Non-contact REM/NREM sleep staging from piezoelectric signals using respiratory and body-movement features with auxiliary TWED-based respiratory stability measures - Scorecard - MDSpire

Non-contact REM/NREM sleep staging from piezoelectric signals using respiratory and body-movement features with auxiliary TWED-based respiratory stability measures

  • By

  • Shaonan Wang

  • Jia Yu

  • Xianjun Yang

  • Diming Liu

  • Qingyuan Bai

  • Jiakuai Yu

  • Shuai Ding

  • Yang Xu

  • Daomin Zhu

  • June 15, 2026

  • 0 min

Share

Clinical Scorecard: Remote Sleep Stage Classification of REM and NREM Using Piezoelectric Sensors and Respiratory Stability Metrics Derived from TWED Analysis

At a Glance

CategoryDetail
ConditionREM/NREM sleep classification
Key MechanismsRespiratory pattern stability quantified by TWED-based RIS similarity features
Target PopulationClinical subjects undergoing sleep monitoring
Care SettingHome-like settings using non-contact piezoelectric sensing

Key Highlights

  • Achieved 84.39% accuracy in REM/NREM classification using combined features
  • TWED-based features improved Kappa and REM F1-score compared to conventional features
  • Low detection error and good agreement with PSG airflow in respiratory tests

Guideline-Based Recommendations

Diagnosis

  • Binary classification of REM and NREM sleep based on respiratory pattern stability

Management

  • Use as a low-burden adjunctive tool for offline monitoring and trend assessment

Monitoring & Follow-up

  • Continuous capture of respiratory dynamics and body movement via piezoelectric sensors

Risks

  • Not a replacement for PSG-based clinical diagnosis or real-time sleep staging

Patient & Prescribing Data

Clinical subjects monitored overnight

Non-contact monitoring may reduce burden compared to traditional PSG

Clinical Best Practices

  • Feature normalization within subjects for improved classification performance
  • Utilization of TWED-based features alongside conventional descriptors

Related Resources & Content

Original Source(s)

Non-contact REM/NREM sleep staging from piezoelectric signals using respiratory and body-movement features with auxiliary TWED-based respiratory stability measures

  • by Shaonan Wang, Jia Yu, Xianjun Yang, Diming Liu, Qingyuan Bai, Jiakuai Yu, Shuai Ding, Yang Xu, Daomin Zhu

  • June 15, 2026

Related Content

Indoor air quality in day-care centers, kindergartens, and primary schools: a pediatric health-oriented operational framework aligned with European and U.S. IAQ standards

The TREM2 paradox in fibrosis: a unified mechanism for opposite outcomes across organs

High-Dose Vitamin C Could Pose Risk in Severe Burns

“High-dose intravenous vitamin C administered early after injury did not reduce organ dysfunction or [mortality] and should not be a treatment in severe burns.”