Systems and methods for generating health predictor models

Abstract

A statistical processing system includes a server operably configured with program instructions implementing a plurality of statistical models to at least one of (a) predict a health outcome based on questionnaire responses, (b) assist a patient's choice of therapeutic modality based on questionnaire responses, and (c) assess a health risk or status based on questionnaire responses. Also provided is a research agency communicating with the server and contracted to provide the statistical models using a visual interface communicated by the server. The server is configured to analyze requests received from users relating to a plurality of said statistical models to reduce redundancy in requests for patient data.

What is claimed is: 
     
         1 . A method of generating a health predictor model, the method comprising:
 identifying types of health status information, demographic information, and clinical information;   generating, by a computer system, an electronic survey to collect the identified types of health status information, demographic information, and clinical information, wherein the electronic survey comprises:
 (a) a human-readable interface or 
 (b) a machine-readable interface; 
   and wherein the electronic survey is dynamically generated one or more times by a rendering engine based upon the identified types of health status information, demographic information, and clinical information;   collecting, by a computer system, the identified types of health status information, demographic information, and clinical information using the electronic survey;   identifying potentially significant predictors of future health states based at least in part on information collected using the electronic survey;   generating a predictor model of future health states using the identified potentially significant predictors of future health states.   
     
     
         2 . The method as defined in  claim 1 , the method further comprising:
 executing the generated predictor model to generate predictor results;   generating treatment recommendations based at least in part on the generated predictor results obtained from executing the generated predictor model;   wherein identifying potentially significant predictors of future health states based at least in part on information collected using the survey comprises calculating univariate statistics to identify potentially significant predictors of future health states, and   wherein the types of clinical information collected using the survey include adverse outcomes and positive outcomes, including hospitalizations.   
     
     
         3 . The method as defined in  claim 1 , wherein the electronic survey comprises a structured form encoded with a markup language. 
     
     
         4 . The method as defined in  claim 1 , wherein the electronic survey comprises a structured form encoded with Extensible Markup Language (XML). 
     
     
         5 . The method as defined in  claim 1 , the method further comprising:
 executing the generated predictor model using the computer system to generate predictor results.   
     
     
         6 . The method as defined in  claim 1 , the method further comprising:
 generating treatment recommendations by the computer system based at least in part on generated predictor results obtained from executing the generated predictor model.   
     
     
         7 . The method as defined in  claim 1 , the method further comprising generating treatment recommendations for a first patient using the generated predictor model. 
     
     
         8 . The method as defined in  claim 1 , wherein identifying potentially significant predictors of future health states based at least in part on information collected using the survey comprises calculating univariate statistics to identify potentially significant predictors of future health states. 
     
     
         9 . The method as defined in  claim 1 , wherein collecting the identified types of health status information, demographic information, and clinical information using the survey, comprises collecting the identified types of health status information, demographic information, and clinical information using a web form. 
     
     
         10 . The method as defined in  claim 1 , wherein collecting the identified types of health status information, demographic information, and clinical information using the survey, comprises collecting the identified types of health status information, demographic information, and clinical information via the electronic survey from a plurality of databases associated with respective third-party systems and/or entities. 
     
     
         11 . The method as defined in  claim 1 , wherein the types of clinical information collected using the survey include adverse outcomes and positive outcomes. 
     
     
         12 . The method as defined in  claim 1 , wherein the types of clinical information collected using the survey includes presence of diabetes. 
     
     
         13 . The method as defined in  claim 1 , wherein the types of clinical information collected using the survey includes a patient's age. 
     
     
         14 . The method as defined in  claim 1 , wherein the types of clinical information collected using the survey includes a patient's gender. 
     
     
         15 . The method as defined in  claim 1 , wherein the types of clinical information collected using the survey includes hospitalizations. 
     
     
         16 . The method as defined in  claim 1 , the method further comprising using one or more generated predictor models of future health states to compare outcomes of different medical treatments. 
     
