes, at least 20 minutes, at least 30 minutes, at least 1 hour, etc.).

[0069] Similarly, wake-up time t rise This is associated with the time when the user leaves bed with the intention of ending the sleep session (not, for example, going to the toilet in the middle of the night, taking care of children or pets, or wandering around). In other words, the wake-up time t rise This is the time when the user last left bed without returning to bed until the next sleep session (e.g., the following night). Therefore, the wake-up time t rise This can be defined, for example, based on the wake-up threshold duration (e.g., the user is out of bed for at least 15 minutes, at least 20 minutes, at least 30 minutes, at least 1 hour, etc.). The second bedtime after the sleep session is t bed It can also be defined based on the wake-up threshold duration (for example, the duration for which the user is out of bed for at least 4 hours, at least 6 hours, at least 8 hours, at least 12 hours, etc.).

[0070] As stated above, the user's first t bed from the final t riseThe last time of wakefulness t is determined based on a predetermined threshold duration after an event (e.g., falling asleep or getting out of bed). wake and / or last wake-up time t rise The threshold duration can be customized to suit the user. For a typical user who goes to bed at night and wakes up and gets up in the morning, any duration between approximately 12 and 18 hours (when the user is awake (t wake ) or wake up (t rise ) then go to bed (t bed ), falling asleep (t GTS ) or sleep (t sleep A threshold time of (until ) can be used. For users who spend a long time in bed, a shorter threshold time (e.g., approximately 8 to 14 hours) may be used. This threshold time may be initially selected and / or adjusted later based on a system that monitors the user's sleep behavior.

[0071] Total time in bed (TIB) is the time in bed t bed From wake time rise This is the duration up to t. Total sleep time (TST) is the duration from the time of first sleep onset to the time of wakefulness, excluding conscious and unconscious wakefulness and / or minute wakefulness during that time. Total sleep time (TST) is generally shorter than total time in bed (TIB) (e.g., 1 minute shorter, 10 minutes shorter, 1 hour shorter, etc.). For example, referring to time series 300 in Figure 3, total sleep time (TST) is from the time of first sleep onset t sleep From awakening time t wake However, the durations of the first micro-awakening MA1, the second micro-awakening MA2, and awakening A are excluded. As shown in the figure, in this example, total sleep time (TST) is shorter than total time in bed (TIB).

[0072] In some implementations, total sleep time (TST) can be defined as total continuous sleep time (PTST). In such implementations, total continuous sleep time excludes a predetermined initial portion or duration of the first non-REM stage (e.g., light sleep stage). For example, this predetermined initial portion may be approximately 30 seconds to 20 minutes, approximately 1 minute to 10 minutes, or approximately 3 minutes to 5 minutes. Total continuous sleep time is a measure of continuous sleep and smooths the sleep / wake sleep progression diagram. For example, upon a user's initial sleep onset, the user may enter a first non-REM stage for a very short period (e.g., approximately 30 seconds), return to a short period (e.g., 1 minute) of wakefulness, and then return to the first non-REM stage. In this example, total continuous sleep time excludes the first instance of the first non-REM stage (e.g., approximately 30 seconds).

[0073] In some implementations, the sleep session is defined by the time of going to bed (t bed It starts with ) and wake-up time (t rise The time that ends at the time of first sleep (t) is defined as total time in bed (TIB). In some implementations, a sleep session is defined as the time that ends at the time of first sleep (t). sleep ) begins, and the wake time (t wake It is defined as ending at t GTS ) begins, and the wake time (t wake It is defined as ending at the time of sleep onset (t). In some implementations, a sleep session is defined as ending at the time of sleep onset (t). GTS It starts with ) and wake-up time (t rise It is defined as ending at bedtime (t). In some implementations, a sleep session is defined as ending at bedtime (t). bed ) begins, and the wake time (t wake It is defined as ending at the time of the first sleep (t). In some implementations, a sleep session is defined as ending at the time of the first sleep (t). sleep It starts with ) and wake-up time (t rise It is defined as something that ends in ).

[0074] Referring to Figure 4, exemplary sleep progression diagrams 600 corresponding to time series 301 (Figure 3) are shown for several implementation configurations. As illustrated, the sleep progression diagram 600 includes a sleep / wake signal (bold), a wakefulness stage axis 610, a REM stage axis 620, a light sleep stage axis 630, and a deep sleep stage axis 640. The intersection of the sleep / wake signal and one of axes 610-640 indicates the sleep stage at any given time during the sleep session.

