ARGUS-MDS: automated, quantitative and scalable system for social processes in behavioral health

Argus Cognitive STTR Grant Application Abstract Standardized behavioral observation methods are integral to developmentaleducationaland behavioral science researchHoweverexisting observational strategies are too laborious to use in large scaleintervention and dissemination trials needed in autism spectrum disorderASDIn additioncurrent observational strategies do not yield sufficiently quantitativecomparable and granular assessment that could drive the comparison of therapies in clinical trials or the optimization and personalization of interventionWe are developing a minimally intrusive medical device technologyARGUS MDSto simultaneously monitor multiple key social and problem behaviors in individuals with ASD and related neurodevelopmental disordersNDDsOur team represents an essential collaboration between computer and clinical scientists with expertise in artificial intelligenceAINDDsdiagnosticsmulti modal interventionsand psychometricsWe seek support in the form of a Fast Track STTR grant to validate the psychometric properties of ARGUS MDS and its ability to provide data on change in target behaviors in early childhood and school aged childrenThis would then support the development of a scalabledigital treatment progress indicator for behaviors reflecting socialrepetitive behaviorand associated symptom profiles in ASDIn Phase Ivideo and audio data will be collected during gold standard diagnostic evaluations individuals with ASDnAimwill establish quality and clinical validity of ARGUS MDS algorithms for key social communication behaviorswhile Aimwill evaluate test retest reliability of biometric outputPhase I will show that ARGUS MDS meets quality metrics for biometric outputvalidates the cliniciantechnician feedback systemand establishes intraclass correlation coefficients for automated social communicationAutoSCoutputIn Phase II our focus shifts to establishing psychometric properties of derived scores for AutoSC analysisevaluating convergence with established clinical and functional measuresand preparing for regulatory filing in Phase IIIAimwill develop scores from biometric data through exploratory and confirmatory factor analyses of social communication behaviorsAimevaluates correspondence of AutoSC scores to scores on standardized clinical assessmentsAimdevelops a comprehensive Validation Strategy and executes Analytical Validationper medical device design control regulation and FDA guidancePhase II will develop scores from AutoSC outputevaluate measurement characteristics of AutoSC scoresreliability andampvalidity of Autos SC scoresand executes all Analytical Validations per the strategy document and FDA guidancePhase I and II milestones will set us up for commercialization in Phase IIIincluding filing for regulatory approval and product launchSuccessful completion of this project will provide a novelscalable medical device technology to support objectiveautomated clinical evaluations of social impairments in ASD and other NDDs Argus Cognitive STTR Grant Application NARRATIVE We seek to contribute to the digital health movement through validation of a minimally intrusive monitoring systemARGUS MDSto simultaneously track multiple key social and problem behaviors in individuals with ASD and related neurodevelopmental disordersNDDsincluding Fragile X SyndromeFXSThis new technology will make diagnosis and monitoring of these disorders quantitativescalableand affordableremoving a serious bottleneck in the current patient journeyrelated tothe limited availability of highly trained human experts andthe qualitative and subjective nature of the results attained with current observational strategiesUsing advanced video and audio analytics and machine learningARGUS MDS achieves an automatedquantitativeand comprehensive assessment of each patientacross settingsclinical trialsacademic researchspecialty clinicspediatric offices and homeswithout requiring the presence of a human expert during the monitored diagnosticmonitoring or therapy sessions