Post-graduate Program in Psychiatry and Behavioral Sciences, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil; Psychological Trauma Research and Treatment Program (NET-Trauma), Hospital de Clínicas de Porto Alegre, Porto Alegre, RS Brazil.
Post-graduate Program in Medical Psychology and Psychiatry, Department of Psychiatry, Universidade Federal de São Paulo, São Paulo, SP, Brazil; Program for Research and Care on Violence and PTSD (PROVE), Universidade Federal de São Paulo, São Paulo, SP, Brazil.
Psychiatry Res. 2022 May;311:114489. doi: 10.1016/j.psychres.2022.114489. Epub 2022 Mar 4.
This proof-of-concept study aimed to investigate the viability of a predictive model to support posttraumatic stress disorder (PTSD) staging. We performed a naturalistic, cross-sectional study at two Brazilian centers: the Psychological Trauma Research and Treatment (NET-Trauma) Program at Universidade Federal of Rio Grande do Sul, and the Program for Research and Care on Violence and PTSD (PROVE), at Universidade Federal of São Paulo. Five supervised machine-learning algorithms were tested: Elastic Net, Gradient Boosting Machine, Random Forest, Support Vector Machine, and C5.0, using clinical (Clinician-Administered PTSD Scale version 5) and sociodemographic features. A hundred and twelve patients were enrolled (61 from NET-Trauma and 51 from PROVE). We found a model with four classes suitable for the PTSD staging, with best performance metrics using the C5.0 algorithm to CAPS-5 15-items plus sociodemographic features, with an accuracy of 65.6% for the train dataset and 52.9% for the test dataset (both significant). The number of symptoms, CAPS-5 total score, global severity score, and presence of current/previous trauma events appear as main features to predict PTSD staging. This is the first study to evaluate staging in PTSD with machine learning algorithms using accessible clinical and sociodemographic features, which may be used in future research.
本概念验证研究旨在探讨一种用于创伤后应激障碍（PTSD）分期的预测模型的可行性。我们在巴西的两个中心进行了一项自然主义、横断面研究：南里奥格兰德州联邦大学的心理创伤研究和治疗（NET-Trauma）计划，以及圣保罗联邦大学的暴力和 PTSD 研究和护理计划（PROVE）。我们测试了五种有监督的机器学习算法：弹性网络、梯度提升机、随机森林、支持向量机和 C5.0，使用了临床（临床医生管理 PTSD 量表第 5 版）和社会人口统计学特征。共纳入了 112 名患者（NET-Trauma 有 61 名，PROVE 有 51 名）。我们发现了一个具有四个类别的模型，适合 PTSD 分期，使用 C5.0 算法对 CAPS-5 15 项加社会人口统计学特征的最佳性能指标，训练数据集的准确率为 65.6%，测试数据集的准确率为 52.9%（均具有统计学意义）。症状数量、CAPS-5 总分、总体严重程度评分以及当前/先前创伤事件的存在似乎是预测 PTSD 分期的主要特征。这是第一项使用机器学习算法和可及的临床和社会人口统计学特征评估 PTSD 分期的研究，可能用于未来的研究。
