Suicidal behaviour prediction models using machine learning techniques: A systematic review.

Autor: Nordin N; School of Computer Sciences, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia. Electronic address: noratikahnordin@student.usm.my., Zainol Z; School of Computer Sciences, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia. Electronic address: zuri@usm.my., Mohd Noor MH; School of Computer Sciences, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia. Electronic address: halimnoor@usm.my., Chan LF; Department of Psychiatry, Faculty of Medicine, National University of Malaysia (UKM) 56000 Cheras, Wilayah Persekutuan Kuala Lumpur, Malaysia.
Jazyk: angličtina
Zdroj: Artificial intelligence in medicine [Artif Intell Med] 2022 Oct; Vol. 132, pp. 102395. Date of Electronic Publication: 2022 Sep 06.
DOI: 10.1016/j.artmed.2022.102395
Abstrakt: Background: Early detection and prediction of suicidal behaviour are key factors in suicide control. In conjunction with recent advances in the field of artificial intelligence, there is increasing research into how machine learning can assist in the detection, prediction and treatment of suicidal behaviour. Therefore, this study aims to provide a comprehensive review of the literature exploring machine learning techniques in the study of suicidal behaviour prediction.
Methods: A search of four databases was conducted: Web of Science, PubMed, Dimensions, and Scopus for research papers dated between January 2016 and September 2021. The search keywords are 'data mining', 'machine learning' in combination with 'suicidal behaviour', 'suicide', 'suicide attempt', 'suicidal ideation', 'suicide plan' and 'self-harm'. The studies that used machine learning techniques were synthesized according to the countries of the articles, sample description, sample size, classification tasks, number of features used to develop the models, types of machine learning techniques, and evaluation of performance metrics.
Results: Thirty-five empirical articles met the criteria to be included in the current review. We provide a general overview of machine learning techniques, examine the feature categories, describe methodological challenges, and suggest areas for improvement and research directions. Ensemble prediction models have been shown to be more accurate and useful than single prediction models.
Conclusions: Machine learning has great potential for improving estimates of future suicidal behaviour and monitoring changes in risk over time. Further research can address important challenges and potential opportunities that may contribute to significant advances in suicide prediction.
Competing Interests: Declaration of competing interest The authors whose names are listed immediately below certify that they have NO affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers' bureaus; membership, employment, consultancies, stock ownership, or other equity interest; and expert testimony or patent-licensing arrangements), or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.
(Copyright © 2022 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: