Ecological Momentary Assessment and Machine Learning for Predicting Suicidal Ideation

This is a virtual seminar. For a Zoom link, please see "Venue details". Please consider subscribing to mailing list:

This study aims to understand what extent does the analysis of daily data encompassing mood fluctuations and contextual stressful events effectively predict short- and long-term suicidal ideation in sexual and gender minority individuals. 103 individuals aged 18 to 29 years found that using 25-day ecological momentary assessment yielded acceptable prediction performance on 1-, 3-, and 8-month suicidal ideation. The prediction effect of feelings faded over time, while the prediction effect of contextual events remained strong. The findings suggest a promising future for detecting suicide ideation over time through the analysis of data on specific types of mood fluctuations and contextual events.