     
         17 . A health predictor model generation system, comprising:
 at least one processing device;   non-transitory media storing program instructions that when executed by the at least one processing device are configured to cause the at least one processing device to perform operations, comprising:
 identifying types of health status information, demographic information, and clinical information; 
 generating an electronic survey to collect the identified types of health status information, demographic information, and clinical information, wherein the electronic survey comprises:
 (c) a human-readable interface or 
 (d) a machine-readable interface; 
 
 and wherein the electronic survey is dynamically generated one or more times by a rendering engine based upon the identified types of health status information, demographic information, and clinical information; 
 collecting the identified types of health status information, demographic information, and clinical information using the electronic survey; 
 identifying potentially significant predictors of future health states based at least in part on information collected using the electronic survey; 
 generating a predictor model of future health states using the identified potentially significant predictors of future health states. 
   
     
     
         18 . The system as defined in  claim 17 , the operations further comprising:
 executing the generated predictor model to generate predictor results;   generating treatment recommendations for a first patient using the generated predictor model;   wherein identifying potentially significant predictors of future health states based at least in part on information collected using the survey comprises calculating univariate statistics to identify potentially significant predictors of future health states, and   wherein the types of clinical information collected using the survey include adverse outcomes and positive outcomes, including hospitalizations.   
     
     
         19 . The system as defined in  claim 17 , wherein the electronic survey comprises a structured form encoded with a markup language. 
     
     
         20 . The system as defined in  claim 17 , wherein the electronic survey comprises a structured form encoded with Extensible Markup Language (XML). 
     
     
         21 . The system as defined in  claim 17 , the operations further comprising:
 executing the generated predictor model to generate predictor results.   
     
     
         22 . The system as defined in  claim 17 , the operations further comprising:
 generating treatment recommendations based at least in part on generated predictor results obtained from executing the generated predictor model.   
     
     
         23 . The system as defined in  claim 17 , the operations further comprising generating treatment recommendations for a first patient using the generated predictor model. 
     
     
         24 . The system as defined in  claim 17 , wherein identifying potentially significant predictors of future health states based at least in part on information collected using the survey comprises calculating univariate statistics to identify potentially significant predictors of future health states. 
     
     
         25 . The system as defined in  claim 17 , wherein collecting the identified types of health status information, demographic information, and clinical information using the survey, comprises collecting the identified types of health status information, demographic information, and clinical information using a web form. 
     
     
         26 . The system as defined in  claim 17 , wherein collecting the identified types of health status information, demographic information, and clinical information using the survey, comprises collecting the identified types of health status information, demographic information, and clinical information via the electronic survey from a plurality of databases associated with respective third-party systems and/or entities. 
     
     
         27 . The system as defined in  claim 17 , wherein the types of clinical information collected using the survey include adverse outcomes and positive outcomes. 
     
     
         28 . The system as defined in  claim 17 , wherein the types of clinical information collected using the survey includes hospitalizations. 
     
     
         29 . The system as defined in  claim 17 , the operations further comprising using one or more generated predictor models of future health states to compare outcomes of different medical treatments. 
     
     
         30 . Non-transitory media storing program instructions that when executed by the at least one processing device are configured to cause the at least one processing device to perform operations, comprising:
 identifying types of health status information, demographic information, and clinical information;   generating an electronic survey to collect the identified types of health status information, demographic information, and clinical information, wherein the electronic survey comprises:
 (e) a human-readable interface or 
 (f) a machine-readable interface; 
   and wherein the electronic survey is dynamically generated one or more times by a rendering engine based upon the identified types of health status information, demographic information, and clinical information;   collecting the identified types of health status information, demographic information, and clinical information using the electronic survey;   identifying potentially significant predictors of future health states based at least in part on information collected using the electronic survey;   generating a predictor model of future health states using the identified potentially significant predictors of future health states.