Scholarlink

<p>Sleep profoundly impacts health, yet current gold-standard Polysomnography (PSG) is constrained by cost, discomfort, and limited scalability for longitudinal monitoring. Ballistocardiography (BCG) offers a non-invasive and user-friendly alternative but often lacks the precision needed for reliable real-world applications. To address this gap, we propose BCGNet, a two-stage transfer learning model that is first pre-trained on 580,865 h of PSG and then fine-tuned and validated on 15,081 h of BCG (total 595,946 h of recordings). Across multiple validation cohorts, BCGNet achieves strong performance in 4-class sleep staging (F1: 0.710−0.817), Apnea-Hypopnea Index (AHI3%) estimation (Pearson’s <i>r</i> &gt; 0.95), and robust quantification of sleep continuity and architecture (ICC and Pearson’s <i>r</i> generally &gt;0.8). Notably, BCGNet maintains strong performance even on short daytime naps and demonstrates excellent generalizability across diverse external datasets. Deployed as a portable, contactless sleep tracking mat, BCGNet represents a major step towards scalable, user-friendly solutions for longitudinal home sleep monitoring, with important implications for population screening and personalized sleep medicine.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

BCGNet: an AI model trained on 600 K hours of sleep data for a novel under-pillow contactless monitoring device

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月3日

查看全文
  • Shigeng Chen,
  • Xuesong Chen,
  • Weijun Huang,
  • Fei Lei,
  • Chuxuan Shan,
  • Zengrui Jin,
  • Yunhan Shi,
  • Yichen Wang,
  • Rui Zhao,
  • Xing Xu,
  • Dongsheng Lv,
  • Yanru Li,
  • Shirui Pan,
  • Ambrose Chiang,
  • M. Brandon Westover,
  • Shenda Hong,
  • Chao Zhang,
  • Shankai Yin,
  • Chun-feng Liu,
  • Hongliang Yi,
  • Xiangdong Tang,
  • Yue Leng

摘要

Sleep profoundly impacts health, yet current gold-standard Polysomnography (PSG) is constrained by cost, discomfort, and limited scalability for longitudinal monitoring. Ballistocardiography (BCG) offers a non-invasive and user-friendly alternative but often lacks the precision needed for reliable real-world applications. To address this gap, we propose BCGNet, a two-stage transfer learning model that is first pre-trained on 580,865 h of PSG and then fine-tuned and validated on 15,081 h of BCG (total 595,946 h of recordings). Across multiple validation cohorts, BCGNet achieves strong performance in 4-class sleep staging (F1: 0.710−0.817), Apnea-Hypopnea Index (AHI3%) estimation (Pearson’s r > 0.95), and robust quantification of sleep continuity and architecture (ICC and Pearson’s r generally >0.8). Notably, BCGNet maintains strong performance even on short daytime naps and demonstrates excellent generalizability across diverse external datasets. Deployed as a portable, contactless sleep tracking mat, BCGNet represents a major step towards scalable, user-friendly solutions for longitudinal home sleep monitoring, with important implications for population screening and personalized sleep medicine.