Scholarlink

<p>Automatic sleep staging with deep learning has advanced considerably, yet clinical adoption remains hindered by limited generalization, model bias, and inconsistent evaluation practices. We present SLEEPYLAND, an open-source framework comprising ~ 220,000 h of in-domain and ~ 84,000 h of out-of-domain polysomnographic recordings, spanning diverse ages, disorders, and hardware configurations. We release pre-trained state-of-the-art models, evaluating them across single- and multi-channel EEG/EOG setups. We introduce SOMNUS, an ensemble that integrates models via soft-voting, achieving robust performance across 24 datasets (macro-F1, 68.7–87.2%), outperforming individual models in 94.9% of cases and exceeding prior state-of-the-art. Exploiting the Bern-Sleep-Wake-Registry (<i>N</i> = 6633), we show that while SOMNUS improves generalization, no model architecture consistently minimizes model demographic/clinical bias. On multi-annotated datasets, SOMNUS surpasses the best human scorer (macro-F1, 85.2% vs 80.8% on DOD-H, and 80.2% vs 75.9% on DOD-O), more closely reproducing consensus. Finally, ensemble disagreement metrics predict scorer ambiguity (ROC-AUC 82.8%), providing reliable proxies for human uncertainty.</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

SLEEPYLAND: trust begins with fair evaluation of automatic sleep staging models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月16日

查看全文
  • Alvise Dei Rossi,
  • Matteo Metaldi,
  • Michal Bechny,
  • Irina Filchenko,
  • Julia van der Meer,
  • Markus H. Schmidt,
  • Claudio L. A. Bassetti,
  • Athina Tzovara,
  • Francesca D. Faraci,
  • Luigi Fiorillo

摘要

Automatic sleep staging with deep learning has advanced considerably, yet clinical adoption remains hindered by limited generalization, model bias, and inconsistent evaluation practices. We present SLEEPYLAND, an open-source framework comprising ~ 220,000 h of in-domain and ~ 84,000 h of out-of-domain polysomnographic recordings, spanning diverse ages, disorders, and hardware configurations. We release pre-trained state-of-the-art models, evaluating them across single- and multi-channel EEG/EOG setups. We introduce SOMNUS, an ensemble that integrates models via soft-voting, achieving robust performance across 24 datasets (macro-F1, 68.7–87.2%), outperforming individual models in 94.9% of cases and exceeding prior state-of-the-art. Exploiting the Bern-Sleep-Wake-Registry (N = 6633), we show that while SOMNUS improves generalization, no model architecture consistently minimizes model demographic/clinical bias. On multi-annotated datasets, SOMNUS surpasses the best human scorer (macro-F1, 85.2% vs 80.8% on DOD-H, and 80.2% vs 75.9% on DOD-O), more closely reproducing consensus. Finally, ensemble disagreement metrics predict scorer ambiguity (ROC-AUC 82.8%), providing reliable proxies for human uncertainty.