%0 Journal Article %T Predicting suicide attempts and suicide deaths among adolescents following outpatient visits %J Journal of affective disorders %D 2021 %A Penfold, Robert B. %A Johnson, Eric %A Shortreed, Susan M. %A Ziebell, Rebecca A. %A Lynch, Frances L. %A Clarke, Greg N. %A Coleman, Karen J. %A Waitzfelder, Beth E. %A Beck, Arne L. %A Rossom, Rebecca C. %A Ahmedani, Brian K. %A Simon, Gregory E. %V 294 %N %P 39-47 %X BACKGROUND: Few studies report on machine learning models for suicide risk prediction in adolescents and their utility in identifying those in need of further evaluation. This study examined whether a model trained and validated using data from all age groups works as well for adolescents or whether it could be improved.

METHODS: We used healthcare data for 1.4 million specialty mental health and primary care outpatient visits among 256,823 adolescents across 7 health systems. The prediction target was 90-day risk of suicide attempt following a visit. We used logistic regression with least absolute shrinkage and selection operator (LASSO) and generalized estimating equations (GEE) to predict risk. We compared performance of three models: an existing model, a recalibrated version of that model, and a newly-learned model. Models were compared using area under the receiver operating curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value.

RESULTS: The AUC produced by the existing model for specialty mental health visits estimated in adolescents alone (0.796; [0.789, 0.802]) was not significantly different than the AUC of the recalibrated existing model (0.794; [0.787, 0.80]) or the newly-learned model (0.795; [0.789, 0.801]). Predicted risk following primary care visits was also similar: existing (0.855; [0.844, 0.866]), recalibrated (0.85 [0.839, 0.862]), newly-learned (0.842, [0.829, 0.854]). LIMITATIONS: The models did not incorporate non-healthcare risk factors. The models relied on ICD9-CM codes for diagnoses and outcome measurement.

CONCLUSIONS: Prediction models already in operational use by health systems can be reliably employed for identifying adolescents in need of further evaluation.

Language: en

%G en %I Elsevier Publishing %@ 0165-0327 %U http://dx.doi.org/10.1016/j.jad.2021.06.057