机器学习算法预测自杀与自伤行为的准确性:系统综述与Meta分析
该系统综述与Meta分析检索8个数据库至2025年4月30日,纳入53项采用病例对照、病例队列或队列设计、以自杀或医院治疗的自伤为结局的研究。机器学习算法预测自杀行为的受试者工作特征曲线下面积为0.69至0.93,灵敏度45%至82%,特异度91%至95%。作者结论认为准确性过低,不足以用于筛查或高危个体干预分派。
要点
- 纳入53项研究,曲线下面积为0.69至0.93,灵敏度45%至82%,特异度91%至95%。
- 阳性似然比6.5至9.9,阴性似然比0.2至0.6;样本内阳性预测值6%至17%。
- 阳性似然比为10时,低、中、高流行人群阳性预测值分别为0.1%、17%、66%。
核心结论
- 机器学习算法预测自杀行为的准确性过低,不足以用于筛查(病例发现)或为高危个体优先安排干预(治疗分派)。
- 对医院治疗的自伤人群,管理应包括三部分:基于需求的评估与回应、识别可改变的危险因素并治疗以降低暴露、实施已证实有效的出院后照护干预。
研究设计与样本
- 系统综述与Meta分析,检索PubMed、PsycINFO、Scopus、EMBASE、IEEE、Medline、CINALH和Web of Science自建库至2025年4月30日。
- 纳入采用病例对照、病例队列或队列设计、以自杀或医院治疗的自伤为结局的研究;排除自报结局或采用其他设计的研究。
- 共53项研究符合纳入标准,准确性采用适用于诊断准确性研究的统计方法评估。
- 研究已注册(PROSPERO CRD42024523074)。
主要发现
- 受试者工作特征曲线下面积范围为0.69至0.93。
- 灵敏度为45%至82%,特异度为91%至95%。
- 阳性似然比为6.5至9.9,阴性似然比为0.2至0.6。
- 使用样本内患病率时,阳性预测值范围为6%至17%。
- 使用样本外患病率、阳性似然比为10时,低流行人群阳性预测值为0.1%,中流行人群为17%,高流行人群为66%。
临床怎么用
- 对医院治疗的自伤人群,管理应包括三部分:基于需求的评估与回应、识别可改变的危险因素并治疗以降低暴露、实施已证实有效的出院后照护干预。
局限性
- 排除了因无法提取足够信息计算准确性统计量的相关研究。
- 研究间观察结局的随访时间存在差异。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: There has been rapid expansion in the development of machine learning algorithms to predict suicidal behaviours. To test the accuracy of these algorithms for predicting suicide and hospital-treated self-harm, we undertook a systematic review and meta-analysis. The study was registered (PROSPERO CRD42024523074). METHODS AND FINDINGS: We searched PubMed, PsycINFO, Scopus, EMBASE, IEEE, Medline, CINALH and Web of Science from database inception until 30 April 2025 to identify studies using machine learning algorithms to predict suicide, self-harm and a combined suicide/self-harm outcome. Studies were included if they examined suicide or hospital-treated self-harm outcomes using a case-control, case-cohort or cohort study design. Studies were excluded if they used self-reported outcomes or examined outcomes using other study designs. Accuracy was assessed using statistical methods appropriate for diagnostic accuracy studies. Fifty-three studies met the inclusion criteria. The area under the receiver operating characteristic curves ranged from 0.69 to 0.93. Sensitivity was 45%-82% and specificity was 91%-95%. Positive likelihood ratios were 6.5-9.9 and negative likelihood values were 0.2-0.6. Using in-sample prevalence values, the positive predictive values ranged from 6% to 17%. Using out-of-sample prevalence values at an LR+ value of 10, the positive predictive value was 0.1% in low prevalence populations, 17% in medium prevalence populations and 66% in high prevalence populations. The main study limitations were the exclusion of relevant studies where we could not extract sufficient information to calculate accuracy statistics and between-study differences in the follow-up time over which the outcomes were observed. CONCLUSIONS: The accuracy of machine learning algorithms for predicting suicidal behaviour is too low to be useful for screening (case finding) or for prioritising high-risk individuals for interventions (treatment allocation). For hospital-treated self-harm populations, management should instead include three components for all patients: a needs-based assessment and response, identification of modifiable risk factors with treatment intended to reduce those exposures, and implementation of demonstrated effective aftercare interventions.
引用
- Spittal MJ, Guo XA, Kang L, et al. Machine learning algorithms and their predictive accuracy for suicide and self-harm: Systematic review and meta-analysis. PLoS Med. 2025. PMID: 40934153. doi:10.1371/journal.pmed.1004581
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。