Flexible pressure sensor pants for app-supported sleep posture monitoring: Feasibility, accuracy, and user experience study

Abstract

Objective This study aims to develop and validate an innovative wearable system—flexible pressure sensor pants—to overcome the privacy, comfort, and portability limitations of conventional sleep posture monitoring methods (e.g., infrared imaging and pressure-sensitive mattresses). The study evaluates the system’s posture classification performance and its feasibility for continuous monitoring in real-world settings. Methods Thirty-four young adults were recruited. During short-term wakefulness trials, participants wore the sensor-integrated sleep pants and assumed four predefined postures (supine, prone, left lateral, and right lateral), yielding 202 annotated posture instances. A confusion matrix was employed to derive sensitivity, specificity, and overall accuracy. Overnight monitoring involved concurrent data acquisition from the sensorized sleep pants and an infrared camera. Statistical analyses included paired t-tests or Mann–Whitney U tests to examine inter-method differences, Bland–Altman plots for agreement assessment, and scatter plots to quantify linear correlations. User feedback on comfort and impact on sleep was collected via questionnaire. Results In awake trials, the system achieved 96% overall accuracy, with mean sensitivity and specificity of 0.95 (0.93–0.98) and 0.98 (0.97–0.99), respectively. Overnight data revealed no statistically significant differences between the two monitoring methods across all postures. Bland–Altman analyses indicated high concordance, while scatter plots demonstrated strong correlations: prone (R=0.5423, p<.001), supine (R=0.8365, p<.001), right lateral (R=0.9108, p<.001), and left lateral (R=0.4665, p<.001). User satisfaction reached 94.1%. Conclusion Flexible pressure sensor pants demonstrated high accuracy, strong agreement with infrared monitoring. The high user satisfaction and practical convenience indicate their potential to meet essential requirements for sleep posture assessment. Compared with traditional methods, they offer greater comfort, portability, and privacy protection, supporting feasibility for real-world sleep posture monitoring.