Predicting suicide risk in real‐time crisis hotline chats integrating machine learning with psychological factors: Exploring the black box
Suicide and Life-Threatening Behavior · 2024-06 · 54 (3) · 416-424
DOI: 10.1111/sltb.13056 ↗Kurz gefasst
Fachartikel in der Zeitschrift Suicide and Life-Threatening Behavior, online erschienen am 12.02.2024. Verfasst von Meytal Grimland und 6 weiteren Autor:innen. Beteiligte Einrichtung: Lior Tsfaty Center for Suicide and Mental Pain Studies, Ruppin Academic Center, Emek Hefer, Israel. Hauptthemen laut MEDLINE: Machine Learning, Suicide, Hotlines. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Israel Science Foundation.
Abstract (Originalsprache)
Background
This study addresses the suicide risk predicting challenge by exploring the predictive ability of machine learning (ML) models integrated with theory‐driven psychological risk factors in real‐time crisis hotline chats. More importantly, we aimed to understand the specific theory‐driven factors contributing to the ML prediction of suicide risk.
Method
The dataset consisted of 17,654 crisis hotline chat sessions classified dichotomously as suicidal or not. We created a suicide risk factors‐based lexicon (SRF), which encompasses language representations of key risk factors derived from the main suicide theories. The ML model (Suicide Risk‐Bert; SR‐BERT) was trained using natural language processing techniques incorporating the SRF lexicon.
Results
The results showed that SR‐BERT outperformed the other models. Logistic regression analysis identified several theory‐driven risk factors significantly associated with suicide risk, the prominent ones were hopelessness, history of suicide, self‐harm, and thwarted belongingness.
Limitations
The lexicon is limited in its ability to fully encompass all theoretical concepts related to suicide risk, nor to all the language expressions of each concept. The classification of chats was determined by trained but non‐professionals in metal health.
Conclusion
This study highlights the potential of how ML models combined with theory‐driven knowledge can improve suicide risk prediction. Our study underscores the importance of hopelessness and thwarted belongingness in suicide risk and thus their role in suicide prevention and intervention.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Lior Tsfaty Center for Suicide and Mental Pain Studies, Ruppin Academic Center, Emek Hefer, Israel.
- Shalvata Mental Health Center, Hod Hasharon, Israel.
- Department of Special Education, University of Haifa, Haifa, Israel.
- Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel.
- School of Informatics, University of Edinburgh, Edinburgh, UK.
- Department of Behavioral Sciences, Ruppin Academic Center, Emek Hefer, Israel.
Förderung
- Israel Science Foundation
Zitieren
APA
Grimland, M., Benatov, J., Yeshayahu, H., Izmaylov, D., Segal, A., Gal, K., & Levi-Belz, Y. (2024). Predicting suicide risk in real‐time crisis hotline chats integrating machine learning with psychological factors: Exploring the black box. Suicide and Life-Threatening Behavior, 54(3), 416-424. https://doi.org/10.1111/sltb.13056
Vancouver
Grimland M, Benatov J, Yeshayahu H, Izmaylov D, Segal A, Gal K, et al. Predicting suicide risk in real‐time crisis hotline chats integrating machine learning with psychological factors: Exploring the black box. Suicide and Life-Threatening Behavior. 2024;54(3):416-424. doi:10.1111/sltb.13056
BibTeX
@article{Grimland2024,
author = {Grimland, Meytal and Benatov, Joy and Yeshayahu, Hadas and Izmaylov, Daniel and Segal, Avi and Gal, Kobi and Levi-Belz, Yossi},
title = {Predicting suicide risk in real‐time crisis hotline chats integrating machine learning with psychological factors: Exploring the black box},
journal = {Suicide and Life-Threatening Behavior},
year = {2024},
volume = {54},
number = {3},
pages = {416--424},
doi = {10.1111/sltb.13056}
}
EUVIMED