■COVID-19大流行加剧了心理健康挑战,尤其是大学生的抑郁症。及早发现有风险的学生至关重要,但仍然具有挑战性,特别是在发展中国家。利用数据驱动的预测模型提出了解决这一紧迫需求的可行解决方案。
■1)开发和比较机器学习(ML)模型,以预测大流行期间阿根廷学生的抑郁症。2)使用适当的指标评估分类和回归模型的性能。3)识别驱动抑郁预测的关键特征。
■纵向数据集(N=1492名大学生)在阿根廷COVID-19隔离期间捕获了T1和T2测量值。ML模型,包括线性逻辑回归分类器/岭回归(LogReg/RR),随机森林分类器/回归器,和支持向量机/回归器(SVM/SVR),被雇用。评估的特征包括抑郁和焦虑评分(T1时),精神障碍/自杀行为史,检疫子期信息,性别,和年龄。对于分类,模型对测试数据的性能使用精度召回曲线下的面积(AUPRC)进行评估,接收机工作特性曲线下的面积,平衡精度,F1得分,和Brier损失。对于回归,R-平方(R2),平均绝对误差,并评估均方误差。进行单变量分析以评估每个单独特征相对于目标变量的预测强度。使用分类器的平均AUPRC得分和回归变量的R2得分比较多变量与单变量模型的性能。
■SVM和LogReg可实现最高性能(例如,AUPRC:0.76,95%CI:0.69,0.81)和SVR和RR模型(例如,SVR和RR的R2:0.56,95%CI:分别为0.45,0.64和0.45,0.63)。单变量模型,特别是使用抑郁(AUPRC:0.72,95%CI:0.64,0.79)或焦虑评分(AUPRC:0.71,95%CI:0.64,0.78)的LogReg和SVM,以及使用抑郁评分(R2:0.48,95%CI:0.39,0.57)的RR表现出接近多变量模型的性能水平,其中包括所有功能。
■这些发现强调了先前存在的抑郁和焦虑状况在预测隔离期间抑郁方面的相关性,强调他们的合并症。ML模型,特别是SVM/SVR和LogReg/RR,在及时发现有风险的学生方面表现出潜力。然而,在临床实施之前还需要进一步的研究.
UNASSIGNED: The COVID-19 pandemic has exacerbated mental health challenges, particularly depression among college students. Detecting at-risk students early is crucial but remains challenging, particularly in developing countries. Utilizing data-driven predictive models presents a viable solution to address this pressing need.
UNASSIGNED: 1) To develop and compare machine learning (ML) models for predicting depression in Argentinean students during the pandemic. 2) To assess the performance of classification and regression models using appropriate metrics. 3) To identify key features driving depression prediction.
UNASSIGNED: A longitudinal dataset (N = 1492 college students) captured T1 and T2 measurements during the Argentinean COVID-19 quarantine. ML models, including linear logistic regression classifiers/ridge regression (LogReg/RR), random forest classifiers/regressors, and support vector machines/regressors (SVM/SVR), are employed. Assessed features encompass depression and anxiety scores (at T1), mental disorder/suicidal behavior history, quarantine sub-period information, sex, and age. For classification, models\' performance on test data is evaluated using Area Under the Precision-Recall Curve (AUPRC), Area Under the Receiver Operating Characteristic curve, Balanced Accuracy, F1 score, and Brier loss. For regression, R-squared (R2), Mean Absolute Error, and Mean Squared Error are assessed. Univariate analyses are conducted to assess the predictive strength of each individual feature with respect to the target variable. The performance of multi- vs univariate models is compared using the mean AUPRC score for classifiers and the R2 score for regressors.
UNASSIGNED: The highest performance is achieved by SVM and LogReg (e.g., AUPRC: 0.76, 95% CI: 0.69, 0.81) and SVR and RR models (e.g., R2 for SVR and RR: 0.56, 95% CI: 0.45, 0.64 and 0.45, 0.63, respectively). Univariate models, particularly LogReg and SVM using depression (AUPRC: 0.72, 95% CI: 0.64, 0.79) or anxiety scores (AUPRC: 0.71, 95% CI: 0.64, 0.78) and RR using depression scores (R2: 0.48, 95% CI: 0.39, 0.57) exhibit performance levels close to those of the multivariate models, which include all features.
UNASSIGNED: These findings highlight the relevance of pre-existing depression and anxiety conditions in predicting depression during quarantine, underscoring their comorbidity. ML models, particularly SVM/SVR and LogReg/RR, demonstrate potential in the timely detection of at-risk students. However, further studies are needed before clinical implementation.