Systems and methods for conducting digital health consultations and for remote programming of medical devices

Abstract

A system and method for conducting a virtual clinic (VC) session between a patient and a clinician using a VC cloud telehealth system to program an implantable pulse generator (IPG) of a patient to provide a neurostimulation therapy to the patient. One or more VC session models or criteria can be defined that represent clinician and patient interactions during a VC session and a first communication connection can be established between a patient electronic device (PED) and the IPG of the patient. A second communication connection can also be established between a patient electronic device (PED) and the VC cloud telehealth system and a third communication connection can be established between a clinician electronic device (CED) and the VC cloud computing system to connect the patient and clinician for the VC session. Based on input from the clinician electrical stimulation for the neurostimulation therapy can be applied to the patient.

Description

SYSTEMS AND METHODS FOR CONDUCTING DIGITAL HEALTH CONSULTATIONS AND FOR REMOTE PROGRAMMING OF MEDICAL DEVICES

[0001] This application claims the benefit of U. S. Provisional Application No.63 / 728,966, filed 6-December-2024, titled “SYSTEMS AND METHODS FOR CONDUCTING DIGITAL HEALTH CONSULTATIONS AND FOR REMOTE PROGRAMMING OF MEDICAL DEVICE”, U. S. Provisional Application No.63 / 728,979, filed 6-December-2024, titled “SYSTEMS AND METHODS FOR CONDUCTING DIGITAL HEALTH CONSULTATIONS AND FOR REMOTE PROGRAMMING OF MEDICAL DEVICE”, and U. S. Provisional Application No.63 / 728,994, filed 6-December-2024, titled “SYSTEMS AND METHODS FOR CONDUCTING DIGITAL HEALTH CONSULTATIONS AND FOR REMOTE PROGRAMMING OF MEDICAL DEVICE” the subject matter of each of which is hereby incorporated by reference in their entireties.BACKGROUND

[0002] Embodiments herein generally relate to systems for telehealth consultations and remote programming of medical devices based on a virtual clinic session.

[0003] Telehealth is a general term used to describe the use of various digital technologies (smartwatches, tablets, and computers) to facilitate longdistance clinical healthcare services, public health and patient or professional15968WOO1 (013-0632PCT1) 1 PATENThealth-related education. Telemedicine is a specific area of telehealth that employs digital technologies to directly connect patients with their healthcare providers in a virtual setting. Telemedicine can be used to replace or supplement traditional in-clinic services to reduce the burden on patients to obtain necessary health care. Often, telemedicine offers patients access to clinicians who specialize in medical services that are not available locally (e.g., for patients in underserved geographical locations).

[0004] Abbott (Plano, TX) provides NEUROSPHERE™ Virtual Clinic telehealth services to facilitate consultations between clinicians and neuromodulation patients. Neuromodulation patients have implanted medical devices that provide therapy for chronic pain or movement disorders. In Abbott’s telehealth system neuromodulation patients receive health care consultations with clinicians in an in-app video chat service. Further, the NEUROSPHERE™ Virtual Clinic systems use cloud and Bluetooth technology to provide updates to the programming of the implanted medical devices of patients to customize therapy for patients.

[0005] Abbott’s NEUROSPHERE™ Virtual Clinic telehealth services have provided significant benefits to patients over a relatively large number of virtual clinic sessions. However, provision of health care in virtual settings is often subject to constraints that clinicians experience for in-clinic services. For example, clinicians are subject to substantial time constraints when providing care to15968WOO1 (013-0632PCT1) 2 PATENTneurostimulation patients whether for in-clinic services or for virtual appointments. In one study, clinicians employing Abbott’s NEUROSPHERE™ Virtual Clinic telehealth services typically experienced a mean duration of remote programming sessions of 15 mins and 04 secs (SD 08 mins and 53 secs), and the median duration was 12 mins and 55 secs.SUMMARY

[0006] In accordance with embodiments herein, a method of conducting a virtual clinic (VC) session between a patient and a clinician using a VC cloud telehealth system to program an implantable pulse generator (IPG) of a patient to provide a neurostimulation therapy to the patient is provided. The method can include defining one or more VC session models or criteria that represent clinician and patient interactions during a VC session, establishing a first communication connection between a patient electronic device (PED) and the IPG of the patient, and establishing a second communication connection between a patient electronic device (PED) and the VC cloud telehealth system. The method can also include establishing a third communication connection between a clinician electronic device (CED) and the VC cloud computing system to connect the patient and clinician for the VC session, receiving input from the clinician for modification of one or more stimulation parameters during the VC session, and communicating one or more signals to the PED to modify the one or more stimulation parameters during the VC session. The method may additionally include applying electrical15968WOO1 (013-0632PCT1) 3 PATENTstimulation for the neurostimulation therapy to the patient according to the modified one or more stimulation parameters during the VC session, repetitively applying VC session data to the VC session models or criteria to calculate a metric related to a probability of successfully completing the VC session while the VC session is ongoing, and providing an indication to the clinician using the CED for display to the clinician a likelihood of successfully completing the VC session. The indication can be updated for display during the VC session as repetitive calculations of the metric related to a probability of successfully completing the VC session are performed.

[0007] Optionally, the method can also include estimating, by the VC cloud telehealth system, a VC session time with sufficient time likely for a successful conclusion of the VC session for the patient. In one aspect, the method may also include conducting, by the VC cloud telehealth system, a pre-VC session interview using a chatbot module of the VC cloud telehealth system, wherein the estimating comprises processing patient responses during the pre-VC session interview to estimate the VC session time. In another aspect, the method can additionally include receiving clinician input via the CED to add additional time to the VC session time, calculating a metric related to a probability of successfully completing the VC session according to the additional time the one or more VC session models or criteria by the VC cloud telehealth system, and providing an indication to the clinician using the CED for display to the clinician a likelihood of successfully completing the VC session with the additional time. In another15968WOO1 (013-0632PCT1) 4 PATENTexample, the one or more VC session models or criteria can have at least one neural network model for processing multiple VC session parameters.

[0008] Optionally, the method can also include selecting between one or more VC session models or criteria for the VC session by identifying a patient condition to be addressed during the VC session. In one aspect the method can additionally include selecting between one or more VC session models or criteria for the VC session according to patient demographic data. In one example, one or more VC session models or criteria for the VC session according to patient demographic data can be defined for respective clinicians for calculating the metric on a clinician specific basis. In another example, the method can also include monitoring a total amount of VC session time and the total amount of VC session time includes an amount of time during the VC session spent programming the patient's implantable pulse generator. In yet another example, the total session time and the amount of time spent programming the patient's implantable pulse generator are provided to the one or more VC session models or criteria.

[0009] In accordance with embodiments herein, a virtual clinic (VC) cloud telehealth system is provided. The VC cloud telehealth system can be configured to conduct a VC session between a patient and a clinician to program an implantable pulse generator (IPG) of the patient. The VC cloud telehealth system can include the IPG, a patient electronic device (PED) including one or more processors. When executing program instructions, the one or more processors15968WOO1 (013-0632PCT1) 5 PATENTcan be configured to establish a first communication connection with the IPG of the patient. The VC cloud telehealth system can additionally include one or more servers having one or more processors. When executing program instructions, the one or more processors of the servers can be configured to define one or more VC session models or criteria that represent clinician and patient interactions during a VC session, establish a second communication connection with the PED, establish a third communication connection with a clinician electronic device (CED) to provide a communication pathway between the patient and a clinician for the VC session, receive input from the clinician for modification of one or more stimulation parameters during the VC session, repetitively apply VC session data to the VC session models or criteria to calculate a metric related to a probability of successfully completing the VC session while the VC session is ongoing, and communicate one or more signals to the PED to modify the one or more stimulation parameters during the VC session. The CED may have an interface and include one or more processors. When executing program instructions, the one or more processors of the CED can be configured to obtain from the one or more servers the probability of successfully completing the VC session and continuously and repeatably update a message on the interface that indicates the probability of successfully completing the VC session as repetitive calculations of the metric related to a probability of successfully completing the VC session are performed. The IPG can include one or more processors, that when executing program instructions, can be configured to obtain instructions from the PED and apply15968WOO1 (013-0632PCT1) 6 PATENTelectrical stimulation for the neurostimulation therapy to the patient according to the one or more stimulation parameters modified during the VC session.

[0010] Optionally, the one or more processors of the one or more servers can be further configured to estimate a VC session time with sufficient time likely for a successful conclusion of the VC session for the patient. In one aspect, the one or more processors of the PED can be further configured to conduct a pre-VC session interview using a chatbot module, wherein to estimate the VC session time comprises processing patient responses during the pre-VC session interview to estimate the VC session time. In another aspect, the one or more processors of the one or more servers may be further configured to receive clinician input via the CED to add additional time to the VC session time, calculate a metric related to the probability of successfully completing the VC session according to the additional time, and communicate an indication of the probability of successfully completing the VC session that includes the additional time to the CED for display by the CED to the clinician. In one example, the one or more VC session models or criteria can have at least one neural network model for processing multiple VC session parameters.

[0011] Optionally, the one or more processors of the one or more servers can be further configured to select between one or more VC session models or criteria for the VC session by identifying a patient condition to be addressed during the VC session. In one aspect, the one or more processors of the one or more15968WOO1 (013-0632PCT1) 7 PATENTservers can be further configured to select between the one or more VC session models or criteria for the VC session according to patient demographic data. In another aspect, one or more VC session models or criteria for the VC session according to patient demographic data can be defined for respective clinicians for calculating the metric on a clinician specific basis. In one example, the one or more processors of the one or more servers may be further configured to monitor a total amount of VC session time and the total amount of VC session time can include an amount of time during the VC session spent programming the patient's implantable pulse generator. In another example, the one or more processors of the one or more servers can provide the total session time and the amount of time spent programming the patient's implantable pulse generator to the one or more VC session models or criteria.

[0012] In accordance with embodiments herein, a method of conducting a virtual clinic (VC) session between a patient and a clinician to provide medical services using a VC cloud telehealth system is provided. The method can include defining one or more set of questions in the VC cloud telehealth system to be delivered by a chatbot module of the VC cloud telehealth system and defining patient models in the VC cloud telehealth system. Each patient model can correspond to a patient condition or a medical response for the patient and each patient model can include multiple entries that define relative relevance of each respective entry to the corresponding patient condition or medical response. The method can also include defining mapping definitions in the VC cloud telehealth15968WOO1 (013-0632PCT1) 8 PATENTsystem between questions of the one or more sets of pre-VC session interview questions to respective entries in the patient models and establishing a first communication connection between a patient electronic device (PED) and the VC cloud telehealth system. The method can additionally include conducting a pre-VC session interview of the patient via the PED using at least one set of pre-VC session interview questions defined in the VC cloud telehealth system by the chatbot module of the VC cloud telehealth system, and upon completion of the pre-VC session interview of the patient, calculating, by the VC cloud telehealth system, relevance metrics for respective questions using processed patient responses, the patient models, and the mapping definitions that reflect relative relevance of the respective questions to be asked by a clinician in determining whether a respective patient condition or medical response is applicable for the patient. The method may also include establishing a second communication connection between a clinician electronic device (CED) and the VC cloud computing system to connect the patient and clinician for the VC session, identifying one or more questions to the CED for display to the clinician according to the calculated relevance metrics, and displaying, on an interface, the one or more questions identified.

[0013] Optionally, the providing identification can provide one or more questions for display to the clinician sorted in an order related to respective relevance metrics for the one or more questions. In one aspect the method can also include generating a summary of the pre-VC session interview using the15968WOO1 (013-0632PCT1) 9 PATENTchatbot module and displaying, on the interface, the summary to the clinician using the CED. In another aspect, the patient models can include entries related to physiological states of a patient. The method can also include obtaining sensor data from a wearable patient device of the patient to evaluate entries related to physiological states of the patient. In one example, the one or more patient models can each comprise an occurrence metric that is reflective of an occurrence of the patient condition or the medical response.

[0014] Optionally, the method may include calculating, by the VC cloud telehealth system, relevance metrics comprises applying occurrence metrics to weight individual question relevance calculations. In one aspect, the VC cloud telehealth system can include a library of pre-defined patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions. In another aspect, the VC cloud telehealth system can include an interface for defining patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions. In one example, the method can also include communicating a signal to control a patient's implantable medical device to conduct diagnostic operations to obtain patient data by the VC cloud telehealth system in response to establishing the first communication connection, wherein one or more entries of the patient models comprises at least one entry related to a condition of a patient's implantable medical device. In another example, the diagnostic operations can include at least one set of operations from the list consisting of: performing impedance measures15968WOO1 (013-0632PCT1) 10 PATENTof electrodes of one or more stimulation leads and performing stimulation lead migration measurements.

[0015] In accordance with embodiments herein, virtual clinic (VC) cloud telehealth system is provided that can be configured to conduct a VC session between a patient and a clinician to provide medical services. The VC cloud telehealth system can include one or more servers configured to be in communication with a patient electronic device and a clinician electronic device over a network. The one or more servers can include one or more processors that, when executing program instructions, are configured to obtain patient inputs from a chatbot module of the patient electronic device and define one or more set of questions to be delivered by the chatbot module to a patient during a pre-VC session interview. The one or more processors can also be configured to obtain patient input data from the patient electronic device based on the one or more set of questions, define patient models, each of the patient models corresponding to a patient condition or a medical response for the patient, wherein each patient model comprises multiple entries that define relative relevance of each respective entry to the corresponding patient condition or medical response, and upon completion of the pre-VC session interview of the patient, calculate, relevance metrics for respective questions using processed patient responses and the patient models. The one or more processors can also be configured to identify one or more questions based on the relevance metrics and communicate the one or more questions identified to a clinician electronic device for display.15968WOO1 (013-0632PCT1) 11 PATENT

[0016] Optionally, the one or more processors can also be configured to sort the one or more questions in an order related to respective relevance metrics for the one or more questions. In one aspect, the one or more processors can additionally be configured to generate a summary of the pre-VC session interview obtained using the chatbot module and transmitting a downloadable for displaying on an interface of the patient electronic device, when transmitting the one or more questions. In another aspect, the patient models can include entries related to a physiological state of a patient, and the one or more processors can be further configured to obtain sensor data to evaluate entries related to the physiological state of the patient. In one example, the patient models may each comprise an occurrence metric that is reflective of an occurrence of the patient condition or the medical response. In another example, to calculate the relevance metrics can include applying occurrence metrics to weight individual question relevance calculations.

[0017] Optionally, the system can also include a library of pre-defined patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions. In one aspect, the one or more processors can be further configured to obtain the defining patient questions, the patient models, and the mapping definitions selected by a clinician at clinician interface to conduct one or more VC sessions. In another aspect, the one or more processors can be further configured to communicate a signal to the patient electronic device to control a patient's implantable medical device to conduct15968WOO1 (013-0632PCT1) 12 PATENTdiagnostic operations to obtain patient data and one or more entries of the patient models can include at least one entry related to a condition of a patient's implantable medical device. In one example, the diagnostic operations may include at least one set of operations from the list consisting of: performing impedance measures of electrodes of one or more stimulation leads and performing stimulation lead migration measurements.DESCRIPTION OF THE DRAWINGS

[0018] FIG. 1 illustrates a schematic diagram of a stimulation system, in accordance with embodiments herein.

[0019] FIG. 2 illustrates a schematic block diagram of remote care service system, in accordance with embodiments herein.

[0020] FIG. 3A illustrates a schematic block diagram of a virtual clinic (VC) cloud telehealth system, in accordance with embodiments herein.

[0021] FIG. 3B illustrates a schematic diagram of a data analytics platform of a VC cloud telehealth system, in accordance with embodiments herein.

[0022] FIG. 4 illustrates a graph of a patient data level over time, in accordance with embodiments herein.

[0023] FIG. 5 illustrates a schematic block flow diagram of operations for a VC session, in accordance with embodiments herein.15968WOO1 (013-0632PCT1) 13 PATENT

[0024] FIG. 6A illustrates a schematic block diagram of a VC cloud telehealth system, in accordance with embodiments herein.

[0025] FIG. 6B illustrates a schematic block diagram of a VC cloud telehealth system, in accordance with embodiments herein.

