Validation of a consumer-grade wearable activity tracker for sleep measurement in Vietnamese patients

Introduction: The increasing use of wearable activity trackers (WAT) for home-based sleep assessment has raised necessity to clarify their accuracy, particularly in resource-limited settings. This study aimed to validate WAT by polysomnography (PSG) for measuring key sleep parameters—including total sleep time (TST), sleep efficiency (SE), wake after sleep onset (WASO), sleep onset latency (SOL), and sleep stage distribution—in a Vietnamese clinical population, with implications for primary care applications.

Methods: This cross-sectional study was conducted at the University Medical Center-Ho Chi Minh City, Vietnam, from December 2023 to July 2024. Sleep data were collected from 47 patients undergoing overnight PSG while simultaneously wearing a WAT. Sensitivity, specificity, and accuracy in detecting sleep versus wakefulness were assessed using epoch-by-epoch comparisons. Bland-Altman analysis was used to evaluate the agreement between WAT and PSG measurements, with mean differences and limits of agreement calculated for each sleep parameter.

Results: The WAT demonstrated high sensitivity (93%) but low specificity (44%) and an accuracy of 79% in identifying sleep versus wakefulness when compared to PSG. No significant differences were found between the two devices in measuring total sleep time (TST), sleep efficiency (SE), sleep onset latency (SOL), and sleep stages. However, the WAT significantly underestimated wake-after-sleep onset (WASO) compared to PSG (p=0.011).

Conclusion: The results are promising, but further confirmation in larger studies is required to confirm the utility of WAT in primary care settings in Vietnam.