Meytal Grimland, Joy Benatov, Hadas Yeshayahu, Daniel Izmaylov, Avi Segal, Kobi Gal, Yossi Levi-Belz
{"title":"Predicting suicide risk in real-time crisis hotline chats integrating machine learning with psychological factors: Exploring the black box.","authors":"Meytal Grimland, Joy Benatov, Hadas Yeshayahu, Daniel Izmaylov, Avi Segal, Kobi Gal, Yossi Levi-Belz","doi":"10.1111/sltb.13056","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>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.</p><p><strong>Method: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Limitations: </strong>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.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":39684,"journal":{"name":"Suicide and Life-Threatening Behavior","volume":" ","pages":"416-424"},"PeriodicalIF":2.7000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Suicide and Life-Threatening Behavior","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/sltb.13056","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/12 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 0
Abstract
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.
期刊介绍:
An excellent resource for researchers as well as students, Social Cognition features reports on empirical research, self-perception, self-concept, social neuroscience, person-memory integration, social schemata, the development of social cognition, and the role of affect in memory and perception. Three broad concerns define the scope of the journal: - The processes underlying the perception, memory, and judgment of social stimuli - The effects of social, cultural, and affective factors on the processing of information - The behavioral and interpersonal consequences of cognitive processes.