RAISR4D Suicide

PROSODIC: Predictive Intelligence for Secondary Prevention of Youth Suicide

23/05/2026

AI Summary

Interpretable machine learning model using routine clinical and sociodemographic data predicted first suicide reattempts in youths; Logistic Regression achieved best performance (AUC-ROC 0.65).
Three-level graded risk scale guides clinical action; key predictors were social vulnerability, behavioural dysregulation and care discontinuity.
Single-site data and moderate discriminative performance limit generalisability; future multisite validation planned to enhance robustness and real-world integration.

Stud Health Technol Inform. 2026 May 21;336:715-719. doi: 10.3233/SHTI260264.

ABSTRACT

Suicide is currently the leading cause of preventable death among young people, yet early identification of reattempt risk remains limited by its multifactorial nature, stigma, fragmented data, reliance on subjective assessments, and heavy workloads. The PROSODIC project developed an interpretable machine learning model to predict first suicide reattempts among youths, using routinely collected clinical and sociodemographic data from 1,031 patients in Seville, Spain, aged 5-25 years. Logistic Regression achieved the best performance (AUC-ROC = 0.65), balancing accuracy and interpretability. A three-level graded risk scale was derived to guide clinical action. Results highlight social vulnerability, behavioral dysregulation, and care discontinuity as key predictors, supporting the model’s clinical relevance and feasibility for integration into real-world suicide secondary prevention pathways. Limitations include the use of single-site data and moderate discriminative performance; however, future work will extend validation across additional regions to enhance generalizability and robustness.

PMID:42174939 | DOI:10.3233/SHTI260264

Document this CPD