Flexible pressure sensor pants for app-supported sleep posture monitoring: Feasibility, accuracy, and user experience study
Authors:
Open Access
- 1 February 2026
- journal article
- research article
- Published by SAGE Publications in Digital Health
- Vol. 12
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.Keywords
Funding Information
- Yunnan Academician Expert Workstation (202205AF150058)
- Science and Technology Commission of Shanghai Municipality (25010702100)
- Science and Technology Commission of Shanghai Municipality (23015820300)
- National Natural Science Foundation of China (82372442)
This publication has 22 references indexed in Scilit:
- Relationship Between Sleep Posture and Low Back Pain: A Systematic ReviewMusculoskeletal Care, 2025
- Millimeter-wave radar based sleep posture transition dataset: SPTData in Brief, 2025
- DeepLPos: a comprehensive hybrid deep learning model for lying position recognition using a tactile sensor array systemMeasurement Science and Technology, 2024
- Sleep State Monitoring System Based on Flexible Pressure Sensor Arrays for Evaluating Sleep QualityIEEE Sensors Journal, 2024
- An interpretable framework for sleep posture change detection and postural inactivity segmentation using wrist kinematicsScientific Reports, 2023
- System Based on Artificial Intelligence Edge Computing for Detecting Bedside Falls and Sleep PostureIEEE Journal of Biomedical and Health Informatics, 2023
- Human Sleeping Posture Recognition Based on Sleeping Pressure ImageIEEE Sensors Journal, 2022
- Sleep deprivation and its association with diseases- a reviewSleep Medicine, 2021
- Lying posture affects sleep structures and cortical activities: a simultaneous EEG-fMRI imaging of the sleeping and waking brainBrain Imaging and Behavior, 2020
- Single-layered ultra-soft washable smart textiles for all-around ballistocardiograph, respiration, and posture monitoring during sleepBiosensors and Bioelectronics, 2020