Cheng Nuo, Guo Meihao, Yan Fang, Guo Zhengjun, Meng Jun, Ning Kui, Zhang Yanping, Duan Zitian, Han Yong, Wang Changhong
Department of Clinical Medicine, Zhengzhou University, Zhengzhou, Henan, China.
Department of Infection Prevention and Control, The Second Affiliated Hospital of Xinxiang Medical University, Xinxiang, Henan, China.
Front Psychiatry. 2023 Mar 20;14:1016586. doi: 10.3389/fpsyt.2023.1016586. eCollection 2023.
To establish a predictive model of aggressive behaviors from hospitalized patients with schizophrenia through applying multiple machine learning algorithms, to provide a reference for accurately predicting and preventing of the occurrence of aggressive behaviors.
The cluster sampling method was used to select patients with schizophrenia who were hospitalized in our hospital from July 2019 to August 2021 as the survey objects, and they were divided into an aggressive behavior group (611 cases) and a non-aggressive behavior group (1,426 cases) according to whether they experienced obvious aggressive behaviors during hospitalization. Self-administered General Condition Questionnaire, Insight and Treatment Attitude Questionnaire (ITAQ), Family APGAR (Adaptation, Partnership, Growth, Affection, Resolve) Questionnaire (APGAR), Social Support Rating Scale Questionnaire (SSRS) and Family Burden Scale of Disease Questionnaire (FBS) were used for the survey. The Multi-layer Perceptron, Lasso, Support Vector Machine and Random Forest algorithms were used to build a predictive model for the occurrence of aggressive behaviors from hospitalized patients with schizophrenia and to evaluate its predictive effect. Nomogram was used to build a clinical application tool.
The area under the receiver operating characteristic curve (AUC) values of the Multi-Layer Perceptron, Lasso, Support Vector Machine, and Random Forest were 0.904 (95% CI: 0.877-0.926), 0.901 (95% CI: 0.874-0.923), 0.902 (95% CI: 0.876-0.924), and 0.955 (95% CI: 0.935-0.970), where the AUCs of the Random Forest and the remaining three models were statistically different ( < 0.0001), and the remaining three models were not statistically different in pair comparisons ( > 0.5).
Machine learning models can fairly predict aggressive behaviors in hospitalized patients with schizophrenia, among which Random Forest has the best predictive effect and has some value in clinical application.
通过应用多种机器学习算法，建立精神分裂症住院患者攻击行为的预测模型，为准确预测和预防攻击行为的发生提供参考。
采用整群抽样法，选取2019年7月至2021年8月在我院住院的精神分裂症患者作为调查对象，根据其在住院期间是否出现明显攻击行为分为攻击行为组（611例）和非攻击行为组（1426例）。采用自行编制的一般情况问卷、自知力与治疗态度问卷（ITAQ）、家庭功能评定问卷（APGAR）、社会支持评定量表问卷（SSRS）和家庭疾病负担量表问卷（FBS）进行调查。运用多层感知器、套索、支持向量机和随机森林算法建立精神分裂症住院患者攻击行为发生的预测模型并评估其预测效果。采用列线图构建临床应用工具。
多层感知器、套索、支持向量机和随机森林的受试者工作特征曲线（AUC）下面积值分别为0.904（95%CI：0.877-0.926）、0.901（95%CI：0.874-0.923）、0.902（95%CI：0.876-0.924）和0.955（95%CI：0.935-0.970），其中随机森林与其余三个模型的AUC有统计学差异（<0.0001），其余三个模型两两比较无统计学差异（>0.5）。
机器学习模型能够较好地预测精神分裂症住院患者的攻击行为，其中随机森林预测效果最佳，具有一定临床应用价值。
