Department of Physical Educantion, Xinzhou Normal University, Xinzhou 034000, China.
College of Physical Educantion, Jinggangshan University, Ji'an 343009, China.
Sensors (Basel). 2024 Jun 28;24(13):4203. doi: 10.3390/s24134203.
(1) Background: This study aims to investigate the correlation between heart rate variability (HRV) during exercise and recovery periods and the levels of anxiety and depression among college students. Additionally, the study assesses the accuracy of a multilayer perceptron-based HRV analysis in predicting these emotional states. (2) Methods: A total of 845 healthy college students, aged between 18 and 22, participated in the study. Participants completed self-assessment scales for anxiety and depression (SAS and PHQ-9). HRV data were collected during exercise and for a 5-min period post-exercise. The multilayer perceptron neural network model, which included several branches with identical configurations, was employed for data processing. (3) Results: Through a 5-fold cross-validation approach, the average accuracy of HRV in predicting anxiety levels was 89.3% for no anxiety, 83.6% for mild anxiety, and 74.9% for moderate to severe anxiety. For depression levels, the average accuracy was 90.1% for no depression, 84.2% for mild depression, and 82.1% for moderate to severe depression. The predictive R-squared values for anxiety and depression scores were 0.62 and 0.41, respectively. (4) Conclusions: The study demonstrated that HRV during exercise and recovery in college students can effectively predict levels of anxiety and depression. However, the accuracy of score prediction requires further improvement. HRV related to exercise can serve as a non-invasive biomarker for assessing psychological health.
（1）背景：本研究旨在探讨大学生运动及恢复期心率变异性（HRV）与焦虑和抑郁水平之间的相关性，并评估基于多层感知器的 HRV 分析在预测这些情绪状态方面的准确性。（2）方法：共有 845 名年龄在 18 至 22 岁之间的健康大学生参与了本研究。参与者完成了焦虑和抑郁自评量表（SAS 和 PHQ-9）。HRV 数据在运动期间和运动后 5 分钟内采集。多层感知器神经网络模型，包含几个具有相同配置的分支，用于数据处理。（3）结果：通过 5 折交叉验证方法，HRV 预测焦虑水平的平均准确率为无焦虑为 89.3%，轻度焦虑为 83.6%，中度至重度焦虑为 74.9%。对于抑郁水平，平均准确率为无抑郁为 90.1%，轻度抑郁为 84.2%，中度至重度抑郁为 82.1%。焦虑和抑郁评分的预测 R-squared 值分别为 0.62 和 0.41。（4）结论：研究表明，大学生运动及恢复期 HRV 可有效预测焦虑和抑郁水平。然而，评分预测的准确性需要进一步提高。与运动相关的 HRV 可以作为评估心理健康的非侵入性生物标志物。
