Machine Learning Frameworks for Wearable-Based Stress Modeling in Naturalistic Settings: Scoping Review

Area of Science:

• Wearable technology
• Machine learning
• Mental health assessment

Background:

• Modern life's pervasive stress impacts mental and physical health.
• Wearable devices excel at physical fitness tracking, but mental stress detection is nascent.
• Objective assessment of stress using technology is a growing research area.

Purpose of the Study:

• To review recent studies on wearable-based stress detection in naturalistic settings.
• To characterize machine learning frameworks used in these studies.
• To propose a standardized reporting framework inspired by model cards.

Main Methods:

• Systematic scoping review using PRISMA-ScR checklist.
• Searched major scientific databases (PubMed, IEEE, ACM, etc.).
• Included studies on healthy adults, naturalistic settings, wearable devices, and machine learning for stress detection.

Main Results:

• 34 eligible studies (2017-2024) analyzed.
• Key machine learning decisions (problem formulation, ground truth, algorithms) were examined.
• A model card framework for reporting was proposed based on study findings.

Conclusions:

• Highlights trends in machine learning for wearable-based stress detection.
• Emphasizes need for standardized reporting of datasets and ML decisions.
• Stresses importance of addressing real-world data collection challenges.