Machine Learning Methods to Identify Predictors of Psychological Distress

Abstract

As people pay ever-increasing attention to the problems caused by psychological stress, research on its influencing factors becomes crucial. This study analyzed the Health Information National Trends Survey (HINTS, Cycle 3 and Cycle 4) data (N = 5484) and assessed the outcomes using descriptive statistics, Chi-squared tests, and t-tests. Four machine learning algorithms were applied for modeling: logistic regression (linear), random forests (RF) (ensemble), the artificial neural network (ANN) (nonlinear), and gradient boosting (GB) (ensemble). The samples were randomly assigned to a 50% training set and a 50% validation set. Twenty-six preselected variables from the databases were used in the study as predictors, and the four models identified twenty predictors of psychological distress. The essence of this paper is a binary classification problem of judging whether an individual has psychological distress based on many different factors. Therefore, accuracy, precision, recall, F1-score, and AUC were used to evaluate the model performance. The logistic regression model selected predictors by forward selection, backward selection, and stepwise regression; variable importance values were used to identify predictors in the other three machine learning methods. Of the four machine learning models, the ANN exhibited the best predictive effect (AUC = 73.90%). A range of predictors of psychological distress was identified by combining the four machine learning models, which would help improve the performance of the existing mental health screening tools.

An Optimized Bagging Ensemble Learning Approach Using BESTrees for Predicting Students’ Performance

“…To choose the appropriate model for predicting students' performance, various models tested were evaluated based on accuracy and F-measure performance metrics. Accuracy is a performance metric that calculates the percentage of correct predictions out of all predictions made [41]. Similarly, the harmonic mean of the model's precision and recall is the F-measure, as illustrated in Equations ( 1) and (2), respectively.…”

Identifying the predictors of severe psychological distress by auto-machine learning methods

“…Bakkeli (2022) diagnosed depression in different epidemic stages based on decision tree models (i.e., gradient boosting machine and random forest) and regularized regression (i.e., elastic net, ridge, and lasso) [ 12 ]. Chen et al (2022) used the same four traditional machine learning methods as Chen et al (2017) to identify predictors of psychological distress [ 15 ]. Traditional machine learning methods were used in the above-mentioned research, and the difficulty of such methods lies in parameter selection.…”