# US 10,478,112 B2 · Enhancing diagnosis of disorder through artificial intelligence and mobile health technologies without compromising accuracy > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,478,112 B2 - Document ID: US10478112B2 - Status: Granted - Kind: B2 - Application number: 16/157,787 - Filed: 2018-10-11 - Published: 2019-02-07 - Granted: 2019-11-19 - Earliest claimed: 2011-10-24 - Assignees: President and Fellows of Harvard College - Applicants: President and Fellows of Harvard College - Inventors: Dennis Wall - Web page: https://patentgrep.com/patent/US10478112B2 ## CPC - G16H 40/63: for local operation - A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety} - A61B 5/168: {Evaluating attention deficit, hyperactivity} - A61B 5/7267: {involving training the classification device} - G06F 8/30: Creation or generation of source code - G06N 20/00: Machine learning - G16H 10/20: for electronic clinical trials or questionnaires - G16H 40/67: for remote operation - G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems - G16Z 99/00: Subject matter not provided for in other main groups of this subclass - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G16Z: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR ## Abstract A computer system for generating a diagnostic tool by applying artificial intelligence to an instrument for diagnosis of a disorder, such as autism. For autism, the instrument can be a caregiver-directed set of questions designed for an autism classification tool or an observation of the subject in a video, video conference, or in person and associated set of questions about behavior that are designed for use in a separate autism classification tool. The computer system can have one or more processors and memory to store one or more computer programs having instructions for generating a highly statistically accurate set of diagnostic items selected from the instrument, which are tested against a first test using a technique using artificial intelligence and a second test against an independent source. Also, a computer implemented method and a non-transitory computer-readable storage medium are disclosed. ## Claims ### Claim 1 A computer-implemented method for evaluating an individual for a behavioral disorder, a developmental delay, or a neurological impairment; said method comprising: (a) displaying a plurality of questions relating to said behavioral disorder, said developmental delay, or said neurological impairment; (b) receiving an input comprising a response to at least one of said plurality of questions; (c) generating an output, based on said input, using a software module comprising a classifier trained with data from a plurality of individuals having said behavioral disorder, said developmental delay, or said neurological impairment; wherein said output comprises an indication of whether said behavioral disorder, said developmental delay, or said neurological impairment is present in said individual; and wherein said output has an accuracy of at least 90%. ### Claim 2 (depends on 1) The method of claim 1, wherein said input is provided by a user who is not a clinician. ### Claim 3 (depends on 1) The method of claim 1, further comprising: (a) selecting or capturing a video of said individual; (b) reviewing said video using said software module; and (c) receiving a result of said review, wherein said input comprises said result of said review. ### Claim 4 (depends on 3) The method of claim 3, wherein said result of said review comprises a score generated by said software module based on up to 8 features derived from a subset of features of a clinical assessment instrument. ### Claim 5 (depends on 3) The method of claim 3, wherein said result of said review comprises a report, and wherein said output is further based on said report. ### Claim 6 (depends on 1) The method of claim 1, wherein said output comprises a report indicating a clinical action to be taken based on whether said output comprises an indication that said behavioral disorder, developmental delay, or neurological impairment is present in said individual. ### Claim 7 (depends on 6) The method of claim 6, wherein said report comprises at least one of the following: a link to a video of said individual, at least one chart depicting results of said report, a list of facilities or clinicians that are capable of performing said clinical action, or a map depicting locations of said facilities or clinicians that are capable of performing said clinical action. ### Claim 8 (depends on 1) The method of claim 1, wherein said at least one of said plurality of questions corresponds to at least one feature from a clinical assessment instrument. ### Claim 9 (depends on 8) The method of claim 8, wherein said plurality of questions consists of no more than 40 questions corresponding to the at least one feature from said clinical assessment instrument. ### Claim 10 (depends on 1) The method of claim 1, wherein said statistical accuracy is determined by testing an algorithm that generates said output against an independent source of clinical data. ### Claim 11 (depends on 10) The method of claim 10, wherein testing said algorithm comprises comparing an output provided by said algorithm to an output provided by a clinical assessment instrument for at least 100 independent autistic subjects. ### Claim 12 (depends on 10) The method of claim 10, wherein said algorithm has a statistical accuracy of at least 95%. ### Claim 13 (depends on 1) The method of claim 1, wherein said method is implemented using a smart device-based user interface or a web-based user interface. ### Claim 14 (depends on 1) The method of claim 1, wherein said output is generated by evaluating said input with said software module to generate a final score indicative of whether said output comprises an indication that said behavioral disorder, developmental delay, or neurological impairment is present in said individual. ### Claim 15 (depends on 14) The method of claim 14, wherein said software module comprises a non-linear machine learning algorithm. ### Claim 16 (depends on 14) The method of claim 14, wherein said software module comprises a machine learning algorithm comprising at least one of ADTree, BFTree, ConjunctiveRule, DecisionStump,Filtered Classifier, FT, J48, J48graft, JRip, LADTree, LMT, NNge, OneR, OrdinalClassClassifier, Random Tree, REPTree, PART, Ridor or SimpleCart. ### Claim 17 (depends on 1) The method of claim 1, comprising treating said individual for said behavioral disorder, developmental delay, or said neurological impairment for which said indication is generated. ### Claim 18 (depends on 1) The method of claim 1, wherein said data comprises responses to said plurality of questions. ### Claim 19 (depends on 18) The method of claim 18, wherein said responses are to a clinical assessment instrument.