Data labeling system and method operative with patient and clinician controller devices disposed in a remote care architecture
A system and method for facilitating remote care management involving a patient having an implantable medical device (IMD). Upon establishing a remote care session between a patient controller device and a clinician programmer, wherein the clinician and the patient are remotely located with respect to each other, input from the patient or the clinician may be received via a user interface control associated with a particular functionality or aspect of the remote care session, including audiovisual (AV) communications, remote therapy programming, and related context. Responsive to the user input, a dialog interface is effectuated at one of the patient controller device and/or the clinician programmer. A user characterization label is received via the dialog interface from the user, wherein the user characterization label is indicative of a subjective assessment of the particular functionality of the remote care session, which may be used in generating user-labeled data pertaining thereto.
1. A method for providing a therapy to a patient having an implantable medical device (IMD), the method comprising:
delivering at least one therapy to the patient via one or more electrodes of at least one lead of the IMD during a remote care session;
receiving input via a user interface control provided by at least one device facilitating the remote care session, the at least one device comprising a patient controller device, a clinician programmer device, or both, wherein the input comprises feedback associated with the at least one therapy;
determining one or more labels based on the feedback, each label corresponding to therapy information associated with therapy settings for the at least one therapy delivered to the patient during the remote care session;
storing one or more data records in a database, each data record of the one or more data records corresponding to a label of the one or more labels and including the corresponding therapy information;
training a machine learning algorithm based on a dataset including the one or more data records, wherein the machine learning algorithm is configured, once trained, to predict future therapy settings for a therapy to be delivered to the patient; and
predicting therapy settings for the patient using the trained machine learning algorithm.
2. The method as recited in claim 1 , wherein the feedback comprises textual content, pictogrammatic content, speech content, sound-based content, or a combination thereof.
3. The method of claim 1 , wherein the remote care session comprises an audio/video (AV) communication session.
4. The method of claim 3 , wherein the feedback relates to an audio quality of the AV communication session.
5. The method of claim 3 , wherein the feedback relates to a video quality of the AV communication session.
6. The method of claim 3 , wherein the feedback relates to a patient motor response capture quality of the AV communication session.
7. The method of claim 6 , further comprising associating a label of the one or more labels to AV data corresponding to the patient motor response.
8. The method of claim 3 , wherein the feedback relates to a patient vocalization capture quality of the AV communication session.
9. The method as recited in claim 1 , wherein the user interface control comprises an audio dialog window facilitating voice recognition.
10. The method as recited in claim 1 , wherein the user interface control comprises a video dialog window for facilitating motion capture and facial recognition.
11. The method as recited in claim 1 , wherein the user interface control comprises a plurality of selectable label elements, each selectable label element corresponding to a particular label of a plurality of labels, and wherein the one or more labels are determined, at least in part, based on selection of one or more of the plurality of selectable label elements.
12. The method of claim 11 , wherein the plurality of selectable label elements comprises software icons, a pull-down menu, or both.
13. The method as recited in claim 1 , wherein the feedback comprises at least one of a voice label, a ranking label, a multi-category label, a binary category label, a graphic icon label, an emoji label, a gesture-based label and a sliding scale label.
14. The method as recited in claim 1 , wherein at least the remote care session is paused in response to determining that a label has occurred a predetermined number of times over a period of time.
15. The method of claim 14 , wherein the period of time is configurable.
16. The method as recited in claim 1 , wherein the at least one therapy comprises a spinal cord stimulation (SCS) therapy, a neuromuscular stimulation therapy, a dorsal root ganglion (DRG) stimulation therapy, a deep brain stimulation (DBS) therapy, a cochlear stimulation therapy, a drug delivery therapy, a cardiac pacemaker therapy, a cardioverter-defibrillator therapy, a cardiac rhythm management (CRM) therapy, an electrophysiology (EP) mapping and radio frequency (RF) ablation therapy, an electroconvulsive therapy (ECT), a repetitive transcranial magnetic stimulation (rTMS) therapy, a vagal nerve stimulation (VNS) therapy, or a combination thereof.
17. The method of claim 1 , wherein the therapy settings predicted for the patient using the trained machine learning algorithm correspond to current therapy settings.
18. The method of claim 1 , wherein the therapy settings predicted for the patient using the trained machine learning algorithm correspond to future therapy settings.
19. The method of claim 1 , further comprising associating a timestamp with each label of the one or more labels.
20. The method of claim 19 , further comprising recording one or more records to a database, each record of the one or more records comprising a particular label of the one or more labels, the timestamp associated with the particular label, and a therapy delivered to the patient.