Department of Psychiatry, NYU Grossman School of Medicine, New York, USA; Department of Population Health, NYU Grossman School of Medicine, New York, USA.
Department of Psychiatry and Behavioral Sciences, Emory University School of Medicine, Atlanta, GA, USA; Center for Visual and Neurocognitive Rehabilitation, Atlanta Veterans' Affairs Health Care System, Atlanta, GA, USA.
Gen Hosp Psychiatry. 2023 Mar-Apr;81:46-50. doi: 10.1016/j.genhosppsych.2023.01.012. Epub 2023 Jan 28.
Predicting risk of posttraumatic stress disorder (PTSD) in the acute care setting is challenging given the pace and acute care demands in the emergency department (ED) and the infeasibility of using time-consuming assessments. Currently, no accurate brief screening for long-term PTSD risk is routinely used in the ED. One instrument widely used in the ED is the 27-item Immediate Stress Reaction Checklist (ISRC). The aim of this study was to develop a short screener using a machine learning approach and to investigate whether accurate PTSD prediction in the ED can be achieved with substantially fewer items than the IRSC.
This prospective longitudinal cohort study examined the development and validation of a brief screening instrument in two independent samples, a model development sample (N = 253) and an external validation sample (N = 93). We used a feature selection algorithm to identify a minimal subset of features of the ISRC and tested this subset in a predictive model to investigate if we can accurately predict long-term PTSD outcomes.
We were able to identify a reduced subset of 5 highly predictive features of the ISRC in the model development sample (AUC = 0.80), and we were able to validate those findings in the external validation sample (AUC = 0.84) to discriminate non-remitting vs. resilient trajectories.
This study developed and validated a brief 5-item screener in the ED setting, which may help to improve the diagnostic process of PTSD in the acute care setting and help ED clinicians plan follow-up care when patients are still in contact with the healthcare system. This could reduce the burden on patients and decrease the risk of chronic PTSD.
鉴于急诊科（ED）的节奏和急性护理需求，以及使用耗时的评估方法不切实际，预测创伤后应激障碍（PTSD）的风险具有挑战性。目前，ED 中没有常规使用用于长期 PTSD 风险的准确简短筛查。ED 中广泛使用的一种工具是 27 项即时应激反应检查表（ISRC）。本研究旨在开发一种使用机器学习方法的简短筛查工具，并探讨是否可以使用比 ISRC 少得多的项目来实现 ED 中准确的 PTSD 预测。
这项前瞻性纵向队列研究在两个独立样本中检验了一种简短筛查工具的开发和验证，一个是模型开发样本（N=253），另一个是外部验证样本（N=93）。我们使用特征选择算法来识别 ISRC 的最小特征子集，并在预测模型中测试该子集，以调查我们是否可以准确预测长期 PTSD 结局。
我们能够在模型开发样本中确定 ISRC 的 5 个高度预测特征的减少子集（AUC=0.80），并能够在外部验证样本中验证这些发现（AUC=0.84），以区分非缓解与有弹性轨迹。
本研究在 ED 环境中开发并验证了一种简短的 5 项筛查工具，这可能有助于改善急性护理环境中 PTSD 的诊断过程，并帮助 ED 临床医生在患者仍与医疗保健系统接触时计划后续护理。这可以减轻患者的负担，降低慢性 PTSD 的风险。
