Indirect, machine learning-based suicide risk screening : evidence from cross-national validation

Rus Prelog, Polona (avtor), Rojnić Kuzman, Martina (avtor), Matić, Teodora (avtor), Pregelj, Peter (avtor), Medved, Sara (avtor), Bjedov, Sarah (avtor), Rojnic Palavra, Irena (avtor), Petek Eric, Anamarija (avtor), Drmic, Stipe (avtor), Vidovic, Domagoj (avtor), Sadikov, Aleksander (avtor)

Background: Suicide is a major public health challenge requiring early detection of suicidal ideation (SI). Traditional direct questioning methods suffer from stigma and disclosure bias, failing to identify many at-risk individuals. While machine learning (ML) models show promise, most lack external validation. Indirect screening, using psychosocial data rather than direct SI questions, offers a scalable alternative. This study aimed to externally validate an indirect, ML-based SI screening tool. We tested if a model trained on a Slovenian general population sample retained predictive accuracy when applied to an independent Croatian sample during a period of societal stress (pandemic and earthquakes), assessing performance across age and gender subgroups. Methods: A logistic regression model was trained on a Slovenian sample (N = 2,989) and validated on a Croatian sample (N = 2,364). The model used only indirect predictors, including sociodemographics, life satisfaction, behavioral changes, and Brief COPE subscales. The target outcome was the presence of SI (SIDAS score > 0). Performance was measured by the area under the receiver operating characteristic curve (AUROC). Results: The model demonstrated strong external validity on the entire Croatian sample, achieving an AUROC of 0.80. Performance remained robust across subgroups: males (AUROC = 0.83), females (AUROC = 0.79), younger adults (AUROC = 0.77), and older adults (AUROC = 0.81). Self-blame, behavioral disengagement, and relationship dissatisfaction were key predictors. Conclusions: An indirect, ML-based screening tool can reliably identify SI risk in the general population. The model demonstrated strong cross-national transferability and resilience during a societal crisis, proving it is a feasible and valid strategy for population-level prevention.

• Jezik: Angleški jezik
• Ključne besede: machine learning, mass screening, risk assessment, suicidal ideation
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: MF - Medicinska fakulteta
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Datum objave: 01.02.2026
• Leto izida: 2026
• Št. strani: 8 str.
• Številčenje: Vol. 69, iss. 1, art. e31
• PID: 20.500.12556/RUL-181423
• UDK: 616.89
• ISSN pri članku: 1778-3585
• DOI: 10.1192/j.eurpsy.2026.10166
• COBISS.SI-ID: 271787011
• Datum objave v RUL: 07.04.2026

Gradivo je del revije

• Naslov: European psychiatry
• Založnik: Éditions scientifiques et médicales Elsevier
• ISSN: 1778-3585
• COBISS.SI-ID: 23139845

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: strojno učenje, množično presejanje, ocena tveganja, samomorilne misli

Projekti

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: P2-0209-2022
• Naslov: Umetna inteligenca in inteligentni sistemi