Evaluation of post implantation patient status and medical device performance

Abstract

Techniques for remote monitoring of a patient and corresponding medical device(s) are described. The remote monitoring comprises providing an interactive session configured to allow a user to navigate a plurality of subsessions, determining a first set of data items in accordance with a first subsession, the first set of data items including the image data, determining a second set of data items in accordance with a second subs ession of the interactive session, determining, based at least in part on the first set of data items and the second set of data items, an abnormality, and outputting a post-implant report of the interactive session.

What is claimed is: 
     
         1 . A system comprising:
 a memory configured to store image data; and   processing circuitry in communication with the memory, the processing circuitry configured to:
 provide an interactive session configured to allow a user to navigate a plurality of subsessions comprising at least a first subsession; 
 display, during the first subsession, a prompt for the user to capture image data of a wound site on a body of a patient via one or more cameras; 
 apply the image data of the wound site on the body of the patient captured during the first subsession and historical image data of the wound site of the body of the patient as input to a machine learning model to analyze progression of healing of the wound site on the body of the patient, wherein the machine learning model is trained on reference image data from a library of reference images; and 
 output a report of the interactive session, wherein the report includes an indication of the progression of the healing of the wound site on the body of the patient. 
   
     
     
         2 . The system of  claim 1 , wherein the image data comprises one or more frames that represent images of the body of the patient. 
     
     
         3 . The system of  claim 1 , wherein processing circuitry is further configured to: output the report to a device of a healthcare professional (HCP). 
     
     
         4 . The system of  claim 1 , wherein the reference image data from the library of reference images are labeled based on improvement or deterioration in the wound site. 
     
     
         5 . The system of  claim 1 , wherein the reference image data from the library of reference images are labeled as corresponding to an abnormality or not. 
     
     
         6 . The system of  claim 1 , wherein the indication of the progression of the healing of the implantation site on the body of the patient includes at least one of an indication as to when redness should subside, an indication as to when soreness should subside below a predefined soreness threshold, an indication as to when a likelihood of infection has dropped below a predefined infection threshold, or an indication as to when the implantation site should be healed beyond a predefined healing threshold. 
     
     
         7 . The system of  claim 1 , wherein to analyze progression of healing of the wound site on the body of the patient, the processing circuitry is further configured to:
 determine, based on the historical image data of the wound site on the body of the patient, a projection of the wound site on the body of the patient;   compare characteristics of the image data captured during the first subsession to the projection to determine whether a healing of the wound site on the body of the patient has deviated from the projection; and   detect an abnormality in the healing of the implantation site on the body of the patient based on the comparison.   
     
     
         8 . The system of  claim 7 , wherein when an abnormality is detected, the processing circuitry is further configured to: output one or more frames of image data for a healthcare professionals (HCPs) review. 
     
     
         9 . The system of  claim 1 , wherein the report includes one or more frames of image data of the wound site on the body of the patient. 
     
     
         10 . The system of  claim 1 , wherein the machine learning model is trained on patient data obtained via a network. 
     
     
         11 . A method of operating a system including a computing device to evaluate a wound site on a body of a patient, the method comprising:
 providing, via the computing device, an interactive session configured to allow a user to navigate a plurality of subsessions comprising at least a first subsession;   displaying, via the computing device, during the first subsession, a prompt for the user to capture image data of the wound site via one or more cameras;   applying the image data of the wound site on the body of the patient captured during the first subsession and historical image data of the wound site of the body of the patient as input to a machine learning model to analyze progression of healing of the wound site on the body of the patient, wherein the machine learning model is trained on reference image data from a library of reference images; and   outputting a report of the interactive session, wherein the report includes an indication of the progression of the healing of the wound site on the body of the patient.   
     
     
         12 . The method of  claim 11 , wherein the image data comprises one or more frames that represent images of the body of the patient. 
     
     
         13 . The method of  claim 11 , wherein outputting the report of the interactive session comprises outputting the report of the interactive session a device of a healthcare professional (HCP). 
     
     
         14 . The method of  claim 11 , wherein the reference image data from the library of reference images are labeled based on improvement or deterioration in the wound site. 
     
     
         15 . The method of  claim 11 , wherein the indication of the progression of the healing of the implantation site on the body of the patient includes at least one of an indication as to when redness should subside, an indication as to when soreness should subside below a predefined soreness threshold, an indication as to when a likelihood of infection has dropped below a predefined infection threshold, or an indication as to when the implantation site should be healed beyond a predefined healing threshold. 
     
     
         16 . The method of  claim 11 , wherein outputting the report of the interactive session further comprises outputting an indication of an abnormality corresponding to the wound site. 
     
     
         17 . The method of  claim 16 , where the method further comprises: outputting, when the abnormality is detected, one or more frames of image data for a healthcare professionals (HCPs) review. 
     
     
         18 . The method of  claim 11 , wherein the report includes one or more frames of image data of the wound site on the body of the patient. 
     
     
         19 . The method of  claim 11 , wherein the machine learning model is trained on patient data obtained via a network. 
     
     
         20 . A non-transitory computer-readable storage medium having stored thereon instructions that, when executed, cause one or more processors to:
 provide an interactive session configured to allow a user to navigate a plurality of subsessions comprising at least a first subsession;   display, during the first subsession, a prompt for the user to capture image data of a wound site on a body of a patient via one or more cameras;   apply the image data of the wound site on the body of the patient captured during the first subsession and historical image data of the wound site of the body of the patient as input to a machine learning model to analyze progression of healing of the wound site on the body of the patient, wherein the machine learning model is trained on reference image data from a library of reference images; and   output a report of the interactive session, wherein the report includes an indication of the progression of the healing of the wound site on the body of the patient.