[0026] FIG. 7 illustrates a schematic diagram of a patient model, in accordance with embodiments herein.

[0027] FIG. 8 illustrates an example chatbot interview, in accordance with embodiments herein.

[0028] FIG. 9 illustrates a schematic block flow diagram of a method for scheduling VC session, in accordance with embodiment herein.

[0029] FIG. 10 illustrates a schematic block flow diagram of training a model with relation to a VC session, in accordance with embodiments herein.

[0030] FIG. 11 illustrates a schematic diagram of a remote programming module, in accordance with embodiments herein.

[0031] FIG. 12 illustrates a schematic block flow diagram of a method of operating a remote programming device, in accordance with embodiments herein.

[0032] FIG. 13 illustrates a schematic diagram of a user interface, in accordance with embodiments herein.15968WOO1 (013-0632PCT1) 14 PATENTDETAILED DESCRIPTION

[0033] It will be readily understood that the components of the embodiments as generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations in addition to the example embodiments described. Thus, the following more detailed description of the example embodiments, as represented in the figures, is not intended to limit the scope of the embodiments, as claimed, but is merely representative of example embodiments.

[0034] Reference throughout this specification to “one embodiment” or “an embodiment” (or the like) means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in one embodiment” or “in an embodiment” or the like in various places throughout this specification are not necessarily all referring to the same embodiment.

[0035] Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments. One skilled in the relevant art will recognize, however, that the various embodiments can be practiced without one or more of the specific details, or with other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or15968WOO1 (013-0632PCT1) 15 PATENTdescribed in detail to avoid obfuscation. The following description is intended only by way of example, and simply illustrates certain example embodiments.

[0036] The methods described herein may employ structures or aspects of various embodiments (e.g., systems and / or methods) discussed herein. In various embodiments, certain operations may be omitted or added, certain operations may be combined, certain operations may be performed simultaneously, certain operations may be performed concurrently, certain operations may be split into multiple operations, certain operations may be performed in a different order, or certain operations or series of operations may be re-performed in an iterative fashion. It should be noted that other methods may be used, in accordance with an embodiment herein. Further, wherein indicated, the methods may be fully or partially implemented by one or more processors of one or more devices or systems. While the operations of some methods may be described as performed by the processor(s) of one device, additionally, some or all of such operations may be performed by the processor(s) of another device described herein.

[0037] It should be clearly understood that the various arrangements and processes broadly described and illustrated with respect to the Figures, and / or one or more individual components or elements of such arrangements and / or one or more process operations associated of such processes, can be employed independently from or together with one or more other components, elements and / or process operations described and illustrated herein. Accordingly, while15968WOO1 (013-0632PCT1) 16 PATENTvarious arrangements and processes are broadly contemplated, described and illustrated herein, it should be understood that they are provided merely in illustrative and non-restrictive fashion, and furthermore can be regarded as but mere examples of possible working environments in which one or more arrangements or processes may function or operate.

[0038] All references, including publications, patent applications and patents cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.Terms

[0039] The term “VC cloud telehealth system” shall mean any group of components, devices, circuits, etc. that communicate with one or more telehealth servers to exchange or analyze patient data and information and create a communication pathway between a patient electronic device and clinician electronic device. In one example, a sensor, wearable device, IMD, or the like used to provide patient information is part of the VC cloud telehealth system in addition to a patient electronic device and clinician electronic device. The one or more telehealth servers may receive and communicate patient data and information, input the patient data and information into one or more patient models, and output questions, summaries, suggestions, or the like that can be communicated to the clinician electronic device.15968WOO1 (013-0632PCT1) 17 PATENT

[0040] The term “clinician electronic device”, shall mean any and all electronic devices utilized by a clinician, technician, physician, caregiver, nurse, doctor, or the like. In examples the clinician electronic device can be utilized for communicating with a patient electronic device over a network via a communication pathway during a virtual clinic (VC) session. The clinician electronic device can be a central processing unit (CPU), desktop computer, laptop computer, tablet, smartphone, smart watch, monitor console, etc. The clinician electronic device includes one or more processors configured to follow instructions, and a transceiver configured to communicate over a network, in a cloud, over Bluetooth (BLE), wirelessly, over the air, through a wire, or the like. In another example, the clinician electronic device is local to the patient, and can communicate with an implanted medical device of a patient. In an example, the clinician electronic device can be located locally at the patient, or remotely and communicate with a patient electronic device to receive input from an IMD or another patient device.

[0041] The term “patient electronic device”, as used herein refers to any and all electronic devices utilized by a patient. In examples the patient electronic device can be utilized for communicating with a clinician electronic device over a network via a communication pathway during a virtual clinic (VC) session. The patient electronic device can monitor, receive inputs, or make determinations related to an IMD of the patient. The patient electronic device can be a central processing unit (CPU), desktop computer, laptop computer, tablet, smartphone, smart watch,15968WOO1 (013-0632PCT1) 18 PATENTmonitor console, etc. The patient electronic device includes one or more processors configured to follow instructions, and a transceiver configured to communicate over a network, in a cloud, over Bluetooth (BLE), wirelessly, over the air, through a wire, or the like. In examples, the patient electronic device can provide a communication connection with a patient device, such as an IMD, to obtain patient input data that can be used during a VC session.

[0042] The term “virtual clinic session” or “VC session” shall mean any period of time dedicated to communication between electronic devices over a network, mesh network, wirelessly, wired, etc. to provide information and data between a patient and medical personnel (e.g., clinician). During a VC session a communication pathway is established between a clinician electronic device and a patient electronic device over a network. In one example, the communication pathway can be established via one or more telehealth servers that are configured to receive input data and information from the patient electronic device and clinician electronic device, analyze the data and information, and out information and data for display by either or both of the patient electronic device and clinician electronic device. In one example the VC session includes a programming session and can be related to the operation of an IMD based on a set of instructions to provide a treatment.

[0043] The terms “pre virtual clinic session” and “pre-VC session” shall mean any period of time dedicated to inputting patient data and information into a15968WOO1 (013-0632PCT1) 19 PATENTpatient electronic device for use during a VC session. In one example the patient data and information may be directly inputted by the patient via an input such as a keyboard, touchscreen, or the like. Alternatively, the patient data and information may be inputted passively, such as through the patient electronic device obtaining sensor data, including from an IMD. The patient data and information can include patient identification data, patient health data, demographic data, patient location data, patient physiological state, patient treatments, IMD data, impedance measurements, electrode use data, answers to questions, questions of the patient, or the like. In one example the pre-VC session occurs prior to the beginning of the VC session. In another example the pre-VC session occurs while a communication pathway between the patient electronic device and clinician electronic device exists, and a VC session is in progress.

[0044] The term “chabot module” shall mean a computer program that uses circuitry to simulate a human conversation so that a human can interact with an electronic device without interaction of another human. In one example, the circuitry can include artificial neurons, synaptic circuits, or the like of an artificial neural network. In examples the chabot module can be responsive to auditory inputs, or manual inputs from a user. In an example the user can be patient.

[0045] The term “mapping definition” shall mean the process of connecting data fields via circuitry from one source to another source. In one example, the15968WOO1 (013-0632PCT1) 20 PATENTmapping definition can be represented by the pathway through artificial neurons and synaptic circuits in an artificial neural network.

[0046] The term “entry” and “entries” shall mean a portion or piece of data that is input into a VC cloud telehealth system. In one example, the entry includes any and all data input into a model, including a patient model. As an example, if during a pre-VC session or VC session the patient inputs that the patient is 1) forty (40) years old, 2) 200 lbs., 3) is experiencing random shooting pain in their gut after eating, 4) feels light headed, 5) has a rash, 6) wants to know if feeling sluggish after eating lunch is normal, and an patient device indicates the patient 7) has a blood glucose of 90 mg / dL. In the example, each of 1-7 is considered an entry that can be inputted into one or more patient models for analysis.

[0047] The term “real-time” shall mean at the same time, or a time substantially contemporaneous, with an occurrence of another event or action. For the avoidance of doubt, as an example, a dynamically adjusted object or device is changed immediately, or within a second or two.

[0048] The term “library” shall mean a collection of digital resources. In one example, the collection of digital resources can be stored in a storage device such as a memory. Digital resources can include precompiled files, functions, scripts, routines, text, images, classes, information, data, or the like.

[0049] The terms “processor,” “a processor,” “one or more processors” and “the processor” shall mean one or more processors. The one or more processors15968WOO1 (013-0632PCT1) 21 PATENTmay be implemented by one, or by a combination of more than one implantable medical device, a wearable device, a local device, a remote device, a server computing device, a network of server computing devices and the like. The one or more processors may be implemented at a common location or at distributed locations. The one or more processors may implement the various operations described herein in a serial or parallel manner, in a shared-resource configuration and the like.

[0050] Embodiments may be implemented in connection with one or more implantable medical devices (IMDs). Non-limiting examples of IMDs include one or more neurostimulator devices, implantable cardiac monitoring and / or therapy devices. For example, the IMD may represent a cardiac monitoring device, pacemaker, cardioverter, cardiac rhythm management device, ICD, neurostimulator, leadless monitoring device, leadless pacemaker, an external shocking device (e.g., an external wearable defibrillator), and the like. For example, the IMD may be a subcutaneous IMD that includes one or more structural and / or functional aspects of the device(s) described in U. S. Application Serial No.: 15 / 973,195, titled “Subcutaneous Implantation Medical Device With Multiple Parasternal-Anterior Electrodes” and filed May 7, 2018; U. S. Application Serial No.: 15 / 973,219, titled “Implantable Medical Systems And Methods Including Pulse Generators And Leads” filed May 7, 2018; US Application Serial No.: 15 / 973, 249, titled “Single Site Implantation Methods For Medical Devices Having Multiple Leads”, filed May 7, 2018, which are hereby incorporated by reference in their15968WOO1 (013-0632PCT1) 22 PATENTentireties. Additionally or alternatively, the IMD may include one or more structural and / or functional aspects of the device(s) described in U. S. Patent 9,333,351 “Neurostimulation Method and System to Treat Apnea” and U. S. Patent 9,044,710 “System and Methods for Providing A Distributed Virtual Stimulation Cathode for Use with an Implantable Neurostimulation System”, which are hereby incorporated by reference. Additionally or alternatively, the IMD may include one or more structural and / or functional aspects of the device(s) described in U. S. Patent Publication No. 2024 / 0050738 “Active Implantable Medical Device”, which is incorporated by reference. Further, one or more combinations of IMDs may be utilized from the above incorporated patents and applications in accordance with embodiments herein.

[0051] Additionally or alternatively, the IMD may include one or more structural and / or functional aspects of the device(s) described in U. S. Patent 9,216,285 “Leadless Implantable Medical Device Having Removable and Fixed Components” and U. S. Patent 8,831,747 “Leadless Neurostimulation Device and Method Including the Same”, which are hereby incorporated by reference. Additionally or alternatively, the IMD may include one or more structural and / or functional aspects of the device(s) described in U. S. Patent 8,391,980 “Method and System for Identifying a Potential Lead Failure in an Implantable Medical Device”, U. S. Patent 9,232,485 “System and Method for Selectively Communicating with an Implantable Medical Device”, EP Application No. 0070404 “Defibrillator” and, U. S. Patent 5,334,045 “Universal Cable Connector for15968WOO1 (013-0632PCT1) 23 PATENTTemporarily Connecting Implantable Leads and Implantable Medical Devices with a Non-lmplantable System Analyzer”, U. S. Patent Application 15 / 973,126, titled " Method And System For Second Pass Confirmation Of Detected Cardiac Arrhythmic Patterns"; U. S. Patent Application 15 / 973,351, Titled " Method And System To Detect R-Waves In Cardiac Arrhythmic Patterns”; U. S. Patent Application 15 / 973,307, titled " Method And System To Detect Post Ventricular Contractions In Cardiac Arrhythmic Patterns"; and U. S. Patent Application 16 / 399,813, titled " Method And System To Detect Noise In Cardiac Arrhythmic Patterns” which are hereby incorporated by reference.

[0052] Additionally or alternatively, the IMD may be a leadless cardiac monitor (ICM) that includes one or more structural and / or functional aspects of the device(s) described in U. S. Patent Application No. 15 / 084,373, filed March 29, 2016, entitled, " Method and System to Discriminate Rhythm Patterns in Cardiac Activity"; U. S. Patent Application 15 / 973,126, titled “Method And System For Second Pass Confirmation Of Detected Cardiac Arrhythmic Patterns”; U. S. Patent Application 15 / 973,351, titled “Method And System To Detect R-Waves In Cardiac Arrhythmic Patterns”; U. S. Patent Application 15 / 973,307, titled “Method And System To Detect Post Ventricular Contractions In Cardiac Arrhythmic Patterns”; and U. S. Patent Application 16 / 399,813, titled " Method And System To Detect Noise In Cardiac Arrhythmic Patterns", which are expressly incorporated herein by reference.15968WOO1 (013-0632PCT1) 24 PATENT

[0053] Embodiments may be implemented in connection with remote programming an IMD with the clinician electronic device or patient electronic device as a result of a VC session. Non-limiting examples of such programming systems that use a network for communicating between a patient device (e.g., IMD) and a remote programming device are providing by U. S. Pat. Application 18 / 337,282, titled “System and Method for Implantable Medical Device Remote Programming” and U. S. Pat. Application 17 / 805,823, titled “System and Method for Implantable Medical Device Remote Programming”, which are expressly incorporated herein by reference.

[0054] Some embodiments are directed to provision of digital health services including telehealth services and virtual clinic services using artificial intelligence and / or machine learning (AI / ML). Some embodiments provide chatbot functionality to interact with patients before sessions with clinicians occur. Some embodiments analyze patient responses to chatbot queries to generate a model of the patient condition. The model of the patient’s condition is compared to one or more condition, disorder, or disease models to diagnose the patient’s condition and / or determine an appropriate medical treatment of the patient. Additionally, the one or more models may be analyzed against the original patient response(s) and / or subsequent response(s) to identify to the clinician the next action to be taken that is most or more probable to lead to a diagnosis or identification of appropriate medical action.15968WOO1 (013-0632PCT1) 25 PATENT

[0055] In some embodiments, AI / ML guided virtual clinic sessions are conducted for the purpose of programming implantable or other personal medical devices of patients. For example, spinal cord stimulation systems, deep brain stimulation systems, cardiac rhythm management (CRM) devices, insulin delivery systems, and / or the like may be programmed during virtual clinic sessions that are guided by AI / ML analysis of patient responses according to some embodiments.

[0056] As an example of an implantable medical device, neurostimulation devices generate electrical pulses for application to neural tissue of a patient to treat a variety of disorders. One category of neurostimulation systems is deep brain stimulation (DBS). In DBS, pulses of electrical current are delivered to target regions of a subject's brain, for example, for the treatment of movement and effective disorders such as PD and essential tremor. Another category of neurostimulation systems is spinal cord stimulation (SCS) which is often used to treat chronic pain such as Failed Back Surgery Syndrome (FBSS) and Complex Regional Pain Syndrome (CRPS). SCS devices may also treat a number of other disorders in addition to chronic pain. Dorsal root ganglion (DRG) stimulation is another example of a neurostimulation therapy in which electrical stimulation is provided to the dorsal root ganglion structure that is just outside of the epidural space. DRG stimulation is also generally used to treat chronic pain but may treat other disorders. Neurostimulation therapies including SCS stimulation and DRG stimulation are also known to effect other physiological processes such as cardiac, respiratory, and digestive processes as examples.15968WOO1 (013-0632PCT1) 26 PATENT

[0057] Neurostimulation systems generally include a pulse generator and one or more leads. A stimulation lead includes a lead body of insulative material that encloses wire conductors. The distal end of the stimulation lead includes multiple electrodes, or contacts, that intimately impinge upon patient tissue and are electrically coupled to the wire conductors. The proximal end of the lead body includes multiple terminals (also electrically coupled to the wire conductors) that are adapted to receive electrical pulses. In DBS systems, the distal end of the stimulation lead is implanted within the brain tissue to deliver the electrical pulses. The stimulation leads are then tunneled to another location within the patient's body to be electrically connected with a pulse generator or, alternatively, to an “extension.” The pulse generator is typically implanted in the patient within a subcutaneous pocket created during the implantation procedure.

