Predicting future onset of depression among middle-aged adults with no psychiatric history.
Yonatan BiluNir KalksteinEva Gilboa-SchechtmanPinchas AkivaGil ZalsmanLiat ItzhakyDana Atzil SlonimPublished in: BJPsych open (2023)
Machine-learning approaches show potential for being beneficial for the identification of clinically relevant predictors of depression. Specifically, we can identify, with moderate success, people with no recorded psychiatric history as at risk for depression by using a relatively small number of features. More work is required to improve these models and evaluate their cost-effectiveness before integrating them into the clinical workflow.