TY  - JOUR
PY  - 2024//
TI  - A reproducible model based on clinical text for predicting suicidal behavior
JO  - Studies in health technology and informatics
A1  - Obeid, Jihad S.
A1  - Tsalatsanis, Athanasios
A1  - Chaphalkar, Chaitanya
A1  - Robinson, Sara
A1  - Klein, Sierra
A1  - Cool, Sarah
A1  - Szwast, Elizabeth
A1  - Bunnell, Brian E.
SP  - 1486
EP  - 1487
VL  - 310
IS  - 
N2  - 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).<p />  <p>Language: en</p>
LA  - en
SN  - 0926-9630
UR  - http://dx.doi.org/10.3233/SHTI231257
ID  - ref1
ER  -