1.
Stud Health Technol Inform
; 310: 1486-1487, 2024 Jan 25.
Article
in English
| MEDLINE
| ID: mdl-38269709
ABSTRACT
Suicide risk models are critical for prioritizing patients for intervention. We demonstrate a reproducible approach for training text classifiers to identify patients at risk. The models were effective in phenotyping suicidal behavior (F1=.94) and moderately effective in predicting future events (F1=.63).