Prediction of Mental Health Problem Using Annual Student Health Survey: Machine Learning Approach

Abstract

Background One of the reasons why students go to counseling is being called on based on self-reported health survey results. However, there is no concordant standard for such calls. Objective This study aims to develop a machine learning (ML) model to predict students’ mental health problems in 1 year and the following year using the health survey’s content and answering time (response time, response time stamp, and answer date). Methods Data were obtained from the responses of 3561 (62.58%) of 5690 undergraduate students from University A in Japan (a national university) who completed the health survey in 2020 and 2021. We performed 2 analyses; in analysis 1, a mental health problem in 2020 was predicted from demographics, answers for the health survey, and answering time in the same year, and in analysis 2, a mental health problem in 2021 was predicted from the same input variables as in analysis 1. We compared the results from different ML models, such as logistic regression, elastic net, random forest, XGBoost, and LightGBM. The results with and without answering time conditions were compared using the adopted model. Results On the basis of the comparison of the models, we adopted the LightGBM model. In this model, both analyses and conditions achieved adequate performance (eg, Matthews correlation coefficient [MCC] of with answering time condition in analysis 1 was 0.970 and MCC of without answering time condition in analysis 1 was 0.976; MCC of with answering time condition in analysis 2 was 0.986 and that of without answering time condition in analysis 2 was 0.971). In both analyses and in both conditions, the response to the questions about campus life (eg, anxiety and future) had the highest impact (Gain 0.131-0.216; Shapley additive explanations 0.018-0.028). Shapley additive explanations of 5 to 6 input variables from questions about campus life were included in the top 10. In contrast to our expectation, the inclusion of answering time–related variables did not exhibit substantial improvement in the prediction of students’ mental health problems. However, certain variables generated based on the answering time are apparently helpful in improving the prediction and affecting the prediction probability. Conclusions These results demonstrate the possibility of predicting mental health across years using health survey data. Demographic and behavioral data, including answering time, were effective as well as self-rating items. This model demonstrates the possibility of synergistically using the characteristics of health surveys and advantages of ML. These findings can improve health survey items and calling criteria.

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

“…This result is in line with findings from Smith et al [ 22 ], who highlighted Random Forest’s effectiveness in mental health prediction among adolescents. However, this contrasts with reports from Jones et al [ 24 ] and Lee and Kim [ 25 ], where gradient boosting and LightGBM outperformed other models, including Random Forest, in similar tasks.…”

“…Machine Learning’s Rising Influence in Mental Health Prediction: In recent years, ML methods have gained significant popularity in the field of mental health prediction [ 22 , 24 , 25 , 26 , 27 ]. However, very few studies have evaluated the performance of these ML methods to ensure their reliability and clinical applicability.…”

“…Studies have demonstrated ML's effectiveness in diagnosing psychiatric conditions by analyzing diverse data sources, such as genetic profiles, neuroimaging, patient-reported histories, and social media data [22][23][24][25][26][27][28][29]. Notably, machine learning algorithms like Support Vector Machines (SVMs) and Gradient Boosting Machines (GBMs) have been extensively investigated for their predictive capabilities in mental health applications, reflecting a growing interest in the integration of technology and psychology [24,25,28,[30][31][32].…”

“…An increasing body of research has explored the nuanced capabilities of ML in uncovering complex patterns within multifaceted health-related datasets, often revealing insights that traditional statistical methods may overlook. Studies have demonstrated ML’s effectiveness in diagnosing psychiatric conditions by analyzing diverse data sources, such as genetic profiles, neuroimaging, patient-reported histories, and social media data [ 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 ]. Notably, machine learning algorithms like Support Vector Machines (SVMs) and Gradient Boosting Machines (GBMs) have been extensively investigated for their predictive capabilities in mental health applications, reflecting a growing interest in the integration of technology and psychology [ 24 , 25 , 28 , 30 , 31 , 32 ].…”

Decoding Minds: Estimation of Stress Level in Students using Machine Learning

“…In (5) the information came from the replies of 3561 (62.58%) of the 5690 undergraduate students at University A, a national university in Japan, who finished the health survey in 2020 and 2021. They conducted two analyses: the first predicted a mental health issue in 2020 based on demographics, health survey responses, and response time in the same year; the second predicted a mental health issue in 2021 based on the same input variables as the first analysis.…”