[0058] The pulse generator is typically implemented using a metallic housing (or “can”) that encloses circuitry for generating the electrical stimulation pulses, control circuitry, communication circuitry, a rechargeable or primary cell battery, etc. The pulse generating circuitry is coupled to one or more stimulation leads through electrical connections provided in a “header” of the pulse generator. Specifically, feedthrough wires typically exit the metallic housing and enter into a header structure of a moldable material. Within the header structure, the feedthrough wires are electrically coupled with annular electrical connectors. The header structure holds the annular connectors in a fixed arrangement that15968WOO1 (013-0632PCT1) 27 PATENTcorresponds to the arrangement of terminals on the proximal end of a stimulation lead.

[0059] Stimulation system 100 is shown in FIG. 1 according to some embodiments. Stimulation system 100 generates electrical pulses for application to tissue of a patient to treat one or more disorders of the patient. System 100 includes an implantable pulse generator (IPG) 150 that is adapted to generate electrical pulses for application to tissue of a patient. Examples of commercially available implantable pulse generators include the ETERNA™, PROCLAIM™, INFINITY™, and LIBERTA™ implantable pulse generators (available from ABBOTT, PLANO Tex.). Alternatively, system 100 may include an external pulse generator (EPG) positioned outside the patient's body. IPG 150 typically includes a metallic housing (or can) that encloses a controller 151, pulse generating circuitry 152, a battery 153, far-field and / or near field communication circuitry 154 (e.g., BLUETOOTH communication circuitry), and other appropriate circuitry and components of the device. Controller 151 typically includes one or more microcontrollers or other suitable processors for controlling the various other components of the device. Software or firmware code is typically stored in memory of IPG 150 for execution by a microcontroller or processor to control respective components of the device.

[0060] IPG 150 may comprise one or more attached extension components 170 or be connected to one or more separate extension components 170.15968WOO1 (013-0632PCT1) 28 PATENTAlternatively, one or more stimulation leads 110 may be connected directly to IPG 150. Within IPG 150, electrical pulses are generated by pulse generating circuitry 152 and are provided to switching circuitry. The switching circuit connects to output wires, metal ribbons, traces, lines, or the like (not shown) from the internal circuitry of pulse generator 150 to output connectors (not shown) of pulse generator 150 which are typically contained in the “header” structure of pulse generator 150. Commercially available ring / spring electrical connectors are frequently employed for output connectors of pulse generators (e.g., “Bal-Seal” connectors). The terminals of one or more stimulation leads 110 are inserted within connector portion 171 for electrical connection with respective connectors or directly within the header structure of pulse generator 150. Thereby, the pulses originating from IPG 150 are conducted to electrodes 111 through wires contained within the lead body of lead 110. The electrical pulses are applied to tissue of a patient via electrodes 111.

[0061] For implementation of the components within IPG 150, a processor and associated charge control circuitry for an implantable pulse generator is described in U. S. Pat. No. 7,571,007, entitled “SYSTEMS AND METHODS FOR USE IN PULSE GENERATION,” which is incorporated herein by reference. Circuitry for recharging a rechargeable battery of an implantable pulse generator using inductive coupling and external charging circuits are described in U. S. Pat. No. 11,969,605, entitled “SYSTEMS AND METHODS FOR NOISE FILTERING IN15968WOO1 (013-0632PCT1) 29 PATENTIMPLANTABLE MEDICAL DEVICE CHARGING SYSTEMS” which is incorporated herein by reference.

[0062] An example and discussion of pulse generating circuitry is provided in U. S. Patent Publication No. US20210252291 A1 entitled “NEUROMODULATION THERAPY WITH A MULTIPLE STIMULATION ENGINE SYSTEM,” which is incorporated herein by reference. One or multiple sets of such circuitry may be provided within IPG 150. Different pulses on different electrodes may be generated using a single set of pulse generating circuitry using consecutively generated pulses according to a “multi-stimset program” as is known in the art. Alternatively, multiple sets of such circuitry may be employed to provide pulse patterns that include simultaneously generated and delivered stimulation pulses through various electrodes of one or more stimulation leads as is also known in the art. Various sets of parameters may define the pulse characteristics and pulse timing for the pulses applied to various electrodes as is known in the art. Although constant current pulse generating circuitry is contemplated for some embodiments, any other suitable type of pulse generating circuitry may be employed such as constant voltage pulse generating circuitry.

[0063] Stimulation lead(s) 110 may include a lead body of insulative material about a plurality of conductors within the material that extends from a proximal end of lead 110 to its distal end. The conductors electrically couple a plurality of electrodes 111 to a plurality of terminals (not shown) of lead 110. The15968WOO1 (013-0632PCT1) 30 PATENTterminals are adapted to receive electrical pulses and the electrodes 111 are adapted to apply stimulation pulses to tissue of the patient. Also, sensing of physiological signals may occur through electrodes 111, the conductors, and the terminals. Additionally or alternatively, various sensors (not shown) may be located near the distal end of stimulation lead 110 and electrically coupled to terminals through conductors within the lead body 172. Stimulation lead 110 may include any suitable number and type of electrodes 111, terminals, and internal conductors.

[0064] External controller device 160 is a device that permits the operations of IPG 150 to be controlled by a user after IPG 150 is implanted within a patient. Also, multiple controller devices may be provided for different types of users (e.g., the patient or a clinician). Controller device 160 can be implemented by utilizing a suitable handheld processor-based system that possesses wireless communication capabilities. Software is typically stored in memory of controller device 160 to control the various operations of controller device 160. The interface functionality of controller device 160 is implemented using suitable software code for interacting with the user and using the wireless communication capabilities to conduct communications or form a communication connection with IPG 150. One or more user interface screens may be provided in software to allow the patient and / or the patient's clinician to control operations of IPG 150 using controller device 160. In some embodiments, commercially available devices such as APPLE iOS devices are adapted for use as controller device 160 by include one15968WOO1 (013-0632PCT1) 31 PATENTor more “apps” that communicate with IPG 150 using, for example, BLUETOOTH communication.

[0065] Controller device 160 preferably provides one or more user interfaces to allow the user to operate IPG 150 according to one or more stimulation programs to treat the patient's disorder(s). Each stimulation program may include one or more sets of stimulation parameters including pulse amplitude, pulse width, pulse frequency or inter-pulse period, pulse repetition parameter (e.g., number of times for a given pulse to be repeated for respective stimset during execution of program), etc.

[0066] Controller device 160 may permit programming of IPG 150to provide a number of different stimulation patterns or therapies to the patient as appropriate for a given patient and / or disorder. Examples of different stimulation therapies include conventional tonic stimulation (continuous train of stimulation pulses at a fixed rate), BurstDR stimulation (burst of pulses repeated at a high rate interspersed with quiescent periods with or without duty cycling), “high frequency” stimulation (e.g., a continuous train of stimulation pulses at 10,000 Hz), noise stimulation (series of stimulation pulses with randomized pulse characteristics such as pulse amplitude to achieve a desired frequency domain profile). Any suitable stimulation pattern or combination thereof can be provided by IPG 150 according to some embodiments. Controller device 160 communicates the stimulation parameters and / or a series of pulse characteristics defining the pulse15968WOO1 (013-0632PCT1) 32 PATENTseries to be applied to the patient to IPG 150 to generate the desired stimulation therapy.

[0067] In some embodiments, IPG 150 implements a “waveform player” stimulation design in which stimulation pulses to be delivered to the patient are defined in a sequence of pulses with respective pulse parameters. An example of a “waveform player” design is described in U. S. Pat. App. Pub. No. US20220203107A1, entitled “System and method for operating an implantable pulse generator for neuromodulation,” which is incorporated herein by reference. Controller device 160 (e.g., a patient controller device and / or a clinician programmer device) may download a program to IPG 150 which defines the various pulses and timing for the pulses for delivery to the patient via defined electrodes or electrode combinations.

[0068] Examples of suitable therapies include tonic stimulation (in which a fixed frequency pulse train) is generated, burst stimulation (in which bursts of multiple high frequency pulses) are generated which in turn are separated by quiescent periods, “high frequency” stimulation, multi-frequency stimulation, and noise stimulation.

[0069] Descriptions of respective neurostimulation therapies are provided in the following publications: (1) Schu S., Slotty P. J., Bara G., von Knop M., Edgar D., Vesper J. A Prospective, Randomised, Double-blind, Placebo-controlled Study to Examine the Effectiveness of Burst Spinal Cord Stimulation Patterns for the15968WOO1 (013-0632PCT1) 33 PATENTTreatment of Failed Back Surgery Syndrome. Neuromodulation 2014; 17: 443-450; (2) Al-Kaisy A1, Van Buyten J P, Smet I, Palmisani S, Pang D, Smith T. 2014. Sustained effectiveness of 10 kHz high-frequency spinal cord stimulation for patients with chronic, low back pain: 24-month results of a prospective multicenter study. Pain Med. 2014 March; 15(3):347-54; and (3) Sweet, Badjatiya, Tan D1, Miller. Paresthesia-Free High-Density Spinal Cord Stimulation for Postlaminectomy Syndrome in a Prescreened Population: A Prospective Case Series. Neuromodulation. 2016 April; 19(3):260-7.

[0070] Burst stimulation is described in U. S. Pat. No. 8,224,453 and U. S. Published Application No. 20060095088 which are incorporated herein by reference. Another burst stimulation pattern includes anodic-leading pulses as described in U. S. Patent No. 11,957,913, entitled “Systems and methods for burst waveforms with anodic-leading pulses,” which is incorporated herein by reference. A hyperpolarizing stimulation pattern is described in U. S. Pat. App. Pub. No.20230144889A1, entitled “System and methods to deliver hyperpolarizing waveform,” which is incorporated herein by reference. Noise stimulation is described in U. S. Pat. Pub. App. No. US20230146551 A1 and U. S. Pat. No.8,682,44162 which are incorporated herein by reference.

[0071] A “coordinated reset” pulse pattern is applied to neuronal subpopulation / target sites to desynchronize neural activity in the subpopulations. Coordinated reset stimulation is described, for example, by Peter A. Tass et al in15968WOO1 (013-0632PCT1) 34 PATENTCOORDINATED RESET HAS SUSTAINED AFTER EFFECTS IN PARKINSONIAN MONKEYS, Annals of Neurology, Volume 72, Issue 5, pages 816-820, November 2012, which is incorporated herein by reference. The electrical pulses in a coordinated reset pattern are generated in bursts of pulses with respective bursts being applied to tissue of the patient using different electrodes in a time-offset manner. The time-offset is selected such that the phase of the neural-subpopulations is reset in a substantially equidistant phase-offset manner. By resetting neuronal subpopulations in this manner, the population will transition to a desynchronized state by the interconnectivity between the neurons in the overall neuronal population. All of these stimulation pattern / waveform references are incorporated herein by reference.

[0072] For implementation of the components within IMD 14, a processor and associated charge control circuitry for an implantable pulse generator is described in U. S. Pat. No. 7,571,007, entitled “SYSTEMS AND METHODS FOR USE IN PULSE GENERATION,” which is incorporated herein by reference. Circuitry for recharging a rechargeable battery of an implantable pulse generator using inductive coupling and external charging circuits are described in U. S. Pat. No. 7,212,110, entitled “IMPLANTABLE DEVICE AND SYSTEM FOR WIRELESS COMMUNICATION” which is incorporated herein by reference.

[0073] IPG 150 modifies its internal parameters in response to the control signals from controller device 160 to vary the stimulation characteristics of15968WOO1 (013-0632PCT1) 35 PATENTstimulation pulses transmitted through stimulation lead 110 to the tissue of the patient. Neurostimulation systems, stimsets, and multi-stimset programs are discussed in PCT Publication No. WO 2001 / 093953, entitled “NEUROMODULATION THERAPY SYSTEM,” and U. S. Pat. No. 7,228,179, entitled “METHOD AND APPARATUS FOR PROVIDING COMPLEX TISSUE STIMULATION PATTERNS,” which are incorporated herein by reference.

[0074] External charger device 165 may be provided to recharge battery 153 of IPG 150 according to some embodiments when IPG 150 includes a rechargeable battery. External charger device 165 comprises a power source and electrical circuitry (not shown) to drive current through coil 166. The patient places the primary coil 166 against the patient's body immediately above the secondary coil (not shown), i.e., the coil of the implantable medical device. Preferably, the primary coil 166 and the secondary coil are aligned in a coaxial manner by the patient for efficiency of the coupling between the primary and secondary coils. In operation during a charging session, external charger device 165 generates an AC-signal to drive current through coil 166 at a suitable frequency. Assuming that primary coil 166 and secondary coil are suitably positioned relative to each other, the secondary coil is disposed within the magnetic field generated by the current driven through primary coil 166. Current is then induced by a magnetic field in the secondary coil. The current induced in the coil of the implantable pulse generator is rectified and regulated to recharge the battery of IPG 150. IPG 150 may also communicate status messages to external charging device 165 during charging15968WOO1 (013-0632PCT1) 36 PATENToperations to control charging operations. For example, IPG 150 may communicate the coupling status, charging status, charge completion status, etc.

[0075] System 100 may include external wearable device 170 such as a smartwatch or health monitor device. Wearable device may be implemented using commercially available devices such as FITBIT VERSA SMARTWATCH™, SAMSUNG GALAXY SMARTWATCH™, and APPLE WATCH™ devices with one or more apps or appropriate software to interact with IPG 150 and / or controller device 160. In some embodiments, wearable device 170, controller device 160, and IPG 150 conduct communications using BLUETOOTH communications.

[0076] Wearable device 170 monitors activities of the patient and / or senses physiological signals. Wearable device 170 may track physical activity and / or patient movement through accelerometers. Wearable device 170 may monitor body temperature, heart rate, electrocardiogram activity, blood oxygen saturation, and / or the like. Wearable device 170 may monitor sleep quality or any other relevant health related activity.

[0077] Wearable device 170 may provide one or more user interface screens to permit the patient to control or otherwise interact with IPG 150. For example, the patient may increase or decrease stimulation amplitude, change stimulation programs, turn stimulation on or off, and / or the like using wearable device 170. Also, the patient may check the battery status of other implant status information using wearable device 170.15968WOO1 (013-0632PCT1) 37 PATENT

[0078] Wearable device 170 may include one or more interface screens to receive patient input. In some embodiments, wearable device 170 and / or controller device 160 are implemented (individually or in combination) to provide an electronic patient diary function. The patient diary function permits the patient to record on an ongoing basis the health status of the patient and the effectiveness of the therapy for the patient. In some embodiments as discussed herein, wearable device 170 and / or controller device 160 enable the user to indicate the current activity of the patient, the beginning of an activity, the completion of an activity, the ease or quality of patient's experience with a specific activity, the patient's experience of pain, the patient's experience of relief from pain by the stimulation, or any other relevant indication of patient health by the patient.

[0079] An example of a known remote care management system is the NEUROSPHERE™ DIGITAL CARE / VIRTUAL CLINIC™ system which is a connected care management platform compatible with ABBOTT (Plano, TX) products. Although the NEUROSPHERE™ DIGITAL CARE / VIRTUAL CLINIC™ system is intended for use with patient receiving neurostimulation therapies, the virtual clinic / remote care system can be modified to support remote support of patients by clinicians for any type of disorder and / or interacting with a variety of patient devices.

[0080] Referring to FIG. 2, depicted therein is an example architecture of a remote care service system 200 configured to support remote patient therapy as15968WOO1 (013-0632PCT1) 38 PATENTpart of an integrated remote care service session according to one or more embodiments of the present patent disclosure. As used herein, a “remote care system” may describe a healthcare delivery system configured to support a remote care service over a network in a communication session between a patient and a clinician wherein telehealth or telemedicine applications involving remote medical consultations. The remote medical consultations may be guided using data from a variety of patient devices 270 (including, for example, sensor system 100 as shown in FIG. 1 and a variety of other patient devices). In some embodiments, remote care services system 200 includes AI / ML functionality to guide patient interaction as will be discussed herein.