[0075] Sleep / wake signals can be generated based on physiological data associated with the user (e.g., generated by one or more of the sensors described herein). Sleep / wake signals may indicate one or more sleep states, including wakefulness, relaxed wakefulness, micro-wakefulness, REM phase, first non-REM phase, second non-REM phase, third non-REM phase, or any combination thereof. In some implementations, one or more of the first, second, and third non-REM phases may be grouped together and classified as a light sleep phase or a deep sleep phase. For example, a light sleep phase may include the first non-REM phase, and a deep sleep phase may include the second and third non-REM phases. While the sleep progression diagram 600 is shown in Figure 4 as including a light sleep phase axis 630 and a deep sleep phase axis 640, in some implementations, the sleep progression diagram 600 may include axes representing the first, second, and third non-REM phases, respectively. In other implementations, the sleep / wake signal may also represent respiratory signal, respiratory rate, inspiratory amplitude, expiratory amplitude, inspiratory-to-expiratory ratio, number of events per hour, event pattern, or any combination thereof. Information describing the sleep / wake signal can be stored in memory 300.

[0076] The sleep progression diagram 600 can be used to determine one or more sleep-related parameters, such as sleep latency (SOL), wakefulness during the night (WASO), sleep efficiency (SE), sleep fragmentation index, sleep block, or any combination thereof.

[0077] Sleep latency (SOL) is the time it takes to fall asleep (t GTS ) and first sleep time (t sleep It is defined as the time between the time the user first attempts to fall asleep and the time the user actually falls asleep. In some implementations, sleep latency is defined as persistent sleep latency (PSOL). Persistent sleep latency differs from sleep latency in that it is defined as the duration from the time the user falls asleep to a given amount of sustained sleep. In some implementations, a given amount of sustained sleep may include, for example, at least 10 minutes of sleep within a second non-REM phase, a third non-REM phase, and / or a wake of 2 minutes or less, a first non-REM phase, and / or transitions between them within a REM phase. In other words, persistent sleep latency requires, for example, at least 8 minutes of sustained sleep within a second non-REM phase, a third non-REM phase, and / or within a REM phase. In other implementations, a predetermined amount of sustained sleep may include at least 10 minutes of sleep within the first non-REM phase, the second non-REM phase, the third non-REM phase, and / or within the REM phase after the initial sleep onset time. In such implementations, the predetermined amount of sustained sleep may exclude all minute awakenings (for example, a 10-second minute awakening will not be followed by a resumption of sleep for 10 minutes).

[0078] Nocturnal awakening (WASO) is associated with the total duration of wakefulness a user experiences from the time of initial sleep onset to the time of wakefulness. Therefore, nocturnal awakening includes short-term and minute awakenings during a sleep session, whether conscious or unconscious (e.g., minute awakenings MA1 and MA2 shown in Figure 4). In some implementations, nocturnal awakening (WASO) is defined as persistent nocturnal awakening (PWASO), which includes only total wakefulness durations of a predetermined length (e.g., more than 10 seconds, more than 30 seconds, more than 60 seconds, more than approximately 5 minutes, more than approximately 10 minutes, etc.).

[0079] Sleep efficiency (SE) is determined by the ratio of total time in bed (TIB) to total sleep time (TST). For example, if total time in bed is 8 hours and total sleep time is 7.5 hours, the sleep efficiency for that sleep session is 93.75%. Sleep efficiency represents the user's sleep hygiene. For example, if a user goes to bed and spends time on other activities (e.g., watching television) before falling asleep, sleep efficiency decreases (e.g., the user may be penalized). In some implementations, sleep efficiency (SE) can be calculated based on total time in bed (TIB) and the total time the user attempts to fall asleep. In such implementations, the total duration the user attempts to fall asleep is defined as the time from the time of sleep onset (GTS) to the time of wake-up as described herein. For example, if total sleep time is 8 hours (e.g., from 11 p.m. to 7 a.m.), the time of sleep onset is 10:45 p.m., and the time of wake-up is 7:15 a.m., the sleep efficiency parameter is calculated to be approximately 94% in such an implementation.

[0080] The fragmentation index is determined at least partially based on the number of awakenings during a sleep session. For example, if a user had two minor awakenings (e.g., minor awakenings MA1 and MA2 shown in Figure 4), the fragmentation index could be represented as 2. In some implementations, this fragmentation index is scaled within a predetermined range of integers (e.g., between 0 and 10).

[0081] A sleep block is associated with a transition between any sleep stage (e.g., the first non-REM stage, the second non-REM stage, the third non-REM stage, and / or REM) and the wakefulness stage. Sleep blocks can be calculated, for example, with a resolution of 30 seconds.

[0082] In some implementations, the system and method described herein are used for bedtime (t bed ), sleep onset time (t GTS ), time of first sleep (t sleep ), one or more first minute awakenings (e.g., MA1 and MA2), awakening time (t wake ), wake-up time (t riseThis may include generating or analyzing a sleep-time chart that includes sleep / wake signals in order to determine or identify, or any combination thereof, based at least partially on the sleep / wake signals of the sleep-time chart.

