Age-specific prevalence and predictors of lifetime suicide attempts using machine learning in Chinese adults: a nationwide multi-centre survey.

IF 6.1 2区医学 Q1 PSYCHIATRY

Epidemiology and Psychiatric Sciences Pub Date : 2025-10-20 DOI:10.1017/S2045796025100231

Yu Wu, Yihao Zhao, Panliang Zhong, Chen Chen, Yibo Wu, Xiaoying Zheng

{"title":"Age-specific prevalence and predictors of lifetime suicide attempts using machine learning in Chinese adults: a nationwide multi-centre survey.","authors":"Yu Wu, Yihao Zhao, Panliang Zhong, Chen Chen, Yibo Wu, Xiaoying Zheng","doi":"10.1017/S2045796025100231","DOIUrl":null,"url":null,"abstract":"Aims: The epidemiology and age-specific patterns of lifetime suicide attempts (LSA) in China remain unclear. We aimed to examine age-specific prevalence and predictors of LSA among Chinese adults using machine learning (ML).Methods: We analyzed 25,047 adults in the 2024 Psychology and Behavior Investigation of Chinese Residents (PBICR-2024), stratified into three age groups (18-24, 25-44, ≥ 45 years). Thirty-seven candidate predictors across six domains-sociodemographic, physical health, mental health, lifestyle, social environment, and self-injury/suicide history-were assessed. Five ML models-random forest, logistic regression, support vector machine (SVM), Extreme Gradient Boosting (XGBoost), and Naive Bayes-were compared. SHapley Additive exPlanations (SHAP) were used to quantify feature importance.Results: The overall prevalence of LSA was 4.57% (1,145/25,047), with significant age differences: 8.10% in young adults (18-24), 4.67% in adults aged 25-44, and 2.67% in older adults (≥45). SVM achieved the best test-set performance across all ages [area under the curve (AUC) 0.88-0.94, sensitivity 0.79-0.87, specificity 0.81-0.88], showing superior calibration and net clinical benefit. SHAP analysis identified both shared and age-specific predictors. Suicidal ideation, adverse childhood experiences, and suicide disclosure were consistent top predictors across all ages. Sleep disturbances and anxiety symptoms stood out in young adults; marital status, living alone, and perceived stress in mid-life; and functional limitations, poor sleep, and depressive symptoms in older adults.Conclusions: LSA prevalence in Chinese adults is relatively high, with a clear age gradient peaking in young adulthood. Risk profiles revealed both shared and age-specific predictors, reflecting distinct life-stage vulnerabilities. These findings support age-tailored suicide prevention strategies in China.","PeriodicalId":11787,"journal":{"name":"Epidemiology and Psychiatric Sciences","volume":"34 ","pages":"e52"},"PeriodicalIF":6.1000,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Epidemiology and Psychiatric Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1017/S2045796025100231","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}

引用次数: 0

Abstract

Aims: The epidemiology and age-specific patterns of lifetime suicide attempts (LSA) in China remain unclear. We aimed to examine age-specific prevalence and predictors of LSA among Chinese adults using machine learning (ML).

Methods: We analyzed 25,047 adults in the 2024 Psychology and Behavior Investigation of Chinese Residents (PBICR-2024), stratified into three age groups (18-24, 25-44, ≥ 45 years). Thirty-seven candidate predictors across six domains-sociodemographic, physical health, mental health, lifestyle, social environment, and self-injury/suicide history-were assessed. Five ML models-random forest, logistic regression, support vector machine (SVM), Extreme Gradient Boosting (XGBoost), and Naive Bayes-were compared. SHapley Additive exPlanations (SHAP) were used to quantify feature importance.

Results: The overall prevalence of LSA was 4.57% (1,145/25,047), with significant age differences: 8.10% in young adults (18-24), 4.67% in adults aged 25-44, and 2.67% in older adults (≥45). SVM achieved the best test-set performance across all ages [area under the curve (AUC) 0.88-0.94, sensitivity 0.79-0.87, specificity 0.81-0.88], showing superior calibration and net clinical benefit. SHAP analysis identified both shared and age-specific predictors. Suicidal ideation, adverse childhood experiences, and suicide disclosure were consistent top predictors across all ages. Sleep disturbances and anxiety symptoms stood out in young adults; marital status, living alone, and perceived stress in mid-life; and functional limitations, poor sleep, and depressive symptoms in older adults.

Conclusions: LSA prevalence in Chinese adults is relatively high, with a clear age gradient peaking in young adulthood. Risk profiles revealed both shared and age-specific predictors, reflecting distinct life-stage vulnerabilities. These findings support age-tailored suicide prevention strategies in China.

查看原文本刊更多论文

在中国成年人中使用机器学习的特定年龄患病率和终生自杀企图的预测因素：一项全国性的多中心调查。

目的：中国终生自杀企图（LSA）的流行病学和年龄特征尚不清楚。我们的目的是利用机器学习（ML）研究中国成年人中LSA的年龄特异性患病率和预测因素。方法：对参与2024年中国居民心理与行为调查（PBICR-2024）的25,047名成年人进行分析，将其分为18-24岁、25-44岁和≥45岁三个年龄组。评估了社会人口统计学、身体健康、心理健康、生活方式、社会环境和自残/自杀史等6个领域的37个候选预测因子。五种机器学习模型——随机森林、逻辑回归、支持向量机（SVM）、极端梯度增强（XGBoost）和朴素贝叶斯——进行了比较。SHapley加性解释（SHAP）用于量化特征的重要性。结果：LSA的总患病率为4.57%(1,145/25,047)，年龄差异显著：青壮年（18-24岁）为8.10%，25-44岁为4.67%，老年人（≥45岁）为2.67%。支持向量机在所有年龄段的测试集表现最佳[曲线下面积（AUC） 0.88-0.94，灵敏度0.79-0.87，特异性0.81-0.88]，显示出优越的校准和临床净效益。SHAP分析确定了共同的和特定年龄的预测因子。自杀意念、不良童年经历和自杀披露在所有年龄段都是一致的预测因子。睡眠障碍和焦虑症状在年轻人中尤为突出；婚姻状况、独居与中年压力感知；以及老年人的功能限制、睡眠不足和抑郁症状。结论：中国成年人的LSA患病率相对较高，年龄梯度明显，在青年期达到高峰。风险概况揭示了共同的和特定年龄的预测因素，反映了不同的生命阶段的脆弱性。这些发现支持了中国针对不同年龄的自杀预防策略。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Epidemiology and Psychiatric Sciences PSYCHIATRY-

CiteScore

7.80

自引率

1.20%

发文量

121

审稿时长

>12 weeks

期刊介绍： Epidemiology and Psychiatric Sciences is a prestigious international, peer-reviewed journal that has been publishing in Open Access format since 2020. Formerly known as Epidemiologia e Psichiatria Sociale and established in 1992 by Michele Tansella, the journal prioritizes highly relevant and innovative research articles and systematic reviews in the areas of public mental health and policy, mental health services and system research, as well as epidemiological and social psychiatry. Join us in advancing knowledge and understanding in these critical fields.