Using Integrative Data Mining to Improve the Prediction of Suicide: An Initial Application
Co-PI: Dr. Ross Jacobucci
This pilot study funded by the Notre Dame Advanced Diagnostics and Therapeutics Discovery Fund aims to identify important correlates and improve prediction of distinct suicide outcomes. Through the combination of machine learning and data integration, our goal is to elucidate the relationship between risk factors at multiple levels of analysis and the occurrence of suicidal ideation, plans, and attempts.
A Multimodal Emergency Department Investigation: Improve Prospective Prediction of Suicide Risk and Recidivism of Psychiatric Visits for Patients in Suicidal Crisis
PI: Dr. Chadd Kraus
This project funded by the Geisinger Healthcare System (and conducted with Geisinger collaborators) aims to utilize electronic medical records, in addition to explicit and implicit measures of symptomatology during patient emergency department visits, to prospectively predict return emergency department visits and suicidal thoughts and behaviors. Results have the potential to improve current suicide risk assessment and treatment planning, optimizing patient care while conserving resources.
Examining the Role of Interpersonal Relationships and Self-Disclosure in Self-Injurious Thoughts and Behavior
This project investigates the factors that influence the self-disclosure of suicidal and non-suicidal thoughts and behaviors. Further, we are interested in the role of interpersonal relationships and social reactions upon disclosures in treatment seeking among high-risk populations.