[0083] In other implementations, one or more of the sensors 130 are used to determine the time of going to bed (t bed ), sleep onset time (t GTS ), time of first sleep (t sleep ), one or more first minute awakenings (e.g., MA1 and MA2), awakening time (t wake ), wake-up time (t rise ), or any combination thereof, can be determined or identified, and by extension, a sleep session can be defined. For example, bedtime t bed This can be determined based on data generated by motion sensors, microphones, cameras, or any combination thereof. For example, the time of falling asleep can be determined based on data from motion sensors (e.g., data indicating no user movement), cameras (e.g., data indicating no user movement and / or the user turning off the lights), microphones (e.g., data indicating the user turning off the TV), mobile device 520 (e.g., data indicating the user is no longer using mobile device 520), pressure sensors and / or flow sensors (e.g., data indicating the user turning on the respiratory therapy device 530), or any combination thereof. As defined using Figure 3, data can be generated by one or more sensors during a sleep session, or a sleep progression diagram like Figure 4 can be generated to help inform the individual's treatment plan.

[0084] One or more further implementations and / or claims of the present disclosure can be formed by combining one or more elements, aspects, steps, or parts thereof from one or more of any of the following claims 1 to 85 with one or more elements, aspects, steps, or parts thereof from one or more of the other claims 1 to 85 or any combination thereof.

