I-Corps: Translation potential of an interactive patient data tracking platform for mental health

This I-Corps project is based on the development of an interactive patient data tracking software platform that provides psychological testing and personalized recommendations for mental health resources. Current digital offerings focus on symptom severity but do little or no assessment of patient needs, and minimal matching to resources with no tracking of outcomes. This technology uses a computerized testing protocol to assess the mental health (wellbeing) of an individual in an adaptive but comprehensive way. Based on the patient's profile, the platform tracks and uncovers patterns to provide personalized recommendations, matching users with resources that fit their unique profiles and needs. These resources range from clinical services such as clinical therapy to non-clinical options such as educational videos and peer support. In addition, individuals have control over their data and may track the outcomes. This technology may reduce inefficiencies in the healthcare system, while also gathering real world outcomes data on interventions and improve patient outcomes. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of a mental health platform that aids in mental health assessment, data security, and resources matching to reduce costs and lower morbidity. The technology combines Computerized Adaptive Testing and Item Response Theory (CAT-IRT), distributed ledger (Web3) technology, and machine learning for a referral algorithm to create computerized psychological testing and referral algorithms. The CAT-IRT psychometrics battery assesses domains of wellbeing rather than the traditional standard brief symptom checklist, which is more representative of the needs of the individual, and reduces assessment time. Data security and user control is provided by integration of a distributed ledger technology giving patients control over their data with no one having access without their permission. The machine-learning referral algorithm is designed to offer recommendations for mental health services (clinical and subclinical) based on the psychometric profile of the individual, which continues to iterate as outcomes data is tracked. This technology may reduce the barrier for patients seeking mental health assessment and resources for mental health services. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.