[0081] As illustrated, the architecture of remote care system 200 includes patient electronic device 250 and clinician electronic device 280, each having a corresponding remote care service application module, e.g., a patient application 252 and a clinician application 282, executed on a suitable hardware / software platform for supporting a remote care service that may be managed by a network entity 255. In some embodiments, the network entity 255 may comprise a datacenter or cloud-based service node (e.g., disposed in a public cloud, a private cloud, or a hybrid cloud, involving at least a portion of the Internet) operative to host a remote care session management service 257.

[0082] In one arrangement, patient application 252 and clinician application 282 may each include a respective remote session manager 254, 284 configured15968WOO1 (013-0632PCT1) 39 PATENTto effectuate or otherwise support a corresponding communication interface 260, 290 with network entity 255 using any known or heretofore unknown communication protocols and / or technologies. In one arrangement, interfaces 260, 290 are each operative to support an AV channel or session 263A, 263B and a remote device channel or session 265A, 265B, respectively, with an AV communication service 261 A and a remote therapy session service 261 B of the remote care session management service 257 as part of a common bi-directional remote care session 259, 299 established therewith.

[0083] In one arrangement, patient application 252 and clinician application 282 may each further include or otherwise support suitable graphical user interfaces (GUIs) and associated controls 256, 286, as well as corresponding AV managers 258, 288, each of which may be interfaced with respective remote session managers 254, 284. Remote care session manager 254 of the patient application 252 and remote care session manager 284 of the clinician application may each also be interfaced with a corresponding logging manager 262, 286 according to some embodiments. Remote care session manager 254 of patient application 252 is further interfaced with a security manager 264, which may be configured to facilitate secure or trusted communication relationships with the network entity 255. Likewise, remote care session manager 284 of clinician application 282 may also be interfaced with a security manager 288 that may be configured to facilitate secure or trusted communication relationships with the network entity 255. Each security manager 264, 288 may be interfaced with a15968WOO1 (013-0632PCT1) 40 PATENTcorresponding communication manager 266, 290 with respect to facilitating secure communications between the clinician electronic device 280 and the patient electronic device 250. Therapy communication manager 266 of the patient application 252 may also interface with a local communication module 268 operative to effectuate secure communications with the patient’s IMD(s) 270 using suitable wireless communication (e.g., Bluetooth). In still further arrangements, security managers 264, 288 of patient and clinician applications 252, 282 may be configured to interface with the remote care session management service 257 to establish trusted relationships between patient electronic device 250, clinician electronic device 280 and / or IMD(s) 270 based on the exchange of a variety of parameters, e.g., trusted indicia, cryptographic keys and credentials, etc.

[0084] In one arrangement, the integrated remote care session management service 257 may include a session data management module 271, an AV session recording service module 275 and a registration service module 283, as well as suitable database modules 273, 285 for storing session data and user registration data, respectively.

[0085] Skilled artisans will realize that the example remote care system architecture 200 set forth above may be advantageously configured to provide both telehealth medical consultations while the patient and the clinician / provider are not in close proximity to each other (e.g., not engaged in an in-person office visit or consultation). Accordingly, in some embodiments, a remote care service15968WOO1 (013-0632PCT1) 41 PATENTof some embodiments may form an integrated healthcare delivery service effectuated via a common application user interface that not only allows healthcare professionals to use electronic communications to evaluate and diagnose patients remotely but also facilitates interaction with and / or programming of the patient's IMD(s) or other devices to support patient care according to some (but not all) embodiments.

[0086] FIG. 3A illustrates an example VC cloud telehealth system 300 that can be configured to provide medical services for a clinician and patient. In a VC cloud telehealth system 300 data can be collected from patient devices and other sources and may be employed for patient management using, for example, a cloud-centric digital healthcare network architecture as illustrated in FIG. 3A according to some embodiments. Example architecture 360 may include one or more virtual clinic platforms 314, remote data logging platforms 316, patient / clinician report processing platforms 318, as well as data analytics platforms 320 and security platforms 322, at least some of which may be configured and / or deployed as an integrated digital health infrastructure 312. Virtual clinic and remote programming platforms are discussed in detail in the following applications which are incorporated herein by reference: U. S. Patent App. Pub. No. 20200398062; U. S. Patent App. Pub. No. 20230317303; U. S. Patent App. Pub. No. 20230100246; U. S. Patent App. Pub. No. 20220105350A1; U. S. Patent App. Pub. No. 20200402656; U. S. Patent App. Pub. No.20220189626; and U. S. Patent App. Pub. No. 20230271019.15968WOO1 (013-0632PCT1) 42 PATENT

[0087] One or more populations of patients are collectively shown at reference numeral 304, wherein individual patients may be provided with one or more suitable IMDs, partially implantable medical devices, other personal biomedical devices, etc., depending on respective patients' health conditions and / or treatments. A plurality of clinician electronic devices 308, patient electronic devices 310, and authorized third-party electronic devices 311 associated with respective users (e.g., clinicians, medical professionals, patients and authorized agents thereof) may be deployed as external electronic devices 306 that may be configured to interact with patients' IMDs and / or sensor / tracking devices for effectuating therapy, monitoring, data logging, secure file transfer, etc., via local communication paths or over network-based remote communication connections established in conjunction with the digital health infrastructure network 312. One or more remote data logging platforms 316 of VC cloud telehealth system 300 (shown in FIG. 3A) may be configured to obtain, receive or otherwise retrieve data from patient electronic devices including an IMD of the patient, clinician electronic devices, other authorized third-party electronic devices, or the like. For example, in response to the VC cloud telehealth system 300 establishing a first communication connection, the VC cloud system can communicate a signal to control a patient's implantable medical device to conduct diagnostic operations to obtain patient data. In one example, one or more entries of the patient models can include at least one entry related to a condition of a patient's implantable medical device.15968WOO1 (013-0632PCT1) 43 PATENT

[0088] In one example the remote logging platforms 316 can conduct diagnostic operations to obtain patient data for the VC cloud telehealth system. In one example, the diagnostic operations can include at least one set of operations including performing impedance measures of electrodes of one or more stimulation leads or performing stimulation lead migration measurements. In another example the remote logging platforms can obtain patient data related to a physiological state or states of the patient. In one example the patient data can be provided by the patient by answering questions, manually providing inputs, or the like. In another example, the physiological state(s) can be determined or related to sensor data, including a wearable patient device that can be in communication with one or more components of the VC could telehealth system.

[0089] On an individual patient level and on a patient population basis, patient aggregate data 350 is available for processing, analysis, and review to optimize patient outcomes for individual patients, for a patient population as a whole, and for relevant patient sub-populations of patients. Patient aggregate data (PAD) 350 may include basic patient data including patient name, age, and demographic information, etc. PAD 350 may also include information typically contained in a patient's medical file such as medical history, diagnosis, results from medical testing, medical images, etc. The data may be inputted directly into VC cloud telehealth system 300 by a clinician or medical professional. Alternatively, this data may be imported from digital health records of patients from one or more health care providers or institutions.15968WOO1 (013-0632PCT1) 44 PATENT

[0090] As previously discussed, a patient may employ one or more patient “apps” on the patient's smartphone or other electronic device to control or interact with patient's biochemical sensor system, IMD(s), and / or minimally invasive medical device. For example, analyte measurements may be retrieved from one or more patient devices for aggregation by VC cloud telehealth system 300. Also, patient interaction with one or more apps may be monitored and logged. For example, the patient app may be adapted to log such events (“Device Use / Events Data”) and communicate the events to VC cloud telehealth system 300 to maintain a history for the patient for review by the patient's clinician(s) to evaluate and / or optimize the patient’s care as appropriate.

[0091] PAD 350 may include “Patient Self-Report Data” obtained using a digital health care or wellness app operating on patient electronic devices 310. The patient self-report data may include patient reported levels of various conditions, patient well-being scores, emotional states, activity levels, and / or any other relevant patient reported information.

[0092] PAD 350 may include sensor data such as sensor analyte data. Data captured using such sensors can be communicated from the medical devices to patient controller devices and then stored within patient / clinician data logging and monitoring platform 316. Patients may also possess wearable devices such as health monitoring products (heart rate monitors, fitness tracking devices, smartwatches, etc.). Any data available from wearable devices may be likewise15968WOO1 (013-0632PCT1) 45 PATENTcommunicated to monitoring platform 316. In one example the VC cloud telehealth system 300 can conduct diagnostic operations to obtain patient data using the wearable devices or the sensors. In one example, the diagnostic operations can include at least one set of operations including performing impedance measures of electrodes of one or more stimulation leads or performing stimulation lead migration measurements.

[0093] As previously discussed, patients may interact with clinicians using remote programming / virtual clinic capabilities of a VC cloud telehealth system 300. The video data captured during virtual clinic and / or remote programming sessions may be archived by platform 314. The video from these sessions may be subjected to automated video analysis (contemporaneously with the sessions or afterwards) to extract relevant patient metrics. PAD data 350 may include video analytic data for individual patients, patient sub-populations, and the overall patient population for each supported therapy.

[0094] The data may comprise various data logs that capture patientclinician interactions (“Remote Programming Event Data” in PAD 350), e.g., individual patients' therapy / program settings data in virtual clinic and / or in-clinic settings, patients' interactions with remote learning resources, physiological / behavioral data, daily activity data, and the like. Clinicians may include clinician reported information such as patient evaluations, diagnoses, etc. in PAD 350 via platform 316 in some embodiments.15968WOO1 (013-0632PCT1) 46 PATENT

[0095] In some example arrangements, data obtained via remote monitoring, background process(es), baseline queries and / or user-initiated data transfer mechanisms may be (pre)processed or otherwise conditioned in order to generate appropriate datasets that may be used fortraining, validating and testing one or more AI / ML-based models or engines for purposes of some embodiments. In some example embodiments, patient input data may be securely transmitted to the cloud-centric digital healthcare infrastructure wherein appropriate AI / ML-based modeling techniques may be executed for evaluating the progress of the therapy trial, predicting efficacy outcomes, providing / recommending updated settings, etc.

[0096] In some embodiments, analytics are generated, and one or more AI / ML or other computation models may be employed as part of a data analytics platform, e.g., platform 320, of a cloud-centric digital health infrastructure 312. In the context of an example implementation of the digital health infrastructure 312, “Big Data” may be used as a qualitative term for a collection of datasets comprising the relevant data (including, but not limited to, PAD 350) for management of patient therapy as described herein. Because “Big Data” available with respect to patients' health data, physiological / behavioral data, sensor data gathered from patients and respective ambient surroundings, daily activity data, therapy settings data, health data collected from clinicians, etc. can be beyond the capability of management by a single, physical sever, platform 320 may employ suitable infrastructure implementations to support AI / ML and computational model processing. For example, such processes may be implemented in a “massively parallel15968WOO1 (013-0632PCT1) 47 PATENTprocessing" (MPP) architecture with software running on tens, hundreds, or even thousands of servers. In an example the one or more processors can select between one or more VC session models or criteria for a VC session based on patient input. In one example the patient data can include patient demographic data.

[0097] Fig. 3B illustrates an example embodiment of a data analytics platform 320 that is an artificial neural network (ANN). In one example, the data analytics platform 320 can be, or can be part of a chatbox module configured to allow human interaction with an electronic device. The ANN 320 can include a series 323 of layers 324A-D, each comprising one or more artificial neurons 326 arranged in one or more neuron arrays or arrangements. While four neurons 326 are shown in each layer 324A-D and four layers 324A-D are shown, alternatively, a different number of neurons 326 may be in one or more of the layers 324A-D and / or there may be a different number of layers 324A-D.

[0098] The ANN 320 may include the neurons 326 arranged in an input layer 324A, an output layer 324D, and two or more fully connected hidden or intermediate layers 324B, 324C between the input and output layers 324A, 324D. Each neuron 326 can include or represent a register 328, a microprocessor 330, and at least one input 332. The neurons 326 can generate outputs based on one or more activation functions. The neurons 326 can receive input from another neuron 326 (e.g., the output from one neuron 326 can be the input for another15968WOO1 (013-0632PCT1) 48 PATENTneuron 326). This input also can include a set of weights. The neurons 326 can be connected with each other via synaptic circuits 334, 334’. The synaptic circuits 334, 334’ can include or represent memories for storing synaptic weights.

[0099] One or more neurons 326 in the input layer 324A of the ANN 320 can receive an input 336 into the ANN 320. These neurons 326 can receive this input via the input(s) 332 of those neurons 326 in the input layer 324A. The neurons 326 receive the input, apply one or more mathematical equations or relationships stored in the registers 328 (and that include the weights) to generate an output. The processors 330 of the neurons 326 apply the equations / relationships and can pass the output to another neuron 326 in the same layer 324A or in a different layer 324B, 324C. The output from one neuron 326 is passed along a synaptic circuit 334 to another neuron 326 and is used as input to this other neuron 326. This process continues until one or more neurons 326 in the output layer 324D generate an output 338 from the ANN 320. The synaptic circuits 334, 334’, weights stored in the synaptic circuits 334, 334’, and / or the mathematical relationships between the neurons 326 can define a model that is used to predict an output such as one or more questions, or set of questions, to ask a patient, a recommendation to provide on a display, a diagnosis, a treatment recommendation, settings for a wearable device, instructions for a clinician, instructions for a patient, operating parameters for a patient electronic device, or the like. In one example, the VC cloud telehealth system 300 includes a library of15968WOO1 (013-0632PCT1) 49 PATENTpre-defined patient questions, patient models, and mapping definitions for selection by a clinician for use during the analysis by the ANN 320.

[0100] During training of the ANN 320, labeled data may be provided as input 336 to the ANN 320. This labeled data can then be encoded to include additional information or data related to the patient, patient device, clinician, diagnosis, treatment, etc. The neurons 326 process the input data as described above to generate the training output of the ANN 320. This training output can be the predicted output described above, but for a second past time period. For example, the client device sensor data from a previous appointment may be used by the ANN 320 via the model to predict the patient’s medical condition after the previous appointment. This prediction can then be compared to what the patient’s medical condition was after the appointment. The past predictions and the past actual results can be compared with each other to identify differences. In one example, the VC cloud telehealth system 300 can conduct diagnostic operations to obtain patient data from a client device sensor. In one example, the diagnostic operations can include at least one set of operations including performing impedance measures of electrodes of one or more stimulation leads or performing stimulation lead migration measurements.

[0101] Feedback can be provided to the ANN 320 in the form of a calculated error or other indication of the differences between the past predictions and the past actual conditions. Based on this error, the neurons 326 can change one or15968WOO1 (013-0632PCT1) 50 PATENTmore of the synaptic circuits 334 that connect the neurons 326, the weights applied by one or more of the neurons 326, and / or the mathematical relationships between the neurons 326. For example, some synaptic circuits 334 can be changed to modified synaptic circuits 334’ such that the same input 336 would result in different neurons 326 receiving input and passing output to other neurons and generating a different output 338’ from the ANN 320. While in the example the input is sensor data and the output is a patient health condition, in other examples the input can be a previous question, set of questions, answer, etc. of a user along with accompanying answer, recommendation, questions, set of questions, etc. provided to a clinician and the output can be an input from a clinician regarding whether the answer, recommendation, question, set of questions, etc. (e.g., output) was satisfactory. If a previous output was satisfactory, a reward, or more weight, can be given for that output, while if not satisfactory, no reward, or less weight can be provided to the output. In one example, for the set of questions relevance metrics can be associated with one or more questions related to the ANN 320 analysis. In an example relevance metrics can include applying occurrence metrics to weight individual question relevance calculations. By providing the weights, or rewards, to each individual question, the relevance metrics can be used to generate outputs using the ANN 320.

[0102] After training the ANN 320, the ANN 320 can use the trained model to predict future outputs. During post-training iterations of operation of the ANN 320, additional feedback can be provided to the ANN 320 based on differences15968WOO1 (013-0632PCT1) 51 PATENTbetween the predicted and provided outputs and what occurred or was considered acceptable. For example, after training, the ANN 329 can receive additional patient sensor data, patient inputs, clinician inputs, etc., and predict outputs for a forward prediction window. As time progresses into the forward prediction window, the outputs and results can be compared to the predicted outputs to identify errors. These errors can again be input into the ANN 320 to continue to change the synaptic circuits 334, 334’, neurons 326, mathematical relationships, etc. to further refine and improve the model for use in continuing to increase the accuracy of answers to one or more questions, answers to a set of questions, diagnosis, treatments, recommendations, or the like. For example, the ANN 320 may be trained and re-trained using backpropagation, which can involve adjusting model parameters (e.g., synaptic circuits 334 and / or weights) using calculated derivatives to minimize the loss function (e.g., the error). The backpropagation can be a mathematical calculation for supervised learning of the ANN 320 using gradient descent. Backpropagation can be used to calculate the gradient of the error function with respect to the weights of the ANN 320. By continuously updating and improving outputs, the clinic platform, and associated computing devices operate more efficiently than a general-purpose computer, improving the computing devices.