[0085] While this disclosure has been described with reference to one or more specific implementations, those skilled in the art will recognize that numerous modifications are possible without departing from the intent and scope of this disclosure. Each of these implementations and its clearest modifications is intended to fall within the intent and scope of this disclosure. Furthermore, it is intended that various forms of implementation of this disclosure may combine any number of features from any of the implementations described herein. The following are additional notes to this disclosure. (Additional note 1) Receiving data associated with an individual, Using a machine learning-based adoption prediction algorithm, process at least a portion of the received data to determine the likelihood that the individual will adopt the prescribed treatment plan. A method comprising (i) generating an individualized treatment adoption plan for the individual based at least in part on the prescribed treatment plan and (ii) a likelihood assessment that the individual will adopt the prescribed treatment plan. (Additional note 2) The method according to Appendix 1, wherein, upon determining that the machine learning-based adoption prediction algorithm has determined that the likelihood of the individual adopting the prescribed treatment plan satisfies a first threshold, the generated individualized treatment adoption plan for the individual includes a modified version of the prescribed treatment plan. (Additional note 3) The method according to Appendix 2, wherein the likelihood that the individual will adopt the prescribed treatment plan is less than 80%, and the likelihood satisfies the first threshold. (Additional note 4) The method according to Appendix 2 or Appendix 3, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using the respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment using the respiratory device within a second pressure range different from the first pressure range. (Additional note 5) The method according to Appendix 2 or Appendix 3, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a mandibular repositioning device. (Additional note 6) The method according to Appendix 2 or Appendix 3, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by undergoing surgery. (Additional note 7) The method according to Appendix 6, wherein the surgery is bariatric surgery, oral surgery, liposuction, or any combination thereof. (Additional note 8) The method according to Appendix 2 or Appendix 3, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by (i) adopting a diet, (ii) adopting an exercise program, or (iii) or both (i) and (ii). (Additional note 9) The method according to Appendix 2 or Appendix 3, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using an adjustable bed-related device. (Additional note 10) The method according to Appendix 9, wherein the adjustable bed-related device includes an adjustable pillow, an adjustable mattress, an adjustable bed frame, adjustable bedding, or any combination thereof. (Additional note 11) The prescribed treatment plan includes a first recommendation that the individual begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a first recommendation that the individual begin treatment using a nasal strip. The method described in Appendix 2 or Appendix 3, including a second recommendation to initiate treatment. (Additional note 12) The method according to Appendix 2 or Appendix 3, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier while sleeping, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof. (Additional note 13) The method according to any one of appendices 2 to 12, wherein, upon determining that the machine learning-based adoption prediction algorithm satisfies a second threshold for the likelihood of the individual adopting the prescribed treatment plan, the generated individualized treatment adoption plan for the individual becomes the prescribed treatment plan. (Additional note 14) The method according to Appendix 13, wherein the likelihood that the individual will adopt the prescribed treatment plan is 80% or higher, and the likelihood satisfies the second threshold. (Additional note 15) The method according to any one of Appendix 1 to 14, wherein the prescribed treatment plan is provided by a physician associated with the individual. (Additional note 16) The method according to any one of Appendix 1 to 15, wherein the data includes personal data associated with multiple individuals, adherence data associated with multiple individuals similar to the individual, summaries of at least a portion of past events that led the individual to a sleep-related diagnosis, indications of the type of person who provided the individual with a sleep-related diagnosis, a determination of whether the individual experiences dyspnea during sleep, the individual's kinship information, web searches performed by the individual, a determination of whether the individual is likely to exhibit binge eating or drinking behavior, a determination of whether the individual is likely to change behavior, summaries of at least a portion of past explanations of clinical behaviors the individual has changed, one or more daily health assessments including the occurrence and frequency of headaches and migraines experienced by the individual, the individual's dependent information, the individual's enrollment in a mobile-based or web-based health management application, social media information associated with the individual, support group information associated with the use of a respiratory device, a determination of whether the individual has a tendency to adopt technology early, treatment plans prescribed to the individual, information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof. (Additional note 17) The method according to any one of the appendices 1 to 16, wherein the data includes training data associated with multiple individuals. (Additional note 18) The method of Appendix 17, further comprising training the machine learning-based adoption prediction algorithm with the training data so that the machine learning-based adoption prediction algorithm is configured to (i) receive at least a portion of the received data as input information, and (ii) determine the likelihood that the individual will adopt the prescribed treatment plan as output information. (Additional note 19) Receiving feedback associated with the individual's level of compliance with the individualized treatment plan, Based at least in part on the generated individualized treatment plans and the feedback. The method according to any one of the appendices 1 to 18, further comprising generating a second individualized treatment adoption plan for the aforementioned individual. (Additional note 20) The method according to Appendix 19, wherein the feedback includes the individual's answers to one or more questions, sensor data, or a combination thereof. (Additional note 21) The method according to any one of Appendix 1 to 20, further comprising providing notifications to terminal devices including a personal computer, a mobile device, a respiratory therapy device, or any combination thereof, based on the generated individualized treatment adoption plan for the individual. (Additional note 22) The method described in Appendix 21, wherein the notification includes commands for adjusting the settings of the respiratory therapy device based at least in part on the individualized treatment plan. (Additional note 23) The method according to any one of the appendices 1 to 22, wherein the data is communicably connected to a network and stored in a data repository including multiple storage devices, including a social media database, an electronic medical record database, a wearable technology database, or any combination thereof. (Additional note 24) The method according to any one of the appendices 1 to 23, further comprising receiving user input information from the said individual, and the use of the machine learning type adoption prediction algorithm comprising processing the said user input information. (Additional note 25) The method according to Appendix 24, wherein the user input information includes one or more videos depicting at least a part of the individual, one or more images depicting at least a part of the individual, or a combination thereof. (Additional note 26) The method according to Appendix 24 or 25, wherein the processing of the user input information includes analyzing the user input information to determine the individual's risk of sleep disorder. (Additional note 27) A control system including one or more processors, It comprises a memory that stores machine-readable instructions, A system in which the method described in any one of appendices 1 to 26 is performed when the control system is connected to the memory and the machine-executable instructions in the memory are executed by at least one of the one or more processors of the control system. (Additional note 28) A system for formulating a treatment adoption plan, comprising a control system configured to implement the method described in any one of the appendices 1 to 26. (Additional note 29) A computer program product that, when executed by a computer, includes instructions causing the computer to perform any of the procedures described in any one of the appendices 1 to 26. (Additional note 30) The computer program product