Systems and methods for predicting a fall

Abstract

Systems, methods and techniques for training and applying machine learning models to predict whether or not one or more individuals will suffer a fall event. In certain embodiments, a machine learning model can include both a static component and a dynamic component, where each component is associated with different types of medical data. In certain embodiments, an adjustment factor based on fall history of individuals is applied to the output of the machine learning model to generate a final score predictive of a fall event. In certain embodiments, the machine learning model is both trained and applied to medical data associated with predetermined forms, and where the predetermined forms include a value range associated with a medical condition.

What is claimed is: 
     
         1 . An apparatus, the apparatus comprising:
 a memory to store instructions; and   processing circuitry, coupled with the memory, operable to execute the instructions, that when executed, cause the processing circuitry to:
 apply a hybrid machine learning model (MLM) to a plurality of data associated with one or more individuals; and 
 compute a fall prediction score for the one or more individuals based in whole or in part on application of the hybrid MLM. 
   
     
     
         2 . The apparatus of  claim 1 , wherein the hybrid MLM includes both of i) a static component and ii) a dynamic component. 
     
     
         3 . The apparatus of  claim 2 , wherein the plurality of data includes: a first plurality of data associated with the one or more individuals and a second plurality of data associated with the one or more individuals, and wherein the static component determines one or more weights associated with the first plurality of data of and the dynamic component determines another one or more weights associated with the second plurality of data. 
     
     
         4 . The apparatus of  claim 2 , wherein one or more outputs of the static component are inputted into the dynamic component. 
     
     
         5 . The apparatus of  claim 3 , wherein the first plurality of data includes at least one of: i) a medical diagnostic information associated with the one or more individuals and ii) a medication information associated with the one or more individuals. 
     
     
         6 . The apparatus of  claim 3 , wherein the second plurality of data includes at least one of: i) a demographic information associated with the one or more individuals, ii) a physical activity information associated with the one or more individuals, iii) a vital change information associated with the one or more individuals, and iv) a governmental information associated with the one or more individuals. 
     
     
         7 . The apparatus of  claim 3 , wherein the first plurality of data includes all of: i) a medical diagnostic information associated with the one or more individuals and ii) a medication information associated with the one or more individuals, and wherein the second plurality of data includes all of: i) a demographic information associated with the one or more individuals, ii) a physical activity information associated the one or more individuals, iii) a vital change information associated with the one or more individuals, and iv) a governmental information associated with the one or more individuals. 
     
     
         8 . The apparatus of  claim 3 , wherein the processing circuitry is further configured to: generate an adjustment factor based on a previous fall history associated with the one or more individuals, and wherein the adjustment factor adjusts the fall prediction score. 
     
     
         9 . The apparatus of  claim 8 , wherein the adjustment factor is generated by an adjustment factor distinct from both of the static component and the dynamic component. 
     
     
         10 . The apparatus of  claim 1 , wherein the processing circuitry is further configured to: assign a specific resource to an individual of the one or more individuals based on the fall predictor score. 
     
     
         11 . The apparatus of  claim 10 , wherein assignment of resources is further based on a medical profile of the individual. 
     
     
         12 . The apparatus of  claim 1 , wherein at least a portion of the plurality of data is based on one or more pre-determined fillable forms. 
     
     
         13 . The apparatus of  claim 12 , wherein the one or more pre-determined fillable forms contain a value range associated with a medical condition of the one or more individuals. 
     
     
         14 . A computer-implemented method, the method comprising:
 receiving, by one or more computer processors, a first plurality of medical data associated with a first plurality of individuals; and   training, by the one or more computer processors, a machine learning model (MLM) based on the received first plurality of data, such that the trained MLM is able to process a second plurality of medical data associated with a second plurality of individuals and output a score associated with each of the second plurality of individuals, wherein the score is an estimation of a likelihood, respectively, that each of the second plurality of individuals will suffer a fall, and wherein at least a portion of the first plurality of data and a portion of the second plurality of data are based on one or more pre-determined fillable forms associated with a value range.   
     
     
         15 . The computer-implemented method of  claim 14 , wherein the MLM includes at least a static component and a dynamic component. 
     
     
         16 . A non-transitory computer-readable storage medium storing computer-readable program code executable by a processor to:
 apply a machine learning model (MLM) to a plurality of data associated with at least one individual;   compute an initial fall risk score for the at least one individual based on the application of the MLM;   generate a final fall risk score by applying an adjustment factor to the initial fall risk score.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , wherein the MLM includes a dynamic model and a static model. 
     
     
         18 . The non-transitory computer-readable storage medium of  claim 17 , wherein the plurality of data includes i) one or more diagnostic data associated with the at least one individual and ii) one or more medication data associated with the at least one individual. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 17 , wherein the dynamic model includes a neural network. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 17 , wherein one or more outputs of the static model are one or more inputs of the neural network. 
     
     
         21 . The non-transitory computer readable storage medium of  claim 18 , wherein the static model at least partially determines a first set of weights associated with the one or more diagnostic data and the one or more medication data, and wherein the dynamic model at least partially determines another one or more weights associated with the remaining plurality of data. 
     
     
         22 . The non-transitory computer-readable storage medium of  claim 17 , wherein the modified fall risk score is generated by another static model that is distinct from the MLM. 
     
     
         23 . The non-transitory computer-readable storage medium of  claim 16 , wherein the another static model is based on a fall history of the at least one individual. 
     
     
         24 . An apparatus, the apparatus comprising:
 a memory to store instructions; and   processing circuitry, coupled with the memory, operable to execute the instructions, that when executed, cause the processing circuitry to:
 receive a plurality of medical data associated with a plurality of individuals; 
 compute a fall prediction score associated with each of the plurality of individuals based on the received medical data; and 
 allocate one or more resources to each of the plurality of individuals based on the fall prediction computation and a medical profile of each of the plurality of individuals. 
   
     
     
         25 . The apparatus of  claim 24 , wherein the plurality of medical data includes one or more data from one or more predetermined forms, and wherein the one or more predetermined forms include a value range associated with a medical condition. 
     
     
         26 . The apparatus of  claim 25 , wherein the allocated one or more resources includes a brace. 
     
     
         27 . A method comprising:
 receiving a first plurality of data associated with one or more individuals;   applying a hybrid machine learning algorithm to the first plurality of data;   generating an initial score based on an application of the hybrid machine learning algorithm to the first plurality of data;   generating a second score by applying an adjustment factor to the initial score, wherein the adjustment factor is based on a fall history data of the one or more individuals;   receiving a second plurality of data associated with the one or more individuals;   applying another algorithm to the second plurality of data associated with the one or more individuals;   generating a third score based on application of the another algorithm; and   generating a final score based on the second score and the third score, where the final score is a prediction as to whether or not the one or more individuals will sustain a fall.   
     
     
         28 . The method according to  claim 27  further comprising:
 assigning a resource to prevent a fall to the one or more individuals based on the final score. 
 
     
     
         29 . The method according to  claim 28 , wherein the second plurality of data is clinical data associated with the one or more individuals. 
     
     
         30 . The method according to  claim 29 , wherein the hybrid machine learning model includes:
 i) one or more static models and ii) one or more dynamic models and the second algorithm includes one or more static models.