[0103] In other implementations, the data analytics platform 320 may be configured to train various AI / ML-based models, computational models, or decision engines for purposes of some example embodiments of the present15968WOO1 (013-0632PCT1) 52 PATENTpatent disclosure. In an example the data analytics platform can select between one or more of the models or criteria for a VC session based on patient input. In one example the patient data can include patient demographic data. In another example a clinician can have access to a library of pre-defined patient questions, patient models, and mapping definitions for selection to conduct one or more VC sessions. In an example the library can be within a memory of a clinician electronic device, or within a memory of a server and communicated to the clinician over a network.

[0104] Various supervised and unsupervised learning and / or reinforcement techniques such as support vector machines (SVMs), support vector networks (SVNs), Naive Bayes (NB), neural networks (e.g., ANNs / CNNs), k-nearest neighbor, decision tree (DT), back-propagation neural network (BPNN), support vector regression (SVR), multiple linear regression (MLR), partial least square (PLS), k-Means, hierarchical algorithm (HA), mean-shift, density-based spatial clustering of application with noise (DBSCAN), feature selection, feature extraction, Q-learning, temporal difference, value iteration, and / or Markov decision processing. Additional details regarding AI / ML and computation models for medical applications can be found in Computers in Biology and Medicine, Volume 145, June 2022, 105458, by Mohammad Shehab et al. which is incorporated herein by reference.15968WOO1 (013-0632PCT1) 53 PATENT

[0105] For example, an SVM may be provided as a supervised learning model with associated learning algorithms that analyze data and recognize patterns that may be used for multivariate classification, regression analysis, and similar techniques. Given example training datasets (e.g., a training dataset developed from a preprocessed database or imported from some other previously developed databases), each marked as belonging to one or more categories, an SVM training methodology may be configured to build a model that assigns new examples into one category or another, making it a non-probabilistic binary linear (or non-linear) classifier in a binary classification model. An SVN may be considered as a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible (i.e., maximal separation). New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall on. In addition to performing linear classification, SVMs can also be configured to perform a non-linear classification using what may be referred to as the “kernel trick”, implicitly mapping their inputs into high-dimensional feature spaces.

[0106] In a multiclass SVM, classification may typically be reduced (i.e., “decomposed”) to a plurality of multiple binary classification models. Typical approaches to decompose a single multiclass scheme may include, e.g., (i) one-versus-rest classifications; (ii) one-versus-one pair-wise classifications; (iii) directed acyclic graphs; and (iv) error-correcting output codes.15968WOO1 (013-0632PCT1) 54 PATENT

[0107] In some arrangements, supervised learning may comprise a type of machine learning that involves training a predictive model based on decision trees built from a training sample to go from observations about a plurality of features or attributes and separating the members of the training sample in an optimal manner according to one or more predefined features. Tree models where a target variable can take a discrete set of values are referred to as classification trees, with terminal nodes or leaves representing class labels and nodal branches representing conjunctions of features and thresholds that indicate the most likely class labels. In some other arrangements, an embodiment of the present patent disclosure may advantageously employ supervised learning that involves ensemble techniques where more than one decision tree (typically, a large set of decision trees) are computed. In one variation, a boosted tree technique may be employed by incrementally building an ensemble by training each tree instance to emphasize the training instances previously mis-modeled or mis-classified. In another variation, bootstrap aggregated (i.e., “bagged”) tree technique may be employed that builds multiple decision trees by repeatedly resampling training data with or without replacement of a randomly selected feature. Accordingly, some example embodiments of the present patent disclosure may involve a Gradient Boosted Tree (GBT) ensemble of a plurality of regression trees and / or a Random Forest (RF) ensemble of a plurality of classification trees, e.g., in patient health score classification and modeling.15968WOO1 (013-0632PCT1) 55 PATENT

[0108] In some arrangements, video-, audio-, and / or sensing-based analytics and associated ML-based techniques effectuated using one or more constituent components of the digital health infrastructure 312 may provide valuable insights with respect to the diagnosis / or prognosis of individual patients Some of the patient conditions may depend on the context (e.g., time of day, activity type, psychological / emotional conditions of the patient, etc.) such that a generalized ML model may not be sufficiently accurate for predictive purposes in a particular setting. Some example embodiments herein may therefore relate to a scheme for rapidly collecting relevant patient data and analyzing / manipulating the data for generating suitable training datasets with respect to select ML-based models using an accelerated inference approach. In some embodiments, context information is gathered passively or through patient self-reporting. In some embodiments, context information may be gathered prior to, immediately before, or at the initiation of a remote virtual clinic session. Such context information may be used for AI / ML processing of patient condition as discussed herein.

[0109] Patient data can be processed to correlate patient states and / or physiological conditions to patient activities (e.g., sleeping, eating, working, exercising, etc.). An example of such automated analysis of patient activity is described in U. S. Patent No. 11,577,081 (the ‘081 patent) which is incorporated herein by reference. Although the ‘081 describes analysis of patient activities for the purpose of controlling a neurostimulation system, similar processing of patient activities may be employed to manage patients with or without implantable medical15968WOO1 (013-0632PCT1) 56 PATENTdevices. As shown in FIG. 4, patient conditions, physiological states, measured analyte levels, medical responses, and / or the like (e.g., patient data levels 401 and 402 plotted in time) may be correlated to patient activities.

[0110] As described in the ‘081 patent, activities of the patient are monitored and detected using one or more sensors of an implantable device or an external device. The sensors may include sensors for sensing physiological conditions, sensors for detection movement or location, and / or any other suitable sensors. In one example, the VC cloud telehealth system 300 can conduct diagnostic operations to obtain patient data from the sensors. In one example, the diagnostic operations can include at least one set of operations including performing impedance measures of electrodes of one or more stimulation leads or performing stimulation lead migration measurements. In some embodiments, an activity profile for the patient is determined that represents expected times when the patient will engage in a plurality of different activities of the patient.

[0111] As described in the ‘081 patent, patient activity may be detected using location determining circuitry and location-based algorithms to correlate location to activity. Microlocation processing algorithms may be employed to determine patient activity within the patient's domicile as one example. The monitoring of activities of a patient may include repetitively detecting a location of the patient using location determining circuitry of the external device of the patient. The circuitry for location-based activity tracking may include cellular15968WOO1 (013-0632PCT1) 57 PATENTcommunication circuitry, WiFi circuitry, and Bluetooth circuitry. Location-based activity detection may include detecting an amount of time spent at an identified location.

[0112] As described in the ‘081 patent, further, monitoring activities of the patient may comprise obtaining data pertaining to physiological signals of the patient using a wearable device or an implanted device. The physiological signals may include heart rate data, electrocardiogram data, a sleep quality data, body temperature data, blood oxygen saturation data, blood glucose data, other measured analyte levels, and / or any other measured physiological-related data.

[0113] As described in the ‘081 patent, an external controller or other user device may receive user input from the patient by the external controller that is indicative of patient activities being performed by the patient. The patient may provide user input by selecting respective ones of activity icons displayed on or more user interface screens where each respective icon represents a distinct patient activity. The user interface screen(s) may receive input from the user indicative of ease or difficulty for the patient in performing a respective activity. Also, the user interface(s) may receive input from the user indicative of one or more patient states (e.g., a wellness level, an overall “energy” level, a level of pain experienced by the patient at a respective point in time, etc.).

[0114] As described in the ‘081 patent, based on receipt of some or all of such information as described in the ‘081 patent, a patient activity profile is15968WOO1 (013-0632PCT1) 58 PATENTgenerated from the activity data collected from the implanted and / or external devices of the patient. In some embodiments, the patient activity data is communicated to a remote care management system, wherein the remote care management system determines the activity profile for the patient. The remote care management system may perform an averaging calculation of observed times for patient activities of the activity profile; calculate average start times of respective activities for the activity profile; may calculate average end times of respective activities for the activity profile; apply a calculation of frequency of performance of activities to determine the activity profile; and / or apply an averaging calculation to determine average duration of activities for the activity profile. Such suitable processing of patient activity data into activity metrics may be employed to create a patient activity profile.

[0115] As previously discussed, telehealth services and virtual clinic services provide medical services to patients while patients and attending clinicians are physically located at separate locations. In one example, chatbot functionality can be integrated with telehealth services (such as provision of answers to “frequently asked questions” (e.g., set of questions) via chatbot functionality). A chatbot is a computer program that simulates conversation with an end user. Examples of application programming interfaces (APIs) useful for chatbot development include Watsonx Assistant (IBM), DialogFlow API (Google), Bot Framework (Microsoft), OpenAI API (OpenAI), and Wit.ai API (Wit.ai) among many others. Many chatbots employ artificial intelligence (Al) algorithms such as15968WOO1 (013-0632PCT1) 59 PATENTnatural language processing (NLP) to process and analyze user input or prompts and automate responses to them.

[0116] FIG. 5 depicts a flowchart for conducting operations for a telehealth consultation or virtual clinic (VC) session according to some representative embodiments. Figures 6A and 6B illustrate example VC cloud telehealth systems 600 that may be utilized to perform at least one or more of the functions and / or steps associated with the method of FIG. 5 depicted.

[0117] The VC cloud telehealth system 600 can be configured to provide medical services for a clinician and patient and can include a patient electronic device 612 that includes a patient interface 614, an analysis system 616, and a clinician electronic device 618 that includes a clinician interface 620. In examples the patient interface 614 and clinician interface 620 can each be a touch screen, or display. In other examples the patient interface 614 or clinician interface can include a keyboard, mouse, input device, microphone, or the like.

[0118] With reference to FIG. 6B, in one example the analysis system 616 can include one or more servers 622 that can include one or more server processors 624, a server memory 626, a telemetry circuit 628 that forms a first communication connection over a network 630 with the patient electronic device 612 and a second communication connection over the network 630 with the clinician electronic device 618. In one example, the one or more servers 622 are considered to be within a so-called cloud environment.15968WOO1 (013-0632PCT1) 60 PATENT

[0119] The first communication connection between the patient electronic device 612 and the one or more servers 622 and the second communication connection between the one or more servers 622 and the clinician electronic device 618 forms a communication pathway between a patient and clinician over the network 630. While in one example the communication connection between the patient electronic device 612 and one or more servers 622 is considered a first communication connection, and the communication connection between the one or more servers 622 and clinician electronic device 618 is considered a second communication connection, in other example embodiments, the communication connection between the patient electronic device 612 and one or more servers 622 can be considered a second communication connection, and the communication connection between the one or more servers 622 and the clinician electronic device 618 can be considered a third communication connection. For example, in one example a first communication connection can be provided between the patient electronic device 612 and an IMD such as an implantable pulse generator (IPG).

[0120] By having the servers located remote from the patient electronic device 612 and clinician electronic device 618, processing, memory space, etc. of each of the patient electronic device 612 and clinician electronic device 618 are saved, improving the functionality of each. In addition, by having one or more servers 622 performing the determinations, calculations, analysis, defining of models, or the like (e.g., the analysis), the efficiency of the servers and server Al15968WOO1 (013-0632PCT1) 61 PATENTapplication 634 can be improved. For example, by having all of the analysis done at the one or more servers 622, the one or more servers 622 can communicate over the network 630 using communication connections with thousands, or more, patient electronic devices 612 and clinician electronic devices 618 resulting in increased learning by the Al application 634. In one example, every interaction involving the servers between a patient electronic device 612 and a clinician electronic device results in updating and improving relevance metrics generated by the Al application 634. For example, the Al application 634 can apply occurrence metrics to weight individual question relevance calculations in making determinations regarding an output to provide for a clinician electronic device 618.

[0121] The servers 622 can also include a server telehealth application 632 and server artificial intelligence (Al) application 634 that each can provide instructions for the one or more processors of the servers to obtain patient inputs, define sets of questions, define, generate, select, and update patient models, make determinations, analyze data and information, or the like. In one example the server telehealth application 632 and Al application are configured to provide instructions to cause a patient electronic device 612 chat bot functionality where a patient may provide inputs, including audible inputs, into a chat bot, and receive outputs from the chat bot. In one example the server telehealth application 632 and Al application 634 are configured to conduct a pre-VC session interview of the patient with the chat bot by providing a prompt or receiving input on the patient interface 614, obtaining input data provided by the patient or patient electronic15968WOO1 (013-0632PCT1) 62 PATENTdevice, analyzing the input data using defined patient models, and providing an output at the patient electronic device 612 accordingly.

[0122] In one example, a clinician can utilize the clinician electronic device 618 to access a library in the server memory 626, or in the clinician memory 650. In an example, the library can include pre-defined patient questions, patient models, mapping definitions, etc. The clinician can then select the patient questions, patient models, mapping definitions, or the like to conduct one or more VC sessions. By allowing the clinician to make the selection, the pre-VC session can be customized for the clinician, improving results of the pre-VC session.

[0123] In one example the output at the patient electronic device 612 can be on the patient interface 614. Alternatively, the output at the patient electronic device 612 can be auditory, a combination of on the patient interface 614 and auditory, or the like. In one example, mapping definitions can be defined between questions of one or more sets of pre-VC session interview questions to respective entries in multiple patient models. In an example the one or more processors can select between one or more VC session models or criteria for a VC session based on patient input. In one example the patient data can include patient demographic data, answers to certain questions, or the like. In one example, one or more entries of the patient models comprises at least one entry related to the condition of a patient's implantable medical device. In another example the patient models can include entries related to physiological states of a patient. Physiological states can15968WOO1 (013-0632PCT1) 63 PATENTinclude health of an organ, system, body part, or the like of a patient. Physiological states can be provided as auditory statements or manually input by a patient at a patient device 635. In one example, physiological states can be based on sensor data. In an example, the sensor data can be from a wearable patient device and utilized to evaluate entries related to physiological states of the patient.

[0124] The patient electronic device 612 may also include one or more patient processors 636, patient memory 638, patient telemetry circuit 640, patient telehealth application 642, and patient Al application 644. In one example, the patient telehealth application 642, and patient Al application 644 can be configured to perform part of or all of the functions of the server telehealth application 632 and the server Al application 634. In one example, from time to time, the patient electronic device can receive an updated Al algorithm from the one or more servers 622 and in response to the network 630 being unavailable or having low connectivity can perform one or more of the steps commonly performed by the one or more servers 622, including chat bot functionality.

[0125] In an example, the patient electronic device 612 can also include one or more sensors 646 or be in communication with one or more sensors 646 that can obtain patient input data. In an example a sensor 646 can be a thermometer, heart rate sensor, blood pressure sensor, or the like. In another example, the one or more sensors 646 can be external from the patient electronic device and associated with an implantable medical device (IMD). In the example,15968WOO1 (013-0632PCT1) 64 PATENTthe IMD can communicate patient input data, readings, signals, or the like to the patient electronic device 612 for communicating with the rest of the VC cloud telehealth system 600 for analysis. In another example, a sensor 646 can be a microphone that receives auditory signals and input from a patient, including spoken words and responses. The patient telehealth application 642 or server telehealth application can convert the audible signals into data or information that can be processed for chat bot functionality. In one example, the patient interface 614 can function as an interface where the patient can input data and information that can be utilized by the patient telehealth application 642 or server telehealth application 632. In one example, the VC cloud telehealth system 600 can conduct diagnostic operations to obtain patient data from the sensors. In one example, the diagnostic operations can include at least one set of operations including performing impedance measures of electrodes of one or more stimulation leads or performing stimulation lead migration measurements.