described in Appendix 29, wherein the computer program product is a non-temporary computer-readable medium. (Additional note 31) A system that predicts whether an individual will adopt a prescribed treatment plan, A data repository that is connected to a network in a communicative manner and includes multiple storage devices that store data, A memory that stores machine-readable instructions and a machine learning-type prediction algorithm, Executing the aforementioned machine-readable instruction, Receiving at least a portion of the data stored in the data repository, and at least a portion of the data associated with the individual, Using the machine learning-based adoption prediction algorithm, process at least a portion of the received data and determine the likelihood that the individual will adopt the prescribed treatment plan. (i) the prescribed treatment plan and (ii) the likelihood assessment that the individual will adopt the prescribed treatment plan, at least in part, are used to generate an individualized treatment adoption plan for the individual. A system comprising a control system including one or more processors configured in such a manner. (Additional note 32) The system according to Appendix 31, wherein, upon the determination by the machine learning-based adoption prediction algorithm that the likelihood of the individual adopting the prescribed treatment plan satisfies a first threshold, the generated individualized treatment adoption plan for the individual includes a modified version of the prescribed treatment plan. (Additional note 33) The system according to appendix 32, wherein the likelihood that the individual will adopt the prescribed treatment plan is less than 80%, and the likelihood satisfies the first threshold. (Additional note 34) The System Method described in Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using the respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment using the respiratory device within a second pressure range different from the first pressure range. (Additional note 35) The system according to Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a mandibular repositioning device. (Additional note 36) The system according to Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by undergoing surgery. (Additional note 37) The system as described in Appendix 36, wherein the surgery is bariatric surgery, oral surgery, liposuction, or any combination thereof. (Additional note 38) The system according to Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by (i) adopting a diet, (ii) adopting an exercise program, or (iii) or both (i) and (ii). (Additional note 39) The system according to Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using an adjustable bed-related device. (Additional note 40) The system according to Appendix 39, wherein the adjustable bed-related device includes an adjustable pillow, an adjustable mattress, an adjustable bed frame, adjustable bedding, or any combination thereof. (Additional note 41) The system according to Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a nasal strip. (Additional note 42) The system described in Appendix 32 or Appendix 33, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier during sleep, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof. (Additional note 43) The system according to any one of appendices 32 to 42, wherein, upon the determination by the machine learning-based adoption prediction algorithm that the likelihood of the individual adopting the prescribed treatment plan satisfies a second threshold, the generated individualized treatment adoption plan for the individual becomes the prescribed treatment plan. (Additional note 44) The system according to appendix 43, wherein the likelihood that the individual will adopt the prescribed treatment plan is 80% or higher, and the likelihood satisfies the second threshold. (Additional note 45) The system described in any one of the appendices 31 to 44, wherein the prescribed treatment plan is provided by a physician associated with the individual. (Additional note 46) The stored data includes personal data associated with multiple individuals, adherence data associated with multiple individuals similar to the individual, summaries of at least a portion of past events that led the individual to a sleep-related diagnosis, indications of the type of person who provided the individual with a sleep-related diagnosis, a determination of whether the individual experiences dyspnea during sleep, kinship information of the individual, web searches performed by the individual, a determination of whether the individual is likely to exhibit binge eating behavior, a determination of whether the individual is likely to change their behavior, summaries of at least a portion of past explanations for the individual's changed clinical behavior, and the individual's A system according to any one of the appendices 31 to 45, including one or more daily health assessments including the occurrence and frequency of headaches and migraines experienced, dependent information of the individual, the individual's enrollment in a mobile-based or web-based health management application, social media information associated with the individual, support group information associated with the use of a respiratory device, a determination of whether the individual has a tendency to adopt technology early, a treatment plan prescribed to the individual, information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof. (Additional note 47) The system according to any one of the appendices 31 to 46, wherein the stored data in the data repository includes training data associated with multiple individuals. (Additional note 48) The system according to Appendix 47, wherein the control system is further configured to execute machine-readable instructions to train the machine learning adoption prediction algorithm with the training data, such that the machine learning adoption prediction algorithm is configured to (i) receive at least a portion of the data as input information, and (ii) determine the likelihood that the individual will adopt the prescribed treatment plan as output information. (Additional note 49) The system according to any one of the appendices 31 to 48, further configured to execute the machine-readable instructions to (i) receive feedback associated with the individual's level of compliance with the individualized treatment plan, and (ii) generate a second individualized treatment plan for the individual, at least in part, based on the generated individualized treatment plan and the feedback. (Additional note 50) The system described in Appendix 49, wherein the feedback includes the individual's answers to one or more questions, sensor data, or a combination thereof. (Additional note 51) The system according to any one of the appendices 31 to 50, further comprising a terminal device associated with the individual and configured to receive notifications from the control system based on the generated individualized treatment adoption plan for the individual, wherein the terminal device includes a personal computer, a mobile device, a respiratory therapy device, or any combination thereof. (Additional note 52) The system according to Appendix 51, wherein the notification received from the control system includes a command for adjusting the settings of the respiratory therapy device based at least in part on the individualized treatment plan. (Additional note 53) The system described in any one of the appendices 31 to 52, wherein the plurality of storage devices include a social media database, an electronic medical record database, a wearable technology database, or any combination thereof. (Additional note 54) The system according to any one of the appendices 31 to 53, wherein the control system is further configured to execute machine-readable instructions and receive user input information from the individual, and the use of the machine learning type adoption prediction algorithm includes processing the user input information. (Additional note 55) The system according to Appendix 54, wherein the user input information includes one or more videos depicting at least a part of the individual, one or more images depicting at least a part of the individual, or a combination thereof. (Additional note 56) The system according to appendix 54 or 55, wherein the processing of the user input information includes analyzing the user input information to determine the individual's risk of sleep disorder. (Additional note 57) A method for predicting whether an individual will adopt a prescribed treatment plan, Receiving at least a portion of the data stored in a data repository, wherein at least a portion of the data is associated with the individual, the data repository is communicably connected to a network, and includes a plurality of storage devices that store the data. Using a machine learning-based adoption prediction algorithm that processes at least a portion of the received data, the likelihood that the individual will adopt the prescribed treatment plan is determined. A method comprising (i) generating an individualized treatment adoption plan for the individual based at least in part on the prescribed treatment plan and (ii) the likelihood determination that the individual will adopt the prescribed treatment plan. (Additional note 58) The method according to