Development of a Heart Rate Variability-Based Predictive Model for Depressive Symptoms in Chinese University Students

Abstract

The current depression assessment tools are limited by subjectivity and potential bias. This study investigated the relationship between heart rate variability (HRV), body composition, and self-reported depressive symptoms to develop an objective depression screening model for Chinese university students. Data from 2,094 students, including demographics, body composition, Self-Rating Depression Scale (SDS) scores, and HRV indicators, were analyzed using SPSS 26.0 to construct a predictive regression model, with accuracy validated in GraphPad Prism 9.4.1. Subsequently, a subgroup of 359 students with depressive symptoms was screened using the model. The results showed no significant differences between the predicted and actual SDS scores (p > .05), with over 91% of the predicted scores falling within the 95% confidence interval of the actual scores. The strong correlation between HRV and SDS scores supports the use of HRV as a reliable indicator for depression screening. Overall, the model demonstrated a prediction accuracy of 92.61%, highlighting its potential for objective mental health assessment among university populations.