Stress is various mental health disorders including depression and anxiety among college students. Early stress diagnosis and intervention may lower the risk of developing mental illnesses. We examined a machine learning-based method for identification of stress using data collected in a naturalistic study utilizing self-reported stress as ground truth as well as physiological data such as heart rate and hand acceleration. The study involved 54 college students from a large campus who used wearable wrist-worn sensors and a mobile health (mHealth) application continuously for 40 days. The app gathered physiological data including heart rate and hand acceleration at one hertz frequency. The application also enabled users to self-report stress by tapping on the watch face, resulting in a time-stamped record of the self-reported stress. We created, evaluated, and analyzed machine learning algorithms for identifying stress episodes among college students using heart rate and accelerometer data. The XGBoost method was the most reliable model with an AUC of 0.64 and an accuracy of 84.5%. The standard deviation of hand acceleration, standard deviation of heart rate, and the minimum heart rate were the most important features for stress detection. This evidence may support the efficacy of identifying patterns in physiological reaction to stress using smartwatch sensors and may inform the design of future tools for real-time detection of stress.

翻译：压力是导致大学生抑郁和焦虑等多种心理健康障碍的因素。早期压力诊断和干预可降低罹患精神疾病的风险。我们研究了一种基于机器学习的方法，利用自然情境研究采集的数据（以自我报告压力为基准，以及心率和手部加速度等生理数据）进行压力识别。该研究涉及一所大型校园内的54名大学生，他们连续40天佩戴腕戴式可穿戴传感器并持续使用移动健康应用程序。该应用程序以1赫兹频率采集包括心率和手部加速度在内的生理数据，同时允许用户通过轻触表盘自我报告压力，生成带时间戳的自我报告压力记录。我们创建、评估并分析了基于心率和加速度计数据识别大学生压力事件的机器学习算法。XGBoost方法是最可靠的模型，其AUC值为0.64，准确率达84.5%。手部加速度标准差、心率标准差和最低心率是压力检测最重要的特征。这一证据可能支持利用智能手表传感器识别生理压力反应模式的有效性，并为未来实时压力检测工具的设计提供参考。