Project Grant R01MH143822

The National Institute of Mental Health awarded The General Hospital Corporation (Massachusetts General Hospital) $824,404 on September 1, 2026, under the Mental Health Research Grants program (CFDA 93.242) to develop machine learning models that integrate clinician-conducted suicide risk assessments with electronic health record data to improve prediction of suicidal behavior and guide precision interventions in outpatient behavioral health settings.

The research leverages routine clinical suicide risk assessment (SRA) data—including clinicians' overall risk judgments, patients' documented suicidal thoughts and behaviors, and identified risk and protective factors—combined with EHR-derived information such as diagnostic codes, laboratory results, and medications. Prior work by the recipient team analyzed more than 600,000 SRAs completed at point of care in outpatient settings and achieved high accuracy (AUC=0.88) when predicting suicide attempt within six months. This award funds integration of clinician SRA features into validated EHR-based statistical models to enhance prediction accuracy and clinical utility for identifying patients requiring additional suicide prevention interventions.

Place of performance is Boston, Massachusetts. The period of performance runs from September 1, 2026, through May 31, 2031. This is a Project Grant, the standard assistance type for investigator-initiated research under NIMH's mental health research portfolio.