University of Michigan, Ann Arbor, MI, USA.
Assessment. 2021 Dec;28(8):1949-1959. doi: 10.1177/1073191120939168. Epub 2020 Jul 15.
Mobile technology offers new possibilities for assessing suicidal ideation and behavior in real- or near-real-time. It remains unclear how intensive longitudinal data can be used to identify proximal risk and inform clinical decision making. In this study of adolescent psychiatric inpatients ( = 32, aged 13-17 years, 75% female), we illustrate the application of a three-step process to identify early signs of suicide-related crises using daily diaries. Using receiver operating characteristic (ROC) curve analyses, we considered the utility of 12 features-constructed using means and variances of daily ratings for six risk factors over the first 2 weeks postdischarge (observations = 360)-in identifying a suicidal crisis 2 weeks later. Models derived from single risk factors had modest predictive accuracy (area under the ROC curve [AUC] 0.46-0.80) while nearly all models derived from combinations of risk factors produced higher accuracy (AUCs 0.80-0.91). Based on this illustration, we discuss implications for clinical decision making and future research.
移动技术为实时或近实时评估自杀意念和行为提供了新的可能性。目前尚不清楚如何利用密集的纵向数据来识别近期风险并为临床决策提供信息。在这项对青少年精神病住院患者的研究中（n=32，年龄 13-17 岁，75%为女性），我们说明了如何使用每日日记来识别与自杀相关的危机的早期迹象的三步过程。使用接收者操作特征（ROC）曲线分析，我们考虑了使用六种风险因素在出院后前两周的每日评分的均值和方差构建的 12 个特征（观察值=360）在 2 周后识别自杀危机的效用。来自单个风险因素的模型具有适度的预测准确性（ROC 曲线下面积 [AUC] 0.46-0.80），而几乎所有来自风险因素组合的模型都产生了更高的准确性（AUC 0.80-0.91）。基于这一说明，我们讨论了对临床决策和未来研究的影响。
