This technology is a hardware and software platform for the digital phenotyping of mental health states that synchronizes neural recordings, wearable sensors, and smartphone data.
Current methods to assess and diagnose mental health and psychiatric state rely on subjective patient self-assessments, interviews, and physician interpretation, which can be time-consuming and lead to inaccurate diagnoses. While digital and offline platforms show promise in monitoring physiological and behavioral states, accurately phenotyping mental health based on high-dimensional, multimodal data remains challenging. At present, no platforms exist that can analyze multimodal patient data to provide accurate assessments and diagnoses for anxiety, depression, and other related psychiatric disorders.
This technology is a digital phenotyping platform that collects physiological and behavioral data from patients and uses a machine learning algorithm to predict and assess psychiatric state. The hardware and software platform integrates and synchronizes neural recordings, wearable sensors, smartphone data, and environmental context to perform predictive, high-dimensional phenotyping. This approach improves upon current subjective assessments of mental health by leveraging multimodal data to predict anxiety levels, cognitive performance, and human behavior. Ultimately, this technology has the potential to improve treatment outcomes for psychiatric illnesses and mental health disorders.
Joshua Jacobs, Ph.D.
Brett Youngerman, M.D.
Patent Pending
IR CU24388
Licensing Contact: Dovina Qu