[0126] The clinician electronic device 618 may also include one or more clinician processors 648, clinician memory 650, clinician telemetry circuit 652, clinician telehealth application 654, and clinician Al application 656. In one example, the clinician telehealth application 654, and clinician Al application 656 can be configured to perform part of or all of the functions of the server telehealth application 632 and the server Al application 634. In one example, from time to time, the clinician electronic device can receive an updated Al algorithm from the one or more servers 622 and in response to the network 630 being unavailable or15968WOO1 (013-0632PCT1) 65 PATENThaving low connectivity can perform one or more of the steps commonly performed by the one or more servers 622, including chat bot functionality. In one example the clinician electronic device provides chat bot functionality similar to that described in relation to the patient electronic device with the clinician providing the inputs instead of the patient.

[0127] The clinician electronic device 618 can also include one or more clinician sensors 658 configured to obtain data or information from a clinician. In one example at least one clinician sensor 658 can be a microphone that receives auditory signals and input from a clinician, including spoken words. The clinician telehealth application 654 or server telehealth application can convert the audible signals into data or information that can be processed for analysis. In one example, the clinician interface 620 can function as an interface where the clinician can input data and information that can be utilized by the clinician telehealth application 654 or server telehealth application 632. In another example the clinician electronic device can be in communication with a patient device 635, such as an IMD to obtain patient data that can be communicated to other electronic devices, servers, components, etc. of the VC cloud telehealth system 600.

[0128] With reference back to FIG. 5, at 501, in real-time one or more processors define at least one set or series of clinician questions to be presented to a patient before initiation of a VC session with a clinician. Multiple sets or series of questions can be defined depending upon a patient’s initial indication of the15968WOO1 (013-0632PCT1) 66 PATENTreasons for the patient’s consultation. With reference to FIG. 6A, in one example a set of questions 601 can be defined for use by Telehealth / Virtual Clinic Infrastructure 610 in VC cloud telehealth system 600. In one example the Telehealth / Virtual Clinic Infrastructure is at the one or more servers 622. In some embodiments, the set or series of questions are predefined for selection by a clinician for the individual clinician’s VC sessions. In other embodiments, clinicians may alternatively or additionally define their own questions to be presented to patients. In some embodiments, VC cloud telehealth system 600 is implemented for a specific medical practice involving patients with a limited set of conditions or disorders. Alternatively, VC cloud telehealth system 600 may be a general system for providing virtual clinic sessions to patients seeking medical guidance for a wide variety of conditions or purposes. The range of a set of questions 601 defined for such respective systems will depend upon the types of patients and the various conditions of the patients to be addressed in the VC sessions.

[0129] With reference back to FIG. 5, at 502, one or more processors can define patient models (602). With reference to FIG. 6A, the patient models 602 are constructed to calculate probability of the cause of patient complaint, to diagnose the patient, to facilitate identification of patient treatment, to facilitate program ing of the patient’s medical device(s), and / or the like. The range of patient models to be defined may depend upon the types of patients and the various conditions of the patients subject to the VC sessions. An example patient model 602 is illustrated in greater detail in FIG. 7.15968WOO1 (013-0632PCT1) 67 PATENT

[0130] With reference back to FIG. 5, at 503, one or more processors obtain patient information and input. In one example, a pre-VC session patient interview is conducted using a chatbot module of a VC system. Alternatively, a questionnaire, survey, checklist, other manual inputs, or the like may be completed and entered by a patient at an interface or display (See FIGS. 6A-6B) of a patient electronic device. In response to obtaining the patient input provided during the pre-VC session patient interview, or provided manually, the one or more processors define mapping definitions between questions of the one or more sets of pre-VC session interview questions or questionnaires to respective entries in the multiple patient models. In one example the entries can then be provided to a clinician electronic device for display and / or use. In an example, one or more entries can include at least one entry related to a condition of a patient's implantable medical device.

[0131] FIG. 6A illustrates an example embodiment where the VC cloud telehealth system 600 includes a chatbot module 603 configured to obtain auditory input from a patient. In one example the auditory input can be obtained from a sensor such as a microphone of a patient electronic device. The patient interview preferably occurs by presenting the defined questions, or set of questions, to the patient. In one example, the chatbot module 603 can record the patient response(s) for further analysis, mapping, etc. as discussed herein.15968WOO1 (013-0632PCT1) 68 PATENT

[0132] With reference back to FIG. 5, at 504, the one or more processors create a pre-VC session interview summary. In one example the pre-VC session interview summary can be created using chatbot functionality. The interview summary may be displayed on the clinician electronic device to be reviewed by a clinician before initiating interaction with the patient during the VC session. In one example the interview summary can be transmitted as a downloadable along with a set of questions to a clinician electronic device. The clinician can then download the summary for review while also reviewing the set of questions. The summary may allow the clinician to gather insight into the patient’s condition to allow the clinician to efficiently and effectively conduct the VC session to address the patient’s needs within time constraints imposed upon the clinician by conventions of medical practice.

[0133] At 505, in real-time, one or more processors utilize patient model(s) 602 to calculate most probative or efficient follow-up question(s), set of questions, or action(s) to arrive at diagnosis, session resolution, or other appropriate clinical action. In one example the one or more server processors utilize the patient model(s) 602 based on instructions from the server telehealth application 632. As information is received from patient data stored on one or more respective databases, files, etc., sensor data or test data, the pre-VC chatbot interview, and subsequent questions or observations from the clinician, the yet unanswered questions / issues with the greatest probabilities of relevance from the various applicable models may be identified and presented to the clinician. In one example15968WOO1 (013-0632PCT1) 69 PATENTthe relevance metrics are determined, including by applying occurrence metrics to weight individual question relevance. In this context, “relevance” may be calculated as the entry in the patient models that will cause a greatest increase in probability of a patient condition if identified to a physiological state. Also, the “relevance” may be further modified by an overall probability of the patient model itself. For example, suppose a specific patient condition (if identified) causes a patient model to increase in probability by 40% but that patient condition only occurs in 5% of patients. In such circumstances, the 40% marginal probability increase may be reduced by the 5% incidence rate to allow for a more efficient process of conducting the clinical session for the patient. Further, the probabilities may be defined in terms of conditional probabilities. That is, the probability of a specific patient condition data leading to a diagnosis or other clinician decision may be dependent on other patient data. Such conditional probabilities may be defined using Bayesian-probability models as an example. In another example, instead of a patient condition, determinations can be made related to medical responses, including medical responses to treatments provided over time. Again, probabilities related to certain medical responses to given treatments can be ascertained and reflected in one or more patient models.

[0134] The clinician may then ask an additional question, request the patient to complete a physical task for observation (e.g., walking, finger tapping, specific joint-movement, etc.), review additional sensor and / or video data, and / or the like to obtain additional patient condition data (based on the identified follow-15968WOO1 (013-0632PCT1) 70 PATENTup question(s) or actions), medical response data, or otherwise at the clinician’s discretion. In one example, the addition questions or requests may be input manually into the clinician interface, provided auditorily to a clinician sensor such as a microphone, or the like. The patient data may be captured automatically or entered by the clinician or the patient into one or more suitable applications accordingly. The captured patient data then is used to dynamically update the VC session by reapplying the patient modeling analysis (see 505).

[0135] FIG. 7 depicts patient models 602 adapted for a VC session for chronic pain patients with an implantable pulse generator system according to some embodiments. In FIG. 7, it is assumed that the patient is contacting the patient’s clinician(s) because the patient is experiencing an increased level of pain. The increased level of pain may be the result of one or more different factors which may be addressed by one or more clinical responses.

[0136] For example, for model 701, the clinician may attempt to reprogram the active electrodes for the patient. That is, the current active electrodes of the patient may not be stimulating the most appropriate dorsal column fibers, and a different set of electrodes will, in turn, stimulate different dorsal column fibers and thereby achieve greater response of the SCS therapy. Reprogramming active electrodes may be appropriate when lead migration has occurred. Alternatively, change in a patient’s neuropathic pain condition may necessitate changing the active electrodes.15968WOO1 (013-0632PCT1) 71 PATENT

[0137] For model 702, the clinical response is reprogramming stimulation power parameters. The active electrodes for the patient may be optimal but the patient response to stimulation can still be improved. In certain cases, the clinician may attempt to reprogram power parameters. For example, stimulation amplitude, pulse width, frequency, and / or duty cycle parameters (as examples) may be modified to optimize the patient response to the SCS or other neurostimulation therapy.

[0138] For model 703, other clinical tasks (other than device-specific tasks) may be the appropriate clinical response. Chronic pain is a complicated disorder and an increase in patient pain may occur even while stimulation parameters and active electrodes are optimized. In such cases, the clinical response may involve identifying a secondary cause for the increase in patient and addressing that specific cause. For example, the patient may have experienced recent injury or trauma which has aggregated the patient’s pain. In such circumstances, reprogramming might not improve the patient’s condition. Temporary pharmaceutical therapy and / or physical therapy may be appropriate for this case. Also, it is known that psychological factors and lifestyle factors have a significant impact on a patient’s perception of pain. Alternatively, other medical conditions can contribute to chronic pain which can be detected by blood work and / or other suitable medical testing.15968WOO1 (013-0632PCT1) 72 PATENT

[0139] Each model includes respective entries that, if present, increase the probability or the respective clinical task in improving the patient condition, or medical response to treatment of the patient condition. For example, for patient model 701, the following entries are defined: impedance change; lead migration; expanded perception of pain; change in pain location; frequent and stimulation program settings. For patient model 702, respective entries are defined for: lack of impedance change; lack of lead migration; lack of expanded perception of pain; lack of change in pain location; repeated amplitude adjustments by patient; increased perception of burning / needle-type pain; and periods of adequate pain relief followed by intermittent increased pain. For patient model 703, respective entries are defined for: - recent injury / trauma; change in sleep patterns; change in appetite / diet; increased anxiety, depression, catastrophizing; stressful life event; and relevant results for blood work / medical testing.

[0140] Each entry of the respective patient models is provided with a metric (see metrics A1-A5, B1-B7, and C1-C6) that relates the relevance of the specific entry to the overall patient model. As previously discussed, the metric may be a probability, a conditional-probability, weighting factor, and / or the like. The exact form of the metrics is not critical so long as the entire set of metrics (A1-A5, B1-B7, and C1-C6) for the various models 701-703 are defined consistently such that relative comparisons between models 701-703 can be made as clinical evaluation while a VC is ongoing. Additionally, each model includes an occurrence rate metric (shown as OR1, OR2, and OR3) that defines the relative occurrence of15968WOO1 (013-0632PCT1) 73 PATENTeach respective patient model as being the appropriate clinical response. In an example the one or more processors can select between one or more of the models during a VC session based on patient input. In one example the patient data can include patient demographic data.

[0141] FIG. 8 depicts chatbot pre-VC session chatbot interview questions 601 according to some representative embodiments. Pre-VC session chatbot interview questions 601 may include one or more open-ended questions that allows a patient to describe in freeform the specific issues or problems that the patient is experiencing (e.g., “WHAT IS YOUR REASON FOR VC VISIT?). Selection questions may be included within questions 601 to be mapped to specific entries in patient models 602 (e.g., “DO YOU HAVE INCREASED PERCEPTION OF PAIN?”, “HAVE YOU EXPERIENCED INEFFECTIVE OR LOW PAIN RELIEF?”, “HAVE YOU EXPERIENCED INTERMITTENT EXPERIENCE OF PAIN?”, “DO YOU HAVE SIDE EFFECTS DURING STIMULATION?”, etc ). Depending upon the CHATBOT functionality processing of the patient responses, the patient states for these entries may automatically update before initiation of the VC session with the clinician.

[0142] Pre-VC session chatbot interview questions 601 may include selected hierarchical questions that depend on prior questions and answers by the patient. For example, the pre-VC session chatbot interview process may present the following question to the patient: “DO YOU HAVE SIDE EFFECTS DURING15968WOO1 (013-0632PCT1) 74 PATENTSTIMULATION?" If answered yes in any suitable manner, the pre-VC session chatbot interview process may automatically prompt the patient for additional details regarding side effects such as “buzzing, burning, needle, or similar unpleasant sensations during stimulation?”, “can't sleep during stimulation?”, “difficulties eating or with speech during stimulation?”, “other side effects?”, and / or the like.

[0143] The pre-VC session chatbot interview may inquire regarding nonmedical issues such as the operation of the patient’s medical device(s) such as “ARE YOU EXPERIENCING TECHNICAL PROBLEMS WITH YOUR SYSTEM?,” “can’t charge device?”, “difficulties with communication connection to device?”, “can’t operate patient controller app effectively or properly?”, and / or the like. These questions may be organized in a hierarchical structure as well. The answers to these questions and / or possibly other questions may determine the type of professional to interact with the patient during the VC session. For example, if the patient is not experiencing medical issues but only technical issues, appropriate technical helpdesk personnel may be selected for the VC session as opposed to a doctor or other medical professional.

[0144] As previously discussed in regard to FIG. 3, device programming, patient / clinician interaction, and patient responses to therapy may be aggregated (see discussion of PAD 350 including “Remote Programming Event Data”) to manage to train computational models for implantable medical device15968WOO1 (013-0632PCT1) 75 PATENTprogramming and / or other patient management purposes. Additionally, U. S. Pat. App. Pub. No. 2022 / 0184405 (which is incorporated herein by reference) discloses a remote program ming / virtual clinic system in which "data labeling" of events in a remote programming session are labeled to facilitate machine learning / computational model training among other operations.

[0145] FIG. 9 illustrates a method for scheduling a VC session and communicating the same. In one example a patient desires to schedule VC session with a clinician through the VC cloud telehealth system using a patient telehealth application. At 901, in real-time one or more processors calculate an estimated time for the VC session. In one example patient data and prior programming history can be analyzed to determine the estimated time. For example, if the patient has previously has ten VC session, the time of each of last ten sessions can be averaged as part of the estimation process. At 902, the one or more processors then schedule the VC session and provide the estimate time calculated for review by the clinician. Alternatively, a clinician can provide a selected amount of time. In one example a clinician may decide the longest they desire for any VC session to last is thirty minutes and select that every VC session to last thirty minutes.

[0146] At 903, the patient initiates the VC session. In one example pre-VC session begins with the patient inputting patient data into the patient electronic device. At this time, the patient electronic device may automatically begin15968WOO1 (013-0632PCT1) 76 PATENTobtaining and collecting patient data from sensors, including heart rate, blood pressure, or the like. Additionally, the patient can correspond with a chatbot, manually input patient data, including questions, or the like.

[0147] At 904, the one or more processors monitor the patient data and information being input into the patient electronic device, along with any and all data and information input by the clinician into a clinician electronic device. The one or more processors can analyze the patient data and clinician data with one or more models, patient models, or the like to address the health condition of the patient.

[0148] At 906, in real-time, as the one or more processor receive the patient and clinician inputs and analyze them with one or more models, the one or more processors update a clinician interface with timer information. For example, if a VC session is originally scheduled for thirty minutes, the one or more processors can provide on the interface the amount of time left in the thirty-minute VC session. Instead of simply counting down the time with a timer, the one or more processors determine the amount of time left to complete the VC session. In some examples, the amount of time remaining will be less than the amount of time allotted for the VC session. Alternatively, the amount of time remaining may be greater than the amount of time remaining during the allotted time (e.g., 30 minutes). In such examples, by showing on the interface the amount of time needed still to complete the VC session, the clinician can begin taking steps to speed up the process or15968WOO1 (013-0632PCT1) 77 PATENTmake a determination that the VC session is taking too long and needs to be rescheduled.

[0149] At 906, in real-time the one or more processors can also determine the probability of a successful and timely conclusion in the remaining time and at 907 can output the probability on the clinician interface. For example, if based on determination the amount of time for completion is twenty minutes, and only eighteen minutes remain in the session, the probability could be determined as a 90% probability that a successful and timely conclusion results. Whereas if the amount of time from completing is twenty minutes, and only ten minutes remain, the probability that a successful and timely conclusion results may only be 5%. By providing this additional information, the clinician can make determinations related to whether to continue the session, reschedule, ask the patient to come in for a visit, or the like so that other patients can also be seen in a timely manner. By providing the real-time updates and probabilities, the clinician has more information and control for setting expectations for a clinician and keeping the schedule of the clinician up to date without unnecessary delays.

