Health with a mobile device

Abstract

Disclosed herein are devices, systems, methods and platforms for continuously monitoring the health status of a user, for example the cardiac health status. The present disclosure describes systems, methods, devices, software, and platforms for continuously monitoring a user's health-indicator data (for example and without limitation PPG signals, heart rate or blood pressure) from a user-device in combination with corresponding (in time) data related to factors that may impact the health-indicator (“other-factors”) to determine whether a user has normal health as judged by or compared to, for example and not by way of limitation, either (i) a group of individuals impacted by similar other-factors, or (ii) the user him/herself impacted by similar other-factors.

What is claimed is: 
     
         1 . An apparatus, comprising:
 a processing device;   a heath-indicator data sensor operatively coupled to the processing device; and   a memory having instructions stored thereon that, when executed by the processing device, cause the processing device to:
 receive measured low fidelity health-indicator data and other-factor data at a first time, wherein measured health-indicator data is obtained by the health-indicator data sensor; 
 input a set of data comprising the health-indicator data and other-factor data at the first time into a trained high-fidelity machine learning model, wherein the trained high-fidelity machine learning model generate a prediction whether a high-fidelity health-indicator signal of the user is normal or abnormal; and 
 in response to the prediction being abnormal, send a notification that the user's health is abnormal. 
   
     
     
         2 . The apparatus according to  claim 1 , wherein the trained high-fidelity machine learning model comprises one or more of a trained high-fidelity generative neural network, a trained recurrent neural network (RNN), a trained feed-forward neural network, or a trained feed-forward neural network. 
     
     
         3 . The apparatus according to  claim 1 , wherein the trained high-fidelity machine learning model is trained on measured user health-indicator data labeled with user specific high-fidelity measurement data. 
     
     
         4 . The apparatus according to  claim 1 , wherein the trained high-fidelity machine learning model is trained on low fidelity health-indicator data labeled with high-fidelity measurement data, wherein the low fidelity health-indicator data and the high-fidelity measurement data is from a population of subjects. 
     
     
         5 . The apparatus according to  claim 1 , wherein the high-fidelity machine learning model outputs a probability distribution, wherein the prediction is sampled from the probability distribution. 
     
     
         6 . The apparatus according to  claim 5 , wherein the prediction is sampled according to a sampling technique selected from the group consisting of: the prediction at a maximum probability;
 and random sampling the prediction from the probability distribution.   
     
     
         7 . The apparatus according to  claim 5 , wherein an averaged prediction is determined by averaging, using an averaging method, the prediction over a period of time steps, and wherein the averaged prediction is used to determine if the user's health-indicator data is normal or abnormal. 
     
     
         9 . The apparatus according to  claim 1 , wherein the mobile device is selected from the group consisting of: a smart watch; a fitness band; a computer tablet; and a laptop computer. 
     
     
         10 . The apparatus according to  claim 1 , wherein each of the low-fidelity health signal data and other factor-data are time segments of data over a time period. 
     
     
         11 . The apparatus according to  claim 1 , wherein the low-fidelity data comprises a record of heart rate prior to the first time, the other-factor data comprises a record of activity level, and the prediction of the user's health-indicator comprises a prediction that the user experienced atrial fibrillation during the record of heart rate prior to the first time. 
     
     
         12 . The apparatus according to  claim 1 , wherein the processing device is further to:
 receive a set of training data, wherein the training data comprises labeled low-fidelity health-indicator data from a population of individuals, corresponding other-factor data from the population individuals, wherein the labeled low-fidelity indicator data is labeled with corresponding high-fidelity data from the population of individuals;   input an interval of the labeled low-fidelity health-indicator data and the corresponding other-factor data into the trained high-fidelity machine learning model;   update the labeled high-fidelity machine learning model by comparing an output from the trained high-fidelity machine learning model to the labeled high-fidelity data.   
     
     
         13 . A method, comprising:
 receiving, by a processing device, measured low fidelity health-indicator data and other-factor data at a first time, wherein measured health-indicator data is obtained by a user health-indicator data sensor;   inputting, by the processing device, data comprising the health-indicator data and other-factor data at the first time into a trained high-fidelity machine learning model, wherein the trained high-fidelity machine learning model generates a prediction whether a high-fidelity health-indicator signal of the user is normal or abnormal; and   in response to the prediction being abnormal, sending a notification that the user's health is abnormal.   
     
     
         14 . The method according to  claim 13 , wherein the trained high-fidelity machine learning model comprises one or more of a trained high-fidelity generative neural network, a trained recurrent neural network (RNN), a trained feed-forward neural network, or a trained feed-forward neural network. 
     
     
         15 . The method according to  claim 13 , wherein each of the low-fidelity health signal data and other factor-data are time segments of data over a time period. 
     
     
         16 . The method according to  claim 13 , wherein the low-fidelity data comprises a record of heart rate prior to the first time, the other-factor data comprises a record of activity level, the prediction of the user's health-indicator comprises a prediction that the user experienced atrial fibrillation during the record of heart rate prior to the first time, and the notification comprises and indication to take an ECG. 
     
     
         17 . A method comprising:
 receiving a set of training data, wherein the training data comprises a set of low-fidelity health-indicator data, a corresponding set of other-factor data, wherein the low-fidelity health-indicator data is labeled with a corresponding set of actual high-fidelity labels;   inputting, by a processing device, an interval of low-fidelity health-indicator data and corresponding other-factor data into an untrained machine learning model to generate a predicted high-fidelity label;   updating, by the processing device, the machine learning model based on comparing the predicted high-fidelity label to an actual high-fidelity label corresponding to the interval of low-fidelity health-indicator data.   
     
     
         18 . The method of  claim 17 , wherein the interval of low-fidelity health-indicator data comprises heart-rate measurements over an interval of time, the other-factor data comprises activity level over the interval of time, and the actual high-fidelity label comprises an indication that atrial fibrillation occurred during that interval of time. 
     
     
         19 . The method of  claim 17 , further comprising:
 inputting additional intervals of low-fidelity heath indicator data and corresponding additional other factor data into the untrained machine learning model to generate additional predicted high-fidelity labels;   comparing the additional predicted high-fidelity labels to additional actual high-fidelity labels corresponding to the additional intervals of low-fidelity health indicator data;   updating the untrained machine learning model; and   in response to determining that the untrained machine learning model has converged, outputting a trained machine learning model.   
     
     
         20 . The method of  claim 19 , further comprising:
 receiving, by a processing device, measured low fidelity health-indicator data and other-factor data at a first time, wherein measured health-indicator data is obtained by a user health-indicator data sensor;   inputting, by the processing device, data comprising the health-indicator data and other-factor data at the first time into a trained high-fidelity machine learning model, wherein the trained high-fidelity machine learning model makes a prediction whether a high-fidelity health-indicator signal of the user is normal or abnormal; and   in response to the prediction being abnormal, sending a notification to at least the user that the user's health is abnormal.