Appendix 57, wherein the likelihood determination satisfies a first threshold, and the generated individualized treatment adoption plan for the individual includes a modified version of the prescribed treatment plan. (Additional note 59) The method according to Appendix 58, wherein the likelihood that the individual will adopt the prescribed treatment plan is less than 80%, and the likelihood satisfies the first threshold. (Additional note 60) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using the respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment using the respiratory device within a second pressure range different from the first pressure range. (Additional note 61) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a mandibular repositioning device. (Additional note 62) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by undergoing surgery. (Additional note 63) The method according to Appendix 62, wherein the surgery is bariatric surgery, oral surgery, liposuction, or any combination thereof. (Additional note 64) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device within a first pressure range, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by (i) adopting a diet, (ii) adopting an exercise program, or (iii) or both (i) and (ii). (Additional note 65) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using an adjustable bed-related device. (Additional note 66) The method according to Appendix 65, wherein the adjustable bed-related device includes an adjustable pillow, an adjustable mattress, an adjustable bed frame, adjustable bedding, or any combination thereof. (Additional note 67) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a nasal strip. (Additional note 68) The method according to Appendix 58 or Appendix 59, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier while sleeping, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof. (Additional note 69) The method according to any one of the appendices 57 to 68, wherein the likelihood determination satisfies a second threshold, and the generated individualized treatment adoption plan for the individual is the prescribed treatment plan. (Additional note 70) The method according to appendix 69, wherein the likelihood that the individual will adopt the prescribed treatment plan is 80% or higher, and the likelihood satisfies the second threshold. (Additional note 71) The method according to any one of the appendices 57 to 70, wherein the prescribed treatment plan is provided by a physician associated with the individual. (Additional note 72) The method according to any one of Appendix 57 to 71, wherein the data includes personal data associated with multiple individuals, adherence data associated with multiple individuals similar to the individual, summaries of at least a portion of past events that led the individual to a sleep-related diagnosis, indications of the type of person who provided the individual with a sleep-related diagnosis, a determination of whether the individual experiences dyspnea during sleep, the individual's kinship information, web searches performed by the individual, a determination of whether the individual is likely to exhibit binge eating or drinking behavior, a determination of whether the individual is likely to change behavior, summaries of at least a portion of past explanations of clinical behaviors the individual has changed, one or more daily health assessments including the occurrence and frequency of headaches and migraines experienced by the individual, the individual's dependent information, the individual's enrollment in a mobile-based or web-based health management application, social media information associated with the individual, support group information associated with the use of a respiratory device, a determination of whether the individual has a tendency to adopt technology early, treatment plans prescribed to the individual, information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof. (Additional note 73) The method according to any one of the appendices 57 to 72, wherein the data stored in the data repository includes training data associated with multiple individuals. (Additional note 74) The method according to Appendix 73, further comprising training the machine learning adoption prediction algorithm with the training data so that the machine learning adoption prediction algorithm is configured to (i) receive at least a portion of the data as input information, and (ii) determine the likelihood that the individual will adopt the prescribed treatment plan as output information. (Additional note 75) The method according to any one of the appendices 57 to 74, further comprising receiving feedback associated with the individual's level of compliance with the individualized treatment plan, and generating a second individualized treatment plan for the individual based at least in part on the generated individualized treatment plan and the feedback. (Additional note 76) The method according to Appendix 75, wherein the feedback includes the individual's answers to one or more questions, sensor data, or a combination thereof. (Additional note 77) The method according to any one of the appendices 57 to 76, further comprising sending a notification to the said individualized treatment plan associated with the said individualized treatment plan. (Additional note 78) The method described in Appendix 77, wherein the notification includes a command for adjusting the settings of a respiratory therapy device associated with the individual, and the adjustment is at least in part based on the individualized treatment adoption plan for the individual. (Additional note 79) The aforementioned multiple storage devices include a social media database, an electronic medical record database, a wearable technology database, or any combination thereof. The method described in any one of the appendices 57 to 78. (Additional note 80) The method according to any one of the appendices 57 to 79, further comprising receiving user input information from the said individual, and determining the likelihood, comprising using the machine learning type adoption prediction algorithm which includes processing the said user input information. (Additional note 81) The method according to Appendix 80, wherein the user input information includes one or more videos depicting at least a part of the individual, one or more images depicting at least a part of the individual, or a combination thereof. (Additional note 82) The method according to Appendix 81, wherein the processing of the user input information includes analyzing the user input information to determine the individual's risk of sleep disorder. (Additional note 83) A data repository including multiple storage devices for storing data, A memory that stores machine-readable instructions and a machine learning-type prediction algorithm, Executing the aforementioned machine-readable instruction, The data includes historical data associated with multiple adopters of one or more treatment plans, and current data associated with individuals. The machine learning-based adoption prediction algorithm is trained on the historical data so that it is configured to (i) receive at least a portion of the current data and a prescribed treatment plan for the individual as input information, and (ii) determine the likelihood that the individual will adopt the prescribed treatment plan as output information. A system comprising a control system including one or more processors configured in such a manner. (Additional note 84) The system as described in Appendix 83, wherein the prescribed treatment plan includes a first recommendation that the individual initiate treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation that the individual initiate treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier during sleep, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof. (Additional note 85) The stored data includes personal data associated with the multiple adopters of the one or more treatment plans, adherence data associated with the multiple adopters of the one or more treatment plans, summaries of at least a portion of past events that led the individual to a sleep-related diagnosis, indications of the type of person who provided the individual with a sleep-related diagnosis, a determination of whether the individual experiences dyspnea during sleep, kinship information of the individual, web searches performed by the individual, a determination of whether the individual is likely to exhibit binge eating behavior, a determination of whether the individual is likely to change their behavior, and at least a past explanation of the clinical behavior the individual has changed. The system described in Appendix 83 or Appendix 84, including a partial summary, one or more daily health assessments including the occurrence and frequency of headaches and migraines experienced by the individual, information on the individual's dependents, the individual's enrollment in a mobile-based or web-based health management application, social media information associated with the individual, support group information associated with the use of a respiratory device, a determination of whether the individual has a tendency to adopt technology early, a treatment plan prescribed to the individual, information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof.

