LemurDx - Objectivity,precision, and clinical utility in hyperactivity measurement for childhood ADHD using smartwatches and machine learning algorithms.

Project SummaryAbstract ADHD is the most common behavioral diagnosis in early childhoodaffecting aroundof all American childrenAlthough hyperactivity is a core symptom of ADHDthere are no objective measures that are widely used in practice settingsLemurDx is a concept for a software system for smartwatches and mobile tabletsoptimized for clinical usethat uses state of the artyet relatively low costsensor technology to measure hyperactivitywith the clinical goal of differentiating children with ADHD hyperactive presentation or ADHD combined presentation from children with typical levels of activityLemurDx will passively collect data from smartwatch sensorsClinicians will ask a child to wear a smartwatch with the LemurDx application for one day and then collect the de identified dataThe data will be transmitted to a HIPAA compliant secure serverMachine learningMLalgorithms will be used to differentiate children with clinical levels of hyperactivity from those with typical levels of activityproviding clinicians with immediate resultsLemurDx is superior to research focused tools such as traditional actigraphy in a number of waysAlong with the improved precision afforded by modern smartwatch sensorsmany of which are not available on actigraphy devicesand machine learningMLalgorithmsthe team is carefully designing a complete system based on the unique needs of cliniciansThis includes a comprehensive system of secure HIPAA compliant serversautomated state of theart ML algorithmspre programmed mobile tablets and smartwatches for clinical usea secure and deidentified data architectureand a simple user interface that eliminates any technological burden on cliniciansAimof the project is to develop a commercial grade prototype of LemurDx following principles of usercentered designwith feedback from focus groups including childrenparentsand cliniciansAimof the project is to test the feasibility of collectingstoringand analyzing data fromchildrenageswho will wear a smartwatch with LemurDx technology for one dayAimof the project is to test and refine several ML algorithms to achieve a high level of sensitivity and specificity to accurately classify children with and without ADHDLemurDx is significant as there is no objective and commercially available measure of hyperactivity to assist in the diagnosis of ADHDdespite a great need in settings including pediatric primary care practiceschildren s hospitalsand behavioral health clinicsThe project is consistent with NICHD s mission to ensurethat all children have the chance to achieve their full potential for healthy and productive livesInnovations include a combination of reliableinexpensive measurement technology combined with accurate ML algorithms to consistently and objectively measure hyperactivity in a system that is designed for clinical usersWe will show that LemurDx has commercialization potential by demonstrating accuracycost effectivenessand user adherenceand will lay the foundation for the development of a scalable clinical delivery system Project Narrative ADHD is the most common behavioral diagnosis in early childhood affecting aroundof all American childrenAlthough hyperactivity is a core symptom of ADHDthere are no objective measures that are widely used in practice settings that can assist in accurate diagnosticsThis project will develop a prototype for a software system for smartwatches to measure hyperactivity with objectivity and precision using state of the art sensors and machine learning algorithms