Methods and apparatus for evaluating developmental conditions and providing control over coverage and reliability

Abstract

The methods and apparatus disclosed herein can evaluate a subject for a developmental condition or conditions and provide improved sensitivity and specificity for categorical determinations indicating the presence or absence of the developmental condition by isolating hard-to-screen cases as inconclusive. The methods and apparatus disclosed herein can be configured to be tunable to control the tradeoff between coverage and reliability and to adapt to different application settings and can further be specialized to handle different population groups.

What is claimed is: 
     
         1 . A computer-implemented method for determining a treatment for an individual for a neurological disorder, said method comprising:
 (a) receiving data of said individual related to said neurological disorder; and   (b) evaluating said data using at least one classifier to select at least one therapeutic agent for treating said neurological disorder.   
     
     
         2 . The method of  claim 1 , wherein said at least one therapeutic agent comprises a stimulant or antipsychotic drug for treating said neurological disorder. 
     
     
         3 . The method of  claim 1 , wherein said at least one therapeutic agent comprises amphetamine or an amphetamine-derived drug. 
     
     
         4 . The method of  claim 1 , wherein said at least one therapeutic agent is selected from the group consisting of risperidone, quetiapine, amphetamine, dextroamphetamine, methylphenidate, methamphetamine, dextroamphetamine, dexmethylphenidate, guanfacine, atomoxetine, lisdexamfetamine, clonidine, and aripiprazole, and modafinil. 
     
     
         5 . The method of  claim 1 , wherein said neurological disorder is selected from the group consisting of autism spectrum disorder, attention deficit disorder, attention deficit hyperactivity disorder, and dyslexia. 
     
     
         6 . The method of  claim 1 , wherein said data comprises active data generated from at least one active data source and passive data generated from at least one passive data source. 
     
     
         7 . The method of  claim 6 , wherein said passive data comprises passive data streams from user interactions with at least one of an activity, game, mobile device or application, smart toy, wearable sensor, and activity monitor. 
     
     
         8 . The method of  claim 1 , wherein said data comprises information acquired from at least one of genetic data, floral data, a sleep monitor, and eye tracking of said individual. 
     
     
         9 . The method of  claim 1 , wherein said data comprises at least one of demographic data and answers to a set of diagnostic questions. 
     
     
         10 . The method of  claim 1 , wherein said at least one classifier comprises an assessment model for providing an evaluation result based on said data, wherein said evaluation result is a first categorical determination or a first inconclusive determination with respect to a presence or absence of said neurological disorder. 
     
     
         11 . The method of  claim 10 , wherein said first categorical determination for said presence or absence of said neurological disorder in said individual is based on a specified sensitivity and a specified specificity. 
     
     
         12 . The method of  claim 10 , wherein said at least one classifier comprises a subset of a plurality of tunable machine learning models. 
     
     
         13 . The method of  claim 12 , further comprising:
 (a) requesting additional data when said evaluation result comprises said first inconclusive determination; and   (b) generating a second categorical determination or a second inconclusive determination based on said additional data using at least one additional machine learning model selected from said plurality of tunable machine learning models.   
     
     
         14 . The method of  claim 12 , further comprising:
 (a) combining scores for each of said subset of said plurality of tunable machine learning models to generate a combined preliminary output score; and   (b) mapping said combined preliminary output score to said first categorical determination or to said first inconclusive determination for said presence or absence of said neurological disorder in said individual.   
     
     
         15 . The method of  claim 1 , wherein said at least one classifier comprises a chain of classifiers for providing an evaluation result for said neurological disorder based on said data. 
     
     
         16 . The method of  claim 15 , wherein said chain of classifiers comprises a first classifier that generates a first output based on said data and a second classifier that generates a second output based on said first output. 
     
     
         17 . The method of  claim 1 , wherein said at least one classifier comprises a therapeutic model for selecting said at least one therapeutic agent. 
     
     
         18 . The method of  claim 17 , wherein said at least one classifier generates a personal therapeutic treatment plan for said individual. 
     
     
         19 . The method of  claim 18 , further comprising receiving feedback data based on performance of said personal therapeutic treatment plan and updating said personal therapeutic treatment plan based on said feedback data. 
     
     
         20 . The method of  claim 18 , wherein said personal therapeutic treatment plan comprises a drug therapy and digital therapeutics.