Circuit Dynamics Underlying Longitudinal Fluctuations in Mood and Cognition in Bipolar Patients

Research on bipolar illness is hampered by a lack of basic understanding of the course of dynamic circuit properties in living individuals that might underlie fluctuations in mood and cognition. We will study a cohort of 30 individuals with well-characterized bipolar affective illness over the course of one year, combining mobile behavioral tracking technology with neuroimaging. This will enable us to collect data on environmental variables and structural brain anatomy/functional network architecture.

Intensive Real-Time Computational Phenotyping in Individuals with Borderline Personality Disorder

The goal of this study is to use various methods of digital phenotyping to characterize the course of symptoms, behaviors, and contextual factors in individuals with BPD and related conditions. By examining facial, gestural and acoustic features derived from clinical interviews with BPD patients, we hope to characterize changes in interaction dynamics in relation to clinically significant behavioral and illness changes within these same individuals. We hope to use all of this data to identify putative causal relationships between symptom/syndromic change in relation to environmental changes.

Capturing Longitudinal Fluctuations in Behavior, Mood, and Cognition in Patients with Obsessive-Compulsive Disorder

While substantial prior research has provided valuable insights into the underlying neurobiology of OCD, most studies of neuropsychiatric signs and symptoms have focused on either clinician-report or self-report measures, or have employed neuropsychological tests or cognitive neuroscience tasks, as the behavioral readout with which to correlate biological findings. We aim to use technology to target individual patients by revealing behavioral abnormalities using actigraphy signals.

Detecting Activity During Mental Health Hospitalization Using Wearable Devices

Inpatient psychiatric treatment settings provide care for individuals with a range of behavioral disturbances and psychopathology, which often manifests as profound alterations in the amount and nature of physical behavior. We aim to establish an efficient and consistent process to identify clinically significant levels of physical activity (e.g., sleep, restlessness, agitation) that could both prove useful for quantifying the overall level treatment success or failure in an individual patient, while also eventually providing realtime support for clinical staff on the unit.

Feasibility and Clinical Utility of MultiSense for Nonverbal Feature Extraction in Psychosis

Determining when a patient is ready for discharge is an open problem, as currently 20% of those hospitalized for psychiatric illness will be hospitalized again within 30 days. To address this issue, we are working to identify behavioral biomarkers for severe mental illness in inpatients hospitalized for psychosis at McLean. The Multisense project is a collaboration with Dr. Louis-Philippe Morency’s team at Carnegie Mellon University, where information is extracted from both audio and video of both clinician and patient during a series of semi-structured inpatient interviews. Multimodal analysis techniques are used both to predict clinical scale and discharge-readiness scores, as well as to visualize a summary of each interview and extract relevant interpretable features.