Selection of a wearable article for a medical device
A medical wearable matching system is provided that pre-assesses a fit of a wearable article of medical device for a patient. The matching system may facilitate fitting and selection of a class of wearable articles for a patient. The matching system may also evaluate potential effects of the fit on operations of the medical device. Patient specific data, such as measurements, are fed into a fit prediction artificial intelligence (“AI”) model. The fitting AI model is trained with fitting data of previous patients to predict a class of wearable medical article that is likely, above a threshold amount, to provide a target fit for the patient. The patient specific information may also be fed into an adverse potential AI model. The adverse potential AI model is trained with patient experience data describing adverse operations of a wearable article worn by prior patients.
1. A method for selecting a wearable article of a medical device for a patient, the method comprising:
receiving patient specific data including body measurement data;
conducting predictive analysis to predict a class of the wearable article that provides a target fit for positioning a component of the wearable article to contact the body of the patient for performance of the medical device to treat and/or monitor the patient for a medical condition, by:
inputting patient specific data and one or more fit factors to a first artificial intelligence (“AI”) model trained on fitting data of previous patients having the same or similar medical condition as the patient; and
receiving an output from the first AI model that includes a predicted class of wearable article that likely provides the target;
selecting the class of the wearable article based, at least in part, on the predicted class;
providing the selected class of the wearable article for treatment and monitoring of the patient for the medical condition during wearing of the wearable article; and
retraining the first AI model with updated inputs including additional fitting data for new patients fitted with the wearable article.
2. The method of claim 1 , wherein the body measurement data is related to a body contact point of the component and is obtained by use of one or more capture devices selected from a group of: a Light Detection and Ranging (LiDAR) device, a body scanner, a camera, a digital scale, and combinations thereof.
3. The method of claim 1 , wherein at least a portion of the patient specific data is obtained by a local client computing device and transferred to a remote computing device, wherein the conducting of the predictive analysis and the selecting of the class of the wearable article are performed by the remote computing device.
4. The method of claim 1 , wherein the predictive analysis is conducted by a remote computing device, wherein the output result is received by a client computing device, and wherein the selecting of the class of the wearable article is by the client computing device.
5. The method of claim 1 , wherein at least a portion of the patient specific data is obtained by a local client computing device, and wherein the conducting of the predictive analysis and the selecting of the class of the wearable article are performed by the client computing device.
6. The method of claim 1 , further comprising:
conducting a second predictive analysis using a second AI model to predict an adverse fit potential of the selected wearable article, by:
inputting the patient specific data and the selected class of the wearable article to the second AI model, wherein the second AI model is trained using patient experience data in which suboptimal operation of the selected class of wearable article worn by prior patients is due, at least in part, to fit of the wearable article; and
receiving an output from the second AI model that includes a predicted adverse fit potential; and
providing an alert of the predicted adverse fit potential to at least one of the patient, a medical provider for the patient, or a caretaker for the patient.
7. The method of claim 1 , wherein the patient specific data further includes patient medical condition information.
8. The method of claim 1 , wherein the component includes one or more sensors and/or one or more electrodes positioned for cardiac monitoring and treatment by the medical device.
9. The method of claim 1 , wherein the retraining of the first AI model includes feeding discrepancy information back into the first AI model, wherein the discrepancy information includes a found adverse effect on the performance of the medical device of previous wearable articles predicted by the first AI model to provide target fit for previous patients.