Claims

1. Receiving data associated with an individual, including a determination of whether the individual experiences difficulty breathing during sleep, Using a machine learning-based adoption prediction algorithm, process at least a portion of the received data to determine the likelihood that the individual will adopt the prescribed treatment plan. (i) generating an individualized treatment adoption plan for the individual, based at least in part on the prescribed treatment plan and (ii) a likelihood assessment that the individual will adopt the prescribed treatment plan. The machine learning-based adoption prediction algorithm determines that the likelihood of the individual adopting the prescribed treatment plan is below a first threshold, and the generated individualized treatment adoption plan for the individual includes a modified version of the prescribed treatment plan. A computer-based method wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a mandibular repositioning device.

2. The method according to claim 1, wherein the likelihood that the individual will adopt the prescribed treatment plan is less than 80%, and the likelihood falls below the first threshold.

3. The method according to claim 1 or 2, wherein the first recommendation comprises initiating treatment using the respiratory device within a first pressure range, and the second recommendation further comprises initiating treatment using the respiratory device within a second pressure range different from the first pressure range.

4. The method according to claim 1 or 2, wherein the first recommendation comprises initiating treatment using the respiratory device within a first pressure range, and the second recommendation further comprises initiating treatment by undergoing surgery.

5. The first recommendation is to initiate treatment using the respiratory device within a first pressure range. The method according to claim 1 or 2, further comprising, wherein the second recommendation further comprises (i) adopting a diet, (ii) adopting an exercise plan, or initiating treatment by (iii) or both (i) and (ii).

6. The method according to claim 1 or 2, wherein the second recommendation further includes initiating treatment using an adjustable bed-related device, the adjustable bed-related device including an adjustable pillow, an adjustable mattress, an adjustable bed frame, adjustable bedding, or any combination thereof.

7. The method according to claim 1 or 2, further comprising the second recommendation to initiate treatment using a nasal strip.

8. The method according to claim 1 or 2, wherein the second recommendation further includes the individual initiating treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier while sleeping, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof.

9. The method according to any one of claims 1 to 8, wherein the machine learning-based adoption prediction algorithm determines that the likelihood of the individual adopting the prescribed treatment plan is greater than or equal to a second threshold, and the generated individualized treatment adoption plan for the individual becomes the prescribed treatment plan.

10. The method according to any one of claims 1 to 9, wherein the data further includes personal data associated with multiple individuals, adherence data associated with multiple individuals similar to the individual, summaries of at least a portion of past events that led the individual to a sleep-related diagnosis, indications of the type of person who provided the individual with a sleep-related diagnosis, kinship information of the individual, web searches performed by the individual, a determination of whether the individual is likely to exhibit binge eating behavior, a determination of whether the individual is likely to change behavior, summaries of at least a portion of past explanations of clinical behaviors the individual has changed, one or more daily health assessments including the occurrence and frequency of headaches and migraines experienced by the individual, dependent information of the individual, the individual's enrollment status in a mobile-based or web-based health management application, social media information associated with the individual, support group information associated with the use of a respiratory device, a determination of whether the individual has a tendency to adopt technology early, a treatment plan prescribed to the individual, information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof.

11. The aforementioned data includes training data associated with multiple individuals, The method according to any one of claims 1 to 10, further comprising training the machine learning adoption prediction algorithm with the training data so that the machine learning adoption prediction algorithm is configured to (i) receive at least a portion of the received data as input information, and (ii) determine the likelihood that the individual will adopt the prescribed treatment plan as output information.

12. Receiving feedback related to the individual's level of compliance with the aforementioned individualized treatment plan, The method according to any one of claims 1 to 11, further comprising generating a second individualized treatment plan for the individual based at least in part on the generated individualized treatment plan and the feedback.

13. The further includes providing notifications to terminal devices, including personal computers, mobile devices, respiratory therapy devices, or any combination thereof, based on the generated individualized treatment adoption plan for the aforementioned individual. The method according to any one of claims 1 to 12, wherein the notification includes a command for adjusting the settings of the respiratory therapy device based at least in part on the individualized treatment plan.

14. The method according to any one of claims 1 to 13, wherein the data is stored in a data repository which includes a plurality of storage devices that are communicably connected to a network and include a social media database, an electronic medical record database, a wearable technology database, or any combination thereof.

