Use of machine learning for predicting stress episodes based on wearable sensor data: A systematic review

This study consists of a systematic literature review that aims to explore the potential of integrating wearable sensor data and machine learning (ML) techniques for predicting stress episodes. It aims to identify prevalent sensors, key physiological features, and the effectiveness of ML methods in real-world stress monitoring and prediction.

This systematic review follows the PRISMA methodology, analyzing literature from January 2010 to June 2025. Data sources included IEEE Xplore, Elsevier, Springer, Multidisciplinary Digital Publishing Institute (MDPI), and paper repositories such as PubMed Central and the Association of Computing Machinery (ACM). The inclusion criteria encompassed studies that employed wearable devices for ML stress prediction, focusing on physiological data such as heart rate variability (HRV), skin conductance, and sleep patterns. Articles were screened for originality, clinical relevance, and methodological rigor.

Key findings highlighted the use of diverse wearable sensors, including electrodermal activity (EDA), photoplethysmography (PPG), and accelerometers. Commonly extracted features included HRV metrics, skin conductance levels, and respiratory patterns. ML models, such as Random Forest (RF), Support Vector Machines (SVM), and deep neural networks (DNN), have demonstrated high predictive accuracy (e.g., up to 99%). Despite promising results, challenges such as small sample sizes, variability in data quality, and the need for standardized protocols were noted.

Wearable sensors combined with ML algorithms provide scalable, real-time stress monitoring solutions, emphasizing proactive healthcare management. However, advancing this field requires addressing limitations through interdisciplinary collaboration and focusing on the accessibility and usability of technologies.

This study highlights the transformative role of wearable technologies in predicting stress, with implications for personalized health interventions, mental health support, and enhanced healthcare efficiency.