Alpert Medical School of Brown University, Department of Psychiatry and Human Behavior, Providence, RI, USA.
University of Notre Dame, Department of Psychology, Notre Dame, IN, USA.
J Affect Disord. 2020 May 1;268:206-214. doi: 10.1016/j.jad.2020.02.048. Epub 2020 Feb 28.
The current study aimed to classify recent and lifetime suicide attempt history among youth presenting to medical settings using machine learning (ML) as applied to a behavioral health screen self-report survey.
In the current study, 13,325 (mean age = 17.06, SD = 2.61) pediatric primary care patients from rural, semi-urban, and urban areas of Pennsylvania and 12,001 (mean age = 15.79, SD = 1.40) pediatric patients from an urban children's hospital emergency department were included in the analyses. We used two methods of ML (decision trees, random forests) to (a) generate algorithms to classify suicide attempt history, and (b) validate generated algorithms within and across samples to assess model performance. We also employed ridge regression to evaluate performance of the ML approaches.
Our findings demonstrate that ML approaches did not enhance our ability to classify lifetime or recent suicide attempt history among youth across medical care settings, suggesting that relationships may be mainly linear and non-interactive. In line with prior research, a history of suicide planning, active suicidal ideation, passive suicidal ideation, and nonsuicidal self-injury emerged as relatively important correlates of suicide attempt.
The cross-sectional nature of the current study prevents us from determining the extent to which the important variables identified confer risk for future suicidal behavior.
The present study underscores the importance of suicide risk screenings that focus on the assessment of active and passive suicidal ideation and suicide planning, in addition to nonsuicidal self-injury, across pediatric medical settings.
本研究旨在通过机器学习（ML）对行为健康筛查自我报告调查进行应用，对就诊于医疗环境的青少年进行近期和终生自杀尝试史的分类。
在本研究中，宾夕法尼亚州农村、半城市和城市地区的 13325 名（平均年龄=17.06，SD=2.61）儿科初级保健患者和 12001 名（平均年龄=15.79，SD=1.40）城市儿童医院急诊部的儿科患者被纳入分析。我们使用两种机器学习方法（决策树、随机森林）来：（a）生成算法以分类自杀尝试史，以及（b）在样本内和跨样本验证生成的算法，以评估模型性能。我们还采用岭回归来评估 ML 方法的性能。
我们的研究结果表明，ML 方法并没有增强我们在医疗保健环境中对青少年终生或近期自杀尝试史进行分类的能力，这表明关系可能主要是线性的且非交互的。与先前的研究一致，自杀计划史、主动自杀意念、被动自杀意念和非自杀性自伤是自杀尝试的相对重要的相关因素。
本研究的横断面性质限制了我们确定所确定的重要变量对未来自杀行为风险的程度。
本研究强调了在儿科医疗环境中，除了非自杀性自伤外，还应重点关注对主动和被动自杀意念和自杀计划的评估，进行自杀风险筛查的重要性。