15. The further includes receiving user input information from the said individual, and the use of the machine learning type adoption prediction algorithm includes processing the said user input information. The method according to any one of claims 1 to 14, wherein the user input information includes one or more videos depicting at least a part of the individual, one or more images depicting at least a part of the individual, or a combination thereof.

16. The method according to claim 15, wherein the processing of the user input information includes analyzing the user input information to determine the risk of sleep disorders for the individual.

17. A computer-based method for predicting whether an individual will adopt a prescribed treatment plan, Receiving at least a portion of data stored in a data repository, which includes a determination of whether the individual experiences difficulty breathing during sleep, wherein at least a portion of the data is associated with the individual, the data repository is communicably connected to a network, and includes a plurality of storage devices that store the data. Using a machine learning-based adoption prediction algorithm that processes at least a portion of the received data, the likelihood that the individual will adopt the prescribed treatment plan is determined. (i) generating an individualized treatment adoption plan for the individual, based at least in part on the prescribed treatment plan and (ii) a likelihood assessment that the individual will adopt the prescribed treatment plan. The generated individualized treatment adoption plan, resulting from the likelihood falling below a first threshold, includes a modified version of the prescribed treatment plan. A method wherein the prescribed treatment plan includes a first recommendation for the individual to begin treatment using a respiratory device, and the modified version of the prescribed treatment plan includes a second recommendation for the individual to begin treatment using a mandibular repositioning device.

18. The method according to claim 17, wherein the first recommendation comprises initiating treatment using the respiratory device in a first pressure range, and the second recommendation further comprises initiating treatment using the respiratory device in a second pressure range different from the first pressure range.

19. The first recommendation includes initiating treatment using the respiratory device within a first pressure range, and the second recommendation further includes initiating treatment by undergoing surgery. The method according to claim 17.

20. The method according to claim 17, wherein the first recommendation comprises initiating treatment using the respiratory device in a first pressure range, and the second recommendation further comprises initiating treatment by (i) adopting a diet, (ii) adopting an exercise program, or (iii) or both (i) and (ii).

21. The method according to claim 17, further comprising the second recommendation to initiate treatment using an adjustable bed-related device.

22. The method according to claim 17, further comprising the second recommendation to initiate treatment using a nasal strip.

23. The method according to claim 17, wherein the second recommendation further includes the individual initiating treatment by using a mandibular repositioning device, undergoing surgery, losing weight, adopting a diet, adopting exercise therapy, avoiding or reducing alcohol consumption, avoiding or reducing smoking, quitting smoking, avoiding or reducing caffeine intake, using a humidifier while sleeping, using a tongue stabilization device, avoiding or reducing the use of sleeping pills, performing vocal exercises, performing one or more respiratory exercises, using an adjustable bed-related device, or any combination thereof.

24. The method according to any one of claims 17 to 23, wherein the individualized treatment adoption plan generated in response to the likelihood being greater than or equal to a second threshold is the prescribed treatment plan.

25. The method according to any one of claims 17 to 24, wherein the data further includes personal data associated with multiple individuals, adherence data associated with multiple individuals similar to the individual, summaries of at least a portion of past events that led the individual to a sleep-related diagnosis, indications of the type of person who provided the individual with a sleep-related diagnosis, kinship information of the individual, web searches performed by the individual, a determination of whether the individual is likely to exhibit binge eating behavior, a determination of whether the individual is likely to change behavior, summaries of at least a portion of past explanations of clinical behaviors the individual has changed, one or more daily health assessments including the occurrence and frequency of headaches and migraines experienced by the individual, dependent information of the individual, the individual's enrollment status in a mobile-based or web-based health management application, social media information associated with the individual, support group information associated with the use of a respiratory device, a determination of whether the individual has a tendency to adopt technology early, a treatment plan prescribed to the individual, information associated with whether the individual is a drug user, information associated with whether the individual drinks alcohol, or any combination thereof.

26. The method according to any one of claims 17 to 25, wherein the data stored in the data repository includes training data associated with a plurality of individuals.

27. The method according to claim 26, further comprising training the machine learning adoption prediction algorithm with the training data such that the machine learning adoption prediction algorithm is configured to (i) receive at least a portion of the data as input information, and (ii) determine the likelihood that the individual will adopt the prescribed treatment plan as output information.

28. Feedback related to the individual's level of compliance with the individualized treatment plan. The method according to any one of claims 17 to 27, further comprising receiving and generating a second individualized treatment adoption plan for the individual, at least in part, based on the generated individualized treatment adoption plan and the feedback.

29. A control system including one or more processors, It comprises a memory that stores machine-readable instructions, A system in which the method according to any one of claims 1 to 28 is carried out, wherein the control system is connected to the memory, and the machine-readable instructions in the memory are executed by at least one of the one or more processors of the control system.

30. A computer program, when executed by a computer, includes instructions causing the computer to perform the method according to any one of claims 1 to 28.

Images