Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York City, NY U.S.A.
Courant Institute of Mathematical Sciences, New York University, New York City, NY U.S.A.
Psychiatry Res. 2021 Oct;304:114118. doi: 10.1016/j.psychres.2021.114118. Epub 2021 Jul 17.
The majority of suicide attempters do not disclose suicide ideation (SI) prior to making an attempt. When reported, SI is nevertheless associated with increased risk of suicide. This paper implemented machine learning (ML) approaches to assess the degree to which current and lifetime SI affect the predictive validity of the Suicide Crisis Syndrome (SCS), an acute condition indicative of imminent risk, for near-term suicidal behaviors (SB ).
In a sample of 591 high-risk inpatient participants, SCS and SI were respectively assessed using the Suicide Crisis Inventory (SCI) and the Columbia Suicide Severity Rating Scale (C-SSRS). Two ML predictive algorithms, Random Forest and XGBoost, were implemented and framed using optimism adjusted bootstrapping. Metrics collected included AUPRC, AUROC, classification accuracy, balanced accuracy, precision, recall, and brier score. AUROC metrics were compared by computing a z-score.
The combination of current SI and SCI showed slightly higher predictive validity for near-term SB as evidenced by AUROC metrics than the SCI alone, but the difference was not significant (p<0.05). Current SI scored the highest amongst a chi square distribution in regards to predictors of near-term SB.
The addition of SI to the SCS does not materially improve the model's predictive validity for near-term SB, suggesting that patient self-reported SI should not be a requirement for the diagnosis of SCS.
大多数自杀未遂者在尝试自杀前不会透露自杀意念（SI）。然而，当报告时，SI 与自杀风险增加有关。本文采用机器学习（ML）方法评估当前和终生 SI 对自杀危机综合征（SCS）预测效度的影响程度，SCS 是一种预示近期风险的急性状态，用于预测近期自杀行为（SB）。
在 591 名高危住院患者样本中，使用自杀危机量表（SCI）和哥伦比亚自杀严重程度评定量表（C-SSRS）分别评估 SCS 和 SI。采用乐观调整的自举法实现了两种 ML 预测算法，即随机森林和 XGBoost。收集的指标包括 AUPRC、AUROC、分类准确性、平衡准确性、精度、召回率和 Brier 分数。通过计算 z 分数比较 AUROC 指标。
当前 SI 和 SCI 的组合在预测近期 SB 方面的表现略优于 SCI 单独使用，这一点体现在 AUROC 指标上，但差异无统计学意义（p<0.05）。在预测近期 SB 的指标中，当前 SI 在卡方分布中得分最高。
将 SI 添加到 SCS 中并不会显著提高模型对近期 SB 的预测效度，这表明患者自我报告的 SI 不应该成为 SCS 诊断的必要条件。
