[Paper Review] Real-Time Stress Monitoring, Detection, and Management in College Students: A Wearable Technology and Machine-Learning Approach

Alan Ta, Nilsu Salgin+6 more|ArXiv.org|May 21, 2025

Emotion and Mood Recognition3 citations

TL;DR

Evaluates a wearable and ML-enabled mHealth intervention (mHELP) for real-time stress detection and self-management in college students via a 12-week randomized trial (n=117).

ABSTRACT

College students are increasingly affected by stress, anxiety, and depression, yet face barriers to traditional mental health care. This study evaluated the efficacy of a mobile health (mHealth) intervention, Mental Health Evaluation and Lookout Program (mHELP), which integrates a smartwatch sensor and machine learning (ML) algorithms for real-time stress detection and self-management. In a 12-week randomized controlled trial (n = 117), participants were assigned to a treatment group using mHELP's full suite of interventions or a control group using the app solely for real-time stress logging and weekly psychological assessments. The primary outcome, "Moments of Stress" (MS), was assessed via physiological and self-reported indicators and analyzed using Generalized Linear Mixed Models (GLMM) approaches. Similarly, secondary outcomes of psychological assessments, including the Generalized Anxiety Disorder-7 (GAD-7) for anxiety, the Patient Health Questionnaire (PHQ-8) for depression, and the Perceived Stress Scale (PSS), were also analyzed via GLMM. The finding of the objective measure, MS, indicates a substantial decrease in MS among the treatment group compared to the control group, while no notable between-group differences were observed in subjective scores of anxiety (GAD-7), depression (PHQ-8), or stress (PSS). However, the treatment group exhibited a clinically meaningful decline in GAD-7 and PSS scores. These findings underscore the potential of wearable-enabled mHealth tools to reduce acute stress in college populations and highlight the need for extended interventions and tailored features to address chronic symptoms like depression.

Motivation & Objective

• Investigate whether a wearable-enabled mHealth intervention can detect real-time stress in college students.
• Evaluate the efficacy of mHELP in reducing Moments of Stress (MS) compared with log-only control.
• Assess secondary psychological outcomes (anxiety, depression, perceived stress) using established scales.
• Explore whether real-time monitoring translates to improvements in self-reported mental health.

Proposed method

• 12-week randomized controlled trial with 117 participants.
• Participants allocated to treatment (full mHELP suite) or control (real-time logging and weekly assessments).
• Wearable smartwatch sensors used to detect stress; ML algorithms perform real-time stress detection.
• Generalized Linear Mixed Models (GLMM) used to analyze primary and secondary outcomes.
• Primary outcome: Moments of Stress (MS) derived from physiological and self-reported indicators.
• Secondary outcomes: GAD-7 (anxiety), PHQ-8 (depression), PSS (perceived stress).

Experimental results

Research questions

• RQ1 Does the full mHELP intervention reduce Moments of Stress in real time compared to logging-only control?
• RQ2 What is the impact of mHELP on anxiety (GAD-7), depression (PHQ-8), and perceived stress (PSS)?
• RQ3 Can wearable-enabled mHealth tools effectively support stress self-management in college students?
• RQ4 Are there differences in acute versus chronic mental health symptoms between groups over 12 weeks?

Key findings

• Treatment group showed a substantial decrease in Moments of Stress versus control.
• No notable between-group differences in GAD-7, PHQ-8, or PSS scores.
• Treatment group exhibited a clinically meaningful decline in GAD-7 and PSS scores.
• Findings indicate potential of wearable-enabled mHealth tools to reduce acute stress in college students.
• Results suggest need for extended interventions and tailored features for chronic symptoms like depression.