Strategies for Reliable Stress Recognition: A Machine Learning Approach Using Heart Rate Variability Features.

Stress recognition, particularly using machine learning (ML) with physiological data such as heart rate variability (HRV), holds promise for mental health interventions. However, limited datasets in affective computing and healthcare research can lead to inaccurate conclusions regarding the ML model performance. This study employed supervised learning algorithms to classify stress and relaxation states using HRV measures. To account for limitations associated with small datasets, robust strategies were implemented based on methodological recommendations for ML with a limited dataset, including data segmentation, feature selection, and model evaluation. Our findings highlight that the random forest model achieved the best performance in distinguishing stress from non-stress states. Notably, it showed higher performance in identifying stress from relaxation (F1-score: 86.3%) compared to neutral states (F1-score: 65.8%). Additionally, the model demonstrated generalizability when tested on independent secondary datasets, showcasing its ability to distinguish between stress and relaxation states. While our performance metrics might be lower than some previous studies, this likely reflects our focus on robust methodologies to enhance the generalizability and interpretability of ML models, which are crucial for real-world applications with limited datasets.

Short-Term Effects of Heart Rate Variability Biofeedback on Working Memory.

Drawing upon the well-documented impact of long-term heart rate variability biofeedback (HRVB) on psychophysiological responses, this study seeks to explore the short-term effects arising from a single HRVB session during and after paced breathing exercise. The research aligns with the neurovisceral integration model, emphasizing the link between heart rate variability (HRV) levels and cognitive performance. Therefore, a randomized controlled trial employing a between-subjects design was conducted with 38 participants. Each participant was assigned to either the paced breathing intervention group or the spontaneous breathing control group. The study assessed various parameters such as cardiac vagal tone, evaluated through vagally mediated HRV measures, and working memory, measured using the N-back task. Additionally, participants' affective states were assessed through self-reported questionnaires, specifically targeting attentiveness, fatigue, and serenity. The results notably reveal enhancements in the working memory task and an elevated state of relaxation and attention following the HRVB session, as evidenced by higher averages of correct responses, serenity and attentiveness scores. However, the findings suggest that this observed improvement is not influenced by changes in cardiac vagal tone, as assessed using a simple mediation analysis. In conclusion, this study presents promising insights into the impact of a single HRVB session, laying the foundation for future research advancements in this domain.