Lee Jeongyoon, Pak Tae-Young
Convergence Program for Social Innovation, Sungkyunkwan University, Seoul, South Korea.
Department of Consumer Science and Convergence Program for Social Innovation, Sungkyunkwan University, Seoul, South Korea.
SSM Popul Health. 2022 Sep 14;19:101231. doi: 10.1016/j.ssmph.2022.101231. eCollection 2022 Sep.
Suicide remains the leading cause of premature death in South Korea. This study aims to develop machine learning algorithms for screening Korean adults at risk for suicidal ideation and suicide planning or attempt.
Two sets of balanced data for Korean adults aged 19-64 years were drawn from the 2012-2019 waves of the Korea Welfare Panel Study using the random down-sampling method ( = 3292 for the prediction of suicidal ideation, = 488 for the prediction of suicide planning or attempt). Demographic, socioeconomic, and psychosocial characteristics were used to predict suicidal ideation and suicide planning or attempt. Four machine-learning classifiers (logistic regression, random forest, support vector machine, and extreme gradient boosting) were tuned and cross-validated.
All four algorithms demonstrated satisfactory classification performance in predicting suicidal ideation (sensitivity 0.808-0.853, accuracy 0.843-0.863) and suicide planning or attempt (sensitivity 0.814-0.861, accuracy 0.864-0.884). Extreme gradient boosting was the best-performing algorithm for predicting both suicidal outcomes. The most important predictors were depressive symptoms, self-esteem, income, consumption, and life satisfaction. The algorithms trained with the top two predictors, depressive symptoms and self-esteem, showed comparable classification performance in predicting suicidal ideation (sensitivity 0.801-0.839, accuracy 0.841-0.846) and suicide planning or attempt (sensitivity 0.814-0.837, accuracy 0.874-0.884).
Suicidal ideation and behaviors may be under-reported due to social desirability bias. Causality is not established.
More than 80% of individuals at risk for suicidal ideation and suicide planning or attempt could be predicted by a number of mental and socioeconomic characteristics of respondents. This finding suggests the potential of developing a quick screening tool based on the known risk factors and applying it to primary care or community settings for early intervention.
自杀仍是韩国过早死亡的主要原因。本研究旨在开发机器学习算法，用于筛查有自杀意念、自杀计划或自杀未遂风险的韩国成年人。
使用随机下采样方法，从2012 - 2019年韩国福利面板研究的各波数据中提取了两组针对19 - 64岁韩国成年人的平衡数据（用于预测自杀意念的样本量 = 3292，用于预测自杀计划或自杀未遂的样本量 = 488）。利用人口统计学、社会经济和心理社会特征来预测自杀意念以及自杀计划或自杀未遂情况。对四种机器学习分类器（逻辑回归、随机森林、支持向量机和极端梯度提升）进行了调优和交叉验证。
所有四种算法在预测自杀意念（灵敏度0.808 - 0.853，准确率0.843 - 0.863）和自杀计划或自杀未遂（灵敏度0.814 - 0.861，准确率0.864 - 0.884）方面均表现出令人满意的分类性能。极端梯度提升是预测这两种自杀结果的性能最佳的算法。最重要的预测因素是抑郁症状、自尊、收入、消费和生活满意度。用前两个预测因素（抑郁症状和自尊）训练的算法在预测自杀意念（灵敏度0.801 - 0.839，准确率0.841 - 0.846）和自杀计划或自杀未遂（灵敏度0.814 - 0.837，准确率0.874 - 0.884）方面表现出相当的分类性能。
由于社会期望偏差，自杀意念和行为可能报告不足。因果关系尚未确立。
通过受访者的一些心理和社会经济特征，可以预测超过80%有自杀意念、自杀计划或自杀未遂风险的个体。这一发现表明，基于已知风险因素开发一种快速筛查工具并将其应用于初级保健或社区环境以进行早期干预具有潜力。