[0150] In some embodiments, events from virtual clinic / remote programming sessions are monitored and used to create, develop, and / or train one or more computational or other models to predict successful conclusion of virtual clinic / remote programming sessions. FIG. 10 depicts operations to create, develop, and / or train one or more computational or other models to predict15968WOO1 (013-0632PCT1) 78 PATENTsuccessful (or equivalently unsuccessful) conclusion of virtual clinic / remote programming sessions.

[0151] In 1001, remote programming sessions are monitored to generate aggregated programming session data (e.g., using the computing system(s) and electronic devices shown in FIGS. 2, 3A, 3B, 6A, 6B). In 1002, a session total time data set is identified or generated for successful / unsuccessful programming sessions. In 1003, a session data set is identified or generated of programming time for successful / unsuccessful programming sessions. In 1004, a session data set of number of electrode combinations is identified or generated for successful / unsuccessful programming sessions. In 1005, a session data set is identified or generated of number of independent power parameters for successful / unsuccessful programming sessions.

[0152] In 1006, a session data set is identified or generated of unexpected side effects for successful / unsuccessful programming sessions. In 1007, a session data set is identified or generated of prior programming session times for respective patients for successful / unsuccessful programming sessions.

[0153] In 1008, the session data is processed by patient demographic and / or relevant subpopulation groups to develop one or more models of remote programming sessions using identified and / or processed session data. The purpose of the one or more models is to predict the probability of successful outcome (or equivalently not achieving a successful outcome) in a remote15968WOO1 (013-0632PCT1) 79 PATENTprogramming session given an allotted amount of time. The one or more models may be used to predict such an outcome dynamically as a given remote programming session proceeds. The one or more models may be used to predict such an outcome when selecting a session time (e.g., 10 minutes, 15 minutes, 30 minutes, etc.). Alternatively, the prediction of such an outcome may be used to select between initiation of a virtual clinic session or omitting the virtual clinic session and replacing it with an in-person clinical appointment. Further, the prediction of such an outcome may vary upon the demographics and / or medical background of the patient (as detailed in, e.g., PAD 350) and / or the specific patient complaint that the patient is experiencing (e.g., as identified by a chatbot pre-VC session interview).

[0154] By developing one or more models in this manner, remote programming sessions may be scheduled in a more efficient manner, personnel for sessions may be selected in a more accurate manner, wasted time spent pursuing unlikely or unfruitful outcomes in session may be avoided, among other potential benefits. In one example, in response to a determination that the remote programming session will not be successful in the time allotted, the analysis using an analytics platform can be terminated to reduce the wear on the hardware of the system and decrease the energy used.

[0155] A number of techniques may be applied to generate or develop the one or more models. Various supervised and unsupervised learning and / or15968WOO1 (013-0632PCT1) 80 PATENTreinforcement techniques such as support vector machines (SVMs), support vector networks (SVNs), Naive Bayes (NB), neural networks (e.g., ANNs / CNNs), k-nearest neighbor, decision tree (DT), back-propagation neural network (BPNN), support vector regression (SVR), multiple linear regression (MLR), partial least square (PLS), k-Means, hierarchical algorithm (HA), mean-shift, density-based spatial clustering of application with noise (DBSCAN), feature selection, feature extraction, Q-learning, temporal difference, value iteration, and / or Markov decision processing. Additional details regarding AI / ML and computation models for medical applications can be found in Computers in Biology and Medicine, Volume 145, June 2022, 105458, by Mohammad Shehab et al. which is incorporated herein by reference.

[0156] In some embodiments, a basic (linear) single-layer neural network is employed to model a remote programming session for successful (or unsuccessful) conclusion based on an allotted amount or remaining amount of time. As previously discussed, multiple models may be created by segmenting patient populations by demographic information, by patient history, by current compliant, disorder, or other medical issue. The training of such models may occur using the data sets described herein obtained from history log data from remote programming sessions. Since a single-layer neural network is employed, identifying the hidden layer coefficients of the neural network is less computationally extensive than other models. However, more complicated neural networks may be employed - such as selecting additional layers and / or more15968WOO1 (013-0632PCT1) 81 PATENTcomplex activation functions for nodes of the network. Although artificial intelligence models may be employed according to some embodiments, other types of modeling may be employed. For example, linear regression models or other statistical models may be developed using the data sets available from history log data from remote programming sessions.

[0157] FIG. 11 depicts remote programming module 1100 for inclusion within a remote programming system for programming implantable medical devices. Remote programming module 1100 includes inputs 1101 to be obtained from an ongoing or to be initiated remote programming session. The inputs 1101 shown in FIG. 11 are by way of example and each of the inputs shown need not be included in all embodiments. Any combination of such inputs may be employed. Also, any other session and / or patient data may be employed. Relevant inputs for a remote programming session model from data from logs from remote programming session events for a population of patients may be subjected to feature importance evaluation (such as Random Forest feature importance analysis). Inputs 1101 are provided to remote programming session model 1102 which provides outcome prediction 1103. Outcome prediction 1103 may be selected in a number of forms. For example, outcome prediction 1103 may be defined in a Boolean manner (either likely to be successful or unlikely to be successful). Additionally or alternatively, outcome prediction 1103 may reflect a rough probability calculation of successful or unsuccessful conclusion (e.g., 75% probability of success).15968WOO1 (013-0632PCT1) 82 PATENT

[0158] FIG. 12 depicts operations associated with a remote programming session for a patient's implantable pulse generator according to some representative embodiments. Although multiple operations are shown in FIG. 12, all of the operations are not required. For example, a pre-interview calculation of success or estimated time may be omitted while in-session prediction may occur or vice versa. The performance of remote programming modeling may occur using one or more (in any combination) of the operations shown in FIG. 12 or otherwise described in this application.

[0159] In 1201, a patient logs onto or otherwise accesses remote programming system. In 1202, patient specific data is retrieved or obtained for the patient. In 1203, a pre-VC session inquiry. For example, as discussed herein, a chatbot interview may be conducted. Additionally or alternatively, the patient may complete electronic patient intake forms via the remote programming system interface to provide appropriate session information. In 1204, a relevant model for the VC session is selected based on patient data. For example, different models may be available based on patient demographics and / or patient compliant(s). For example, for spinal cord stimulation (SCS) therapies, different models may be available for foot pain, leg pain, low back pain, torso pain, arm and / or hand pain, trigeminal or occipital pain, peripheral diabetic neuropathy pain, as examples. In 1205, the relevant data is provided to remote programming session model. In 1206, the likely needed time for the VC session is estimated. For example, multiple VC session lengths (e.g., 10 minutes, 15 minutes, 30 minutes, etc.) may15968WOO1 (013-0632PCT1) 83 PATENTbe provided to the model and the lowest time that produces a likely successful outcome could be selected as the estimated time.

[0160] In 1207, the VC session is scheduled based on estimated time or clinician selected time. The VC session for this patient could be placed in a queue for the VC session if the estimated time matches any requirements for the queue. Alternatively, a specific clinician may be selected using, in part, the estimated time. For example, a specific clinician may only have a limited window of available times between appointments in view of the estimated time and the patient may be allowed to select between such times. In other embodiments, more difficult sessions (e.g., ones that might require longer times) may be provided for specific clinicians while other sessions may be provided for other clinicians.

[0161] In 1208, the VC session for the patient is initiated. In 1209, the remote programming system monitors ongoing events in programming session (e.g., via patient and / or clinician input via respective apps), automatic voice-to-text and analysis, automatic analysis of patient video, and / or the like. In 1210, updated data (e.g., the ongoing remote programming data) is provided to the selected remote programing model. In 1211, the remote programming system receives the outcome prediction from the model. In 1212, the clinician user interface is updated with prediction data using one or more session outcome prediction GUI components.15968WOO1 (013-0632PCT1) 84 PATENT

[0162] FIG. 13 depicts clinician user interface 1300 with outcome prediction GUI component 1301 according to some representative embodiments. Outcome prediction GUI component 1301 may include a timer which can show the amount of time elapsed since the initiation of the VC session and / or the amount of time remaining in the scheduled VC session. Outcome prediction GUI component 1301 includes a graphical icon (in this case, a "checkmark") indicative of the probability of successfully concluding the VC session with an appropriate outcome. Any suitable representation of the outcome prediction data may be provided (e.g., different colors as opposed to icons).

[0163] As the clinician conducts the VC session, the model may predict that a successful conclusion is unlikely. The representation of GUI component 1301 may change based on the change in VC session status. A different icon may be displayed. Also, multiple icons or indications may be used (e.g., green for likely successful outcome, yellow for possible unsuccessful outcome, and red for likely unsuccessful outcome).

[0164] In response to receiving such information via GUI component 1301, the clinician may make any number of decisions. For example, if time is running out, the clinician may switch techniques to provide the most likely changes or parameters to obtain a successful conclusion. Alternatively, the clinician may modify the VC session time to add additional time, and a new prediction can be provided based on the additional time. Still further, the clinician may decide that15968WOO1 (013-0632PCT1) 85 PATENTthe remote programming session is unlikely in the clinician's professional opinion to obtain the desired results. The clinician may then end the VC session, schedule a new VC session, schedule an in-person clinical visit, and / or the like. One particular relevant use case of such a workflow is to provide the clinician with insight into whether further programming attempts will likely result in a successful outcome.

[0165] For example, certain patients may have difficulty providing suitable feedback to the clinician after a certain period of time and / or programming changes. In such circumstances, the clinician might be unlikely to properly configure the patient's IPG program parameters even if additional time is added to the VC session (thereby taking time away from attending to other patients). In such a circumstance, the clinician may be able to avoid spending time on a clinical exercise that is unlikely to help this patient while reserving such time for other beneficial clinical tasks.Closing

[0166] It should be clearly understood that the various arrangements and processes broadly described and illustrated with respect to the Figures, and / or one or more individual components or elements of such arrangements and / or one or more process operations associated of such processes, can be employed independently from or together with one or more other components, elements and / or process operations described and illustrated herein. Accordingly, while15968WOO1 (013-0632PCT1) 86 PATENTvarious arrangements and processes are broadly contemplated, described and illustrated herein, it should be understood that they are provided merely in illustrative and non-restrictive fashion, and furthermore can be regarded as but mere examples of possible working environments in which one or more arrangements or processes may function or operate.

[0167] As will be appreciated by one skilled in the art, various aspects may be embodied as a system, method, or computer (device) program product. Accordingly, aspects may take the form of an entirely hardware embodiment or an embodiment including hardware and software that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects may take the form of a computer (device) program product embodied in one or more computer (device) readable storage medium(s) having computer (device) readable program code embodied thereon.

[0168] Any combination of one or more non-signal computer (device) readable medium(s) may be utilized. The non-signal medium may be a storage medium. A storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a storage medium would include the following: a portable computer diskette, a hard disk, a randomaccess memory (RAM), a dynamic random-access memory (DRAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash15968WOO1 (013-0632PCT1) 87 PATENTmemory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0169] Program code for conducting operations may be written in any combination of one or more programming languages. The program code may execute entirely on a single device, partly on a single device, as a stand-alone software package, partly on single device and partly on another device, or entirely on the other device. In some cases, the devices may be connected through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made through other devices (for example, through the Internet using an Internet Service Provider) or through a hard wire connection, such as over a USB connection. For example, a server having a first processor, a network interface, and a storage device for storing code may store the program code for conducting the operations and provide this code through its network interface via a network to a second device having a second processor for execution of the code on the second device.

[0170] Aspects are described herein with reference to the figures, which illustrate example methods, devices, and program products according to various example embodiments. The program instructions may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing device or information handling device to produce a machine, such15968WOO1 (013-0632PCT1) 88 PATENTthat the instructions, which execute via a processor of the device implement the functions / acts specified. The program instructions may also be stored in a device readable medium that can direct a device to function in a particular manner, such that the instructions stored in the device readable medium produce an article of manufacture including instructions which implement the function / act specified. The program instructions may also be loaded onto a device to cause a series of operational steps to be performed on the device to produce a device implemented process such that the instructions which execute on the device provide processes for implementing the functions / acts specified.

[0171] The units / modules / applications herein may include any processorbased or microprocessor-based system including systems using microcontrollers, reduced instruction set computers (RISC), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), logic circuits, and any other circuit or processor capable of executing the functions described herein. Additionally, or alternatively, the modules / controllers herein may represent circuit modules that may be implemented as hardware with associated instructions (for example, software stored on a tangible and non-transitory computer readable storage medium, such as a computer hard drive, ROM, RAM, or the like) that perform the operations described herein. The above examples are exemplary only and are thus not intended to limit in any way the definition and / or meaning of the term “controller.” The units / modules / applications herein may execute a set of instructions that are stored in one or more storage elements, in order to process15968WOO1 (013-0632PCT1) 89 PATENTdata. The storage elements may also store data or other information as desired or needed. The storage element may be in the form of an information source or a physical memory element within the modules / controllers herein. The set of instructions may include various commands that instruct the modules / applications herein to perform specific operations such as the methods and processes of the various embodiments of the subject matter described herein. The set of instructions may be in the form of a software program. The software may be in various forms such as system software or application software. Further, the software may be in the form of a collection of separate programs or modules, a program module within a larger program or a portion of a program module. The software also may include modular programming in the form of object-oriented programming. The processing of input data by the processing machine may be in response to user commands, or in response to results of previous processing, or in response to a request made by another processing machine.

[0172] It is to be understood that the subject matter described herein is not limited in its application to the details of construction and the arrangement of components set forth in the description herein or illustrated in the drawings hereof. The subject matter described herein is capable of other embodiments and of being practiced or of being conducted in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of “including,” “comprising,” or “having”15968WOO1 (013-0632PCT1) 90 PATENTand variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items.

[0173] It is to be understood that the above description is intended to be illustrative, and not restrictive. For example, the above-described embodiments (and / or aspects thereof) may be used in combination with each other. In addition, many modifications may be made to adapt a particular situation or material to the teachings herein without departing from its scope. While the dimensions, types of materials and coatings described herein are intended to define various parameters, they are by no means limiting and are illustrative in nature. Many other embodiments will be apparent to those of skill in the art upon reviewing the above description. The scope of the embodiments should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. In the appended claims, the terms "including" and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein." Moreover, in the following claims, the terms "first," "second," and "third," etc. are used merely as labels, and are not intended to impose numerical requirements on their objects or order of execution on their acts.15968WOO1 (013-0632PCT1) 91 PATENT

Claims

1. WHAT IS CLAIMED IS:

1. A method of conducting a virtual clinic (VC) session between a patient and a clinician using a VC cloud telehealth system to program an implantable pulse generator (IPG) of a patient to provide a neurostimulation therapy to the patient, comprising:3.defining one or more VC session models or criteria that represent clinician and patient interactions during a VC session;4.establishing a first communication connection between a patient electronic device (PED) and the IPG of the patient;5.establishing a second communication connection between a patient electronic device (PED) and the VC cloud telehealth system;6.establishing a third communication connection between a clinician electronic device (CED) and the VC cloud computing system to connect the patient and clinician for the VC session;7.receiving input from the clinician for modification of one or more stimulation parameters during the VC session;8.communicating one or more signals to the PED to modify the one or more stimulation parameters during the VC session;9.15968WOO1 (013-0632PCT1) 92 PATENT applying electrical stimulation for the neurostimulation therapy to the patient according to the modified one or more stimulation parameters during the VC session;10.repetitively applying VC session data to the VC session models or criteria to calculate a metric related to a probability of successfully completing the VC session while the VC session is ongoing; and11.providing an indication to the clinician using the CED for display to the clinician a likelihood of successfully completing the VC session, wherein the indication is updated for display during the VC session as repetitive calculations of the metric related to a probability of successfully completing the VC session are performed.

2. The method of claim 1 further comprising:13.estimating, by the VC cloud telehealth system, a VC session time with sufficient time likely for a successful conclusion of the VC session for the patient.

3. The method of claim 2 further comprising:15.conducting, by the VC cloud telehealth system, a pre-VC session interview using a chatbot module of the VC cloud telehealth system, wherein the estimating comprises processing patient responses during the pre-VC session interview to estimate the VC session time.16.15968WOO1 (013-0632PCT1) 93 PATENT 4. The method of any preceding claim further comprising:17.receiving clinician input via the CED to add additional time to the VC session time;18.calculating a metric related to a probability of successfully completing the VC session according to the additional time the one or more VC session models or criteria by the VC cloud telehealth system; and19.providing an indication to the clinician using the CED for display to the clinician a likelihood of successfully completing the VC session with the additional time.

5. The method of any preceding claim wherein the one or more VC session models or criteria comprise at least one neural network model for processing multiple VC session parameters.

6. The method of any preceding claim further comprising:22.selecting between one or more VC session models or criteria for the VC session by identifying a patient condition to be addressed during the VC session.

7. The method of any preceding claim further comprising:24.selecting between one or more VC session models or criteria for the VC session according to patient demographic data.25.15968WOO1 (013-0632PCT1) 94 PATENT 8. The method of any preceding claim wherein one or more VC session models or criteria for the VC session according to patient demographic data are defined for respective clinicians for calculating the metric on a clinician specific basis.

9. The method of any preceding claims further comprising monitoring a total amount of VC session time and the total amount of VC session time includes an amount of time during the VC session spent programming the patient's implantable pulse generator.

10. The method of claim 9 wherein the total session time and the amount of time spent programming the patient's implantable pulse generator are provided to the one or more VC session models or criteria.

11. A virtual clinic (VC) cloud telehealth system configured to conduct a VC session between a patient and a clinician to program an implantable pulse generator (IPG) of the patient comprising:29.the IPG;30.a patient electronic device (PED) including one or more processors that, when executing program instructions, are configured to: establish a first communication connection with the IPG of the patient;31.one or more servers including one or more processors that, when executing program instructions, are configured to:32.15968WOO1 (013-0632PCT1) 95 PATENT define one or more VC session models or criteria that represent clinician and patient interactions during a VC session;33.establish a second communication connection with the PED;34.establish a third communication connection with a clinician electronic device (CED) to provide a communication pathway between the patient and a clinician for the VC session;35.receive input from the clinician for modification of one or more stimulation parameters during the VC session;36.repetitively apply VC session data to the VC session models or criteria to calculate a metric related to a probability of successfully completing the VC session while the VC session is ongoing;37.communicate one or more signals to the PED to modify the one or more stimulation parameters during the VC session;38.the CED having an interface and including one or more processors that, when executing program instructions, are configured to:39.obtain from the one or more servers the probability of successfully completing the VC session; and40.continuously and repeatably update a message on the interface that indicates the probability of successfully completing the VC session as41.15968WOO1 (013-0632PCT1) 96 PATENT repetitive calculations of the metric related to a probability of successfully completing the VC session are performed;42.the IPG including one or more processors that, when executing program instructions, are configured to:43.obtain instructions from the PED; and44.apply electrical stimulation for the neurostimulation therapy to the patient according to the one or more stimulation parameters modified during the VC session.

12. The system of claim 11, wherein the one or more processors of the one or more servers are further configured to:46.estimate a VC session time with sufficient time likely for a successful conclusion of the VC session for the patient.

13. The system of claim 12 wherein the one or more processors of the PED are further configured to conduct a pre-VC session interview using a chatbot module, wherein to estimate the VC session time comprises processing patient responses during the pre-VC session interview to estimate the VC session time.

14. The system of any of claims 11-13 wherein the one or more processors of the one or more servers are further configured to:49.15968WOO1 (013-0632PCT1) 97 PATENT receive clinician input via the CED to add additional time to the VC session time;50.calculate a metric related to the probability of successfully completing the VC session according to the additional time; and51.communicate an indication of the probability of successfully completing the VC session that includes the additional time to the CED for display by the CED to the clinician.

15. The system of any of claims 11-14, wherein the one or more VC session models or criteria comprise at least one neural network model for processing multiple VC session parameters.

16. The system of any of claims 11-15, wherein the one or more processors of the one or more servers are further configured to:54.select between one or more VC session models or criteria for the VC session by identifying a patient condition to be addressed during the VC session.

17. The system of any of claims 11-16, wherein the one or more processors of the one or more servers are further configured to:56.select between the one or more VC session models or criteria for the VC session according to patient demographic data.57.15968WOO1 (013-0632PCT1) 98 PATENT 18. The system of any of claims 11-17, wherein one or more VC session models or criteria for the VC session according to patient demographic data are defined for respective clinicians for calculating the metric on a clinician specific basis.

19. The system of any of claims 11-18 wherein the one or more processors of the one or more servers are further configured to monitor a total amount of VC session time and the total amount of VC session time includes an amount of time during the VC session spent programming the patient's implantable pulse generator.

20. The system of claim 19 wherein the one or more processors of the one or more servers provide the total session time and the amount of time spent programming the patient's implantable pulse generator to the one or more VC session models or criteria.

21. A method of conducting a virtual clinic (VC) session between a patient and a clinician to provide medical services using a VC cloud telehealth system, comprising:61.defining multiple patient models in the VC cloud telehealth system, each patient model corresponding to a patient condition or a medical response for the patient, wherein each patient model comprises multiple entries that define relative62.15968WOO1 (013-0632PCT1) 99 PATENT relevance of each respective entry to the corresponding patient condition or medical response;63.establishing a first communication connection between a patient electronic device (PED) and the VC cloud telehealth system;64.establishing a second communication connection between a clinician electronic device (CED) and the VC cloud computing system to connect the patient and clinician for the VC session;65.receiving input during the VC session indicative of patient state or condition relevant to one or more respective entries in the multiple patient models;66.in response to receiving the input indicative of patient state or condition, calculating, by the VC cloud telehealth system, relevance metrics for respective questions using the received input and the multiple patient models that reflect relative relevance of the respective questions to be asked by a clinician in determining whether a respective patient condition or medical response is applicable for the patient;67.identifying one or more questions to the clinician electronic device for display to the clinician according to the calculated relevance metrics; and68.displaying, on an interface, the one or more questions identified.69.15968WOO1 (013-0632PCT1) 100 PATENT 22. The method of claim 12 wherein the providing identification provides one or more questions for display to the clinician sorted in an order related to respective relevance metrics for the one or more questions.

23. The method of any of claims 21-22 further comprising:71.generating a summary of a pre-VC session interview using a chatbot module of the VC cloud telehealth system and presenting the summary to the clinician using the CED.

24. The method of any of claims 21-23 wherein the patient models comprise entries related to physiological states of a patient, wherein the method further comprises:73.obtaining sensor data from a wearable patient device of the patient to evaluate entries related to physiological states of the patient.

25. The method of any of claims 21-24 wherein the one or more patient models each comprise an occurrence metric that is reflective of an occurrence of its corresponding patient condition or a medical response.

26. The method of claim 25 wherein the calculating, by the VC cloud telehealth system, relevance metrics comprises applying occurrence metrics to weight individual question relevance calculations.76.15968WOO1 (013-0632PCT1) 101 PATENT 27. The method of any of claims 21-26 wherein the VC cloud telehealth system comprises a library of pre-defined patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions.

28. The method of any of claims 21-27 wherein the VC cloud telehealth system comprises an interface for defining patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions.

29. The method of any of claims 21-28 further comprising:79.communicating a signal to the PC to control a patient's implantable medical device to conduct diagnostic operations to obtain patient data by the VC cloud telehealth system, wherein one or more entries of the patient models comprises at least one entry related to a condition of a patient's implantable medical device.

30. The method of claim 9 wherein the diagnostic operations comprise at least one set of operations from the list consisting of: performing impedance measures of electrodes of one or more stimulation leads and performing stimulation lead migration measurements.

31. A virtual clinic (VC) cloud telehealth system configured to conduct a VC session between a patient and a clinician to provide medical services comprising:82.15968WOO1 (013-0632PCT1) 102 PATENT one or more servers configured to be in communication with a patient electronic device and a clinician electronic device over a network;83.the one or more servers including one or more processors that, when executing program instructions, are configured to:84.define patient models, each patient model corresponding to a patient condition or a medical response for a patient, wherein each patient model comprises entries that define relative relevance of each respective entry to the corresponding patient condition or medical response;85.establish a first communication connection between a patient electronic device (PED) and the one or more servers;86.establish a second communication connection between a clinician electronic device (CED) and the one or more servers to provide a communication pathway between the patient and a clinician for the VC session;87.receive input during the VC session indicative of patient state or condition relevant to one or more respective entries in the patient models;88.in response to receiving the input, calculate relevance metrics for respective questions using the received input and the patient models that reflect relative relevance of the respective questions to be asked by the clinician in determining whether a respective patient condition or medical response is applicable for the patient;89.15968WOO1 (013-0632PCT1) 103 PATENT identify one or more questions according to the relevance metrics calculated; and90.communicate the one or more questions to the clinician electronic device for display to the clinician.

32. The system of claim 11 wherein to identify the one or more questions comprises sorting the one or more questions in an order related to the relevance metrics for the one or more questions.

33. The system of any of claims 31-32 the one or more processors further configured to:93.generate a summary of the pre-VC session interview obtained using the chatbot module; and transmit a downloadable for displaying on an interface of the patient electronic device, when transmitting the one or more questions.

34. The system of any of claims 31-32, wherein the patient models comprise entries related to a physiological state of a patient, and wherein the one or more processors are further configured to:95.obtain sensor data to evaluate entries related to the physiological state of the patient.96.15968WOO1 (013-0632PCT1) 104 PATENT 35. The system of any of claims 31-34 wherein the patient models each comprise an occurrence metric that is reflective of an occurrence of the patient condition or the medical response.

36. The system of claim 35 wherein to calculate the relevance metrics comprises applying occurrence metrics to weight individual question relevance calculations.

37. The system of any of claims 31 -36 further comprising a library of predefined patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions.

38. The system of any of claims 31-37 wherein the one or more processors are further configured to obtain the defining patient questions, the patient models, and the mapping definitions selected by a clinician at clinician interface to conduct one or more VC sessions.

39. The system of any claims 31-38 wherein the one or more processors are further configured to:101.communicate a signal to the patient electronic device to control a patient's implantable medical device to conduct diagnostic operations to obtain patient data; wherein one or more entries of the patient models comprises at least one entry related to a condition of a patient's implantable medical device.102.15968WOO1 (013-0632PCT1) 105 PATENT 40. The system of claim 39 wherein the diagnostic operations comprise at least one set of operations from the list consisting of: performing impedance measures of electrodes of one or more stimulation leads and performing stimulation lead migration measurements.

41. A method of conducting a virtual clinic (VC) session between a patient and a clinician to provide medical services using a VC cloud telehealth system, comprising:104.defining one or more set of questions in the VC cloud telehealth system to be delivered by a chatbot module of the VC cloud telehealth system;105.defining patient models in the VC cloud telehealth system, each patient model corresponding to a patient condition or a medical response for the patient, wherein each patient model comprises multiple entries that define relative relevance of each respective entry to the corresponding patient condition or medical response;106.defining mapping definitions in the VC cloud telehealth system between questions of the one or more sets of pre-VC session interview questions to respective entries in the patient models;107.establishing a first communication connection between a patient electronic device (PED) and the VC cloud telehealth system;108.15968WOO1 (013-0632PCT1) 106 PATENT conducting a pre-VC session interview of the patient via the PED using at least one set of pre-VC session interview questions defined in the VC cloud telehealth system by the chatbot module of the VC cloud telehealth system;109.upon completion of the pre-VC session interview of the patient, calculating, by the VC cloud telehealth system, relevance metrics for respective questions using processed patient responses, the patient models, and the mapping definitions that reflect relative relevance of the respective questions to be asked by a clinician in determining whether a respective patient condition or medical response is applicable for the patient;110.establishing a second communication connection between a clinician electronic device (CED) and the VC cloud computing system to connect the patient and clinician for the VC session;111.identifying one or more questions to the CED for display to the clinician according to the calculated relevance metrics; and112.displaying, on an interface, the one or more questions identified.

42. The method of claim 41 wherein the providing identification provides one or more questions for display to the clinician sorted in an order related to respective relevance metrics for the one or more questions.

43. The method of any of claims 41 -42 further comprising:115.15968WOO1 (013-0632PCT1) 107 PATENT generating a summary of the pre-VC session interview using the chatbot module and displaying, on the interface, the summary to the clinician using the CED.

44. The method of any of claims 41-43 wherein the patient models comprise entries related to physiological states of a patient, wherein the method further comprises:117.obtaining sensor data from a wearable patient device of the patient to evaluate entries related to physiological states of the patient.

45. The method of any of claims 41 -45 wherein the one or more patient models each comprise an occurrence metric that is reflective of an occurrence of the patient condition or the medical response.

46. The method of claim 45 wherein the calculating, by the VC cloud telehealth system, relevance metrics comprises applying occurrence metrics to weight individual question relevance calculations.

47. The method of any of claims 41-47 wherein the VC cloud telehealth system comprises a library of pre-defined patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions.

48. The method of any of claims 41 -48 wherein the VC cloud telehealth system comprises an interface for defining patient questions, patient models, and 15968WOO1 (013-0632PCT1) 108 PATENTmapping definitions for selection by a clinician to conduct one or more VC sessions.

49. The method of any of claims 41 -48 further comprising:123.communicating a signal to control a patient's implantable medical device to conduct diagnostic operations to obtain patient data by the VC cloud telehealth system in response to establishing the first communication connection, wherein one or more entries of the patient models comprises at least one entry related to a condition of a patient's implantable medical device.

50. The method of claim 49 wherein the diagnostic operations comprise at least one set of operations from the list consisting of: performing impedance measures of electrodes of one or more stimulation leads and performing stimulation lead migration measurements.

51. A virtual clinic (VC) cloud telehealth system configured to conduct a VC session between a patient and a clinician to provide medical services comprising:126.one or more servers configured to be in communication with a patient electronic device and a clinician electronic device over a network;127.the one or more servers including one or more processors that, when executing program instructions, are configured to:128.15968WOO1 (013-0632PCT1) 109 PATENT obtain patient inputs from a chatbot module of the patient electronic device;129.define one or more set of questions to be delivered by the chatbot module to a patient during a pre-VC session interview;130.obtain patient input data from the patient electronic device based on the one or more set of questions;131.define patient models, each of the patient models corresponding to a patient condition or a medical response for the patient, wherein each patient model comprises multiple entries that define relative relevance of each respective entry to the corresponding patient condition or medical response;132.upon completion of the pre-VC session interview of the patient, calculate, relevance metrics for respective questions using processed patient responses and the patient models;133.identify one or more questions based on the relevance metrics; and134.communicate the one or more questions identified to a clinician electronic device for display.

52. The system of claim 51, the one or more processors further configured to sort the one or more questions in an order related to respective relevance metrics for the one or more questions.136.15968WOO1 (013-0632PCT1) 110 PATENT 53. The system of any of claims 51-52, the one or more processors further configured to:137.generate a summary of the pre-VC session interview obtained using the chatbot module and transmitting a downloadable for displaying on an interface of the patient electronic device, when transmitting the one or more questions.

54. The system of any of claims 51-53, wherein the patient models comprise entries related to a physiological state of a patient, and wherein the one or more processors are further configured to:139.obtain sensor data to evaluate entries related to the physiological state of the patient.

55. The system of any of claims 51-54 wherein the patient models each comprise an occurrence metric that is reflective of an occurrence of the patient condition or the medical response.

56. The system of claim 15 wherein to calculate the relevance metrics comprises applying occurrence metrics to weight individual question relevance calculations.

57. The system of any of claims 51 -56 further comprising a library of predefined patient questions, patient models, and mapping definitions for selection by a clinician to conduct one or more VC sessions.143.15968WOO1 (013-0632PCT1) 111 PATENT 58. The system of any of claims 51-57 wherein the one or more processors are further configured to obtain the defining patient questions, the patient models, and the mapping definitions selected by a clinician at clinician interface to conduct one or more VC sessions.

59. The system of any of claims 51-58 wherein the one or more processors are further configured to:145.communicate a signal to the patient electronic device to control a patient's implantable medical device to conduct diagnostic operations to obtain patient data; wherein one or more entries of the patient models comprises at least one entry related to a condition of a patient's implantable medical device.

60. The system of claim 59 wherein the diagnostic operations comprise at least one set of operations from the list consisting of: performing impedance measures of electrodes of one or more stimulation leads and performing stimulation lead migration measurements.147.15968WOO1 (013-0632PCT1) 112 PATENT

Images