10. A matching system for selecting a wearable article of a medical device system, the matching system comprising:
at least one computing device comprising:
an interface for receiving patient specific data including body measurement data; and
one or more processors and logic encoded in one or more non-transitory media for execution by the one or more processors and when executed operable to perform steps comprising:
conducting predictive analysis to predict a class of the wearable article that provides a target fit for positioning a component of the wearable article to contact the body of the patient for performance of the medical device to treat and monitor the patient for a medical condition, by:
inputting patient specific data and one or more fit factors to a first artificial intelligence (“AI”) model trained on fitting data of previous patients having the same or similar medical condition as the patient; and
receiving an output from the first AI model that includes a predicted class of wearable article that likely provides the target fit; and
receiving an output from the first AI model that includes a predicted class of the wearable article that likely provides the target fit;
selecting the class of the wearable article based, at least in part, on the predicted class; and
providing the selected class of the wearable article for treatment and monitoring of the patient for the medical condition during wearing of the wearable article; and
retraining the first AI model with updated inputs including additional fitting data for new patients fitted with the wearable article.
11. The system of claim 10 , wherein the body measurement data is related to a body contact point of the component and is obtained by use of one or more capture devices selected from a group of: a LiDAR device, a body scanner, a camera, a digital scale, and combinations thereof.
12. The system of claim 10 , wherein the at least one computing device includes a local client computing device configured to obtain at least a portion of the patient specific data and to transfer the at least portion of the patient specific data to a remote computing device, and wherein the at least one computing device further includes the remote computing device configured to conduct the predictive analysis and to select the class of the wearable article.
13. The system of claim 10 , wherein the at least one computing device includes a remote computing device configured to conduct the predictive analysis, and wherein the at least one computing device further includes a local client computing device configured to receive the output result from the remote computing device and to select the class of the wearable article.
14. The system of claim 10 , wherein the at least one computing device includes a local client computing device configured to obtain at least a portion of the patient specific data at a patient location and to transfer the at least portion of the patient specific data to a remote computing device, and wherein the at least one computing device further includes the remote computing device configured to conduct the predictive analysis and transfer the output result to the client computing device, and wherein the client computing device is further configured to select the class of the wearable article.
15. The system of claim 10 , wherein the steps further comprise:
conducting a second predictive analysis using a second AI model to predict an adverse fit potential of the selected wearable article, by:
inputting the patient specific data and the selected class of the wearable article to the second AI model, wherein the second AI model is trained using patient experience data in which suboptimal operation of the selected class of wearable article worn by prior patients is due, at least in part, to fit of the wearable article; and
receiving an output from the second AI model that includes a predicted adverse fit potential; and
providing an alert of the predicted adverse fit potential to at least one of the patient, a medical provider for the patient, or a caretaker for the patient.
16. A method for selecting a wearable article of a medical monitoring device for a patient, the method comprising:
training a first artificial intelligence (“AI”) model by inputting fitting data of previous patients having a medical condition and one or more fit factors for contact of a component of the wearable article with the body of the patient, to predict a class of the wearable article that provides a target fit for positioning a component of the wearable article to contact the body of the patient for performance of the medical device to treat and monitor the patient for the medical condition;
receiving patient specific data including body measurement data of a patient;
inputting the patient specific data into the trained first AI model;
conducting predictive analysis using the trained first AI model to output a predicted class of wearable article that likely provides the target fit based, at least in part, on the patient specific data as input to the first AI model;
selecting the class of the wearable article based, at least in part, on an output result of the predictive analysis to provide the selected class of the wearable article for treatment and monitoring of the patient during wearing of the wearable article;
determining that the selected class of the wearable article fails to provide the target fit for the patient; and
generating discrepancy data to feed back into the trained first AI model for retraining; and
retraining the first AI model with updated inputs including additional fitting data for new patients fitted with the wearable article.
17. The method of claim 16 , further comprising:
training a second AI model using patient experience data of previous patients to predict an adverse fit potential of the selected wearable article for the patient in which suboptimal operation of the selected class of wearable article worn by prior patients is due, at least in part, to fit of the wearable article;
inputting the patient specific data into the trained second AI model;
conducting a second predictive analysis using the trained second AI model to output a predicted adverse fit potential of the selected wearable article, based on the patient specific data and the selected class of the wearable article class;
determining that the selected class of the wearable article causes an adverse experience for the patient; and
generating discrepancy data to feed back into the trained second AI model for retraining.