arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.09793cs.LGq-bio.QM
收藏

全自动睡眠分期:一种通用深度神经网络在帕金森病和孤立性快速眼动睡眠行为障碍中的多中心验证

Fully-automated sleep staging: multicenter validation of a generalizable deep neural network for Parkinson's disease and isolated REM sleep behavior disorder

Aarhus University(奥胡斯大学);Aarhus University Hospital(奥胡斯大学医院);Lundbeck Foundation Parkinson’s Disease Research Center (PACE)(伦德贝克基金会帕金森病研究中心(PACE));University of Cologne(科隆大学);University Hospital Cologne(科隆大学医院);Institute for Biomedical Informatics, Faculty of Medicine and University Hospital Cologne(科隆大学医学院暨科隆大学医院生物医学信息学研究所);Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital Cologne(科隆大学医学院暨科隆大学医院科隆分子医学中心(CMMC));Research Center Juelich(于利希研究中心);University of Bonn(波恩大学);University Hospital Bonn(波恩大学医院);German Center for Neurodegenerative Diseases (DZNE)(德国神经退行性疾病中心(DZNE));Glostrup University Hospital(格洛斯楚普大学医院);Danish Center for Sleep Medicine(丹麦睡眠医学中心)
Jesper Strøm, Casper Skjærbæk, Natasha Becker Bertelsen, Steffen Torpe Simonsen, Niels Okkels, David Bertram, Sinah Röttgen, Konstantin Kufer, Kaare B. Mikkelse… 展开作者

Jesper Strøm, Casper Skjærbæk, Natasha Becker Bertelsen, Steffen Torpe Simonsen, Niels Okkels, David Bertram, Sinah Röttgen, Konstantin Kufer, Kaare B. Mikkelsen, Marit Otto, Poul Jørgen Jennum, Per Borghammer, Michael Sommerauer, Preben Kidmose

AI总结:

本研究开发了一种通用深度神经网络,用于全自动睡眠分期,通过多中心验证提高了帕金森病和孤立性快速眼动睡眠行为障碍的诊断准确性。

摘要:

孤立性快速眼动睡眠行为障碍(iRBD)是帕金森病(PD)的关键前驱标志物,视频多导睡眠图(vPSG)仍然是诊断的金标准。然而,由于EEG异常和睡眠碎片化,神经退行性疾病中的手动睡眠分期尤其具有挑战性,使PSG评估成为部署新RBD筛查技术的瓶颈。我们采用了U-Sleep深度神经网络,用于在PD和iRBD中实现通用的睡眠分期。一个基于大规模多中心非神经退行性数据集(PUB;19,236个PSG,12个中心)预训练的U-Sleep模型被在两个中心( Lundbeck基金会帕金森病研究中心(PACE)和科隆-波恩队列(CBC);112例PD,138例iRBD,89例年龄匹配的对照组)的研究数据集上进行微调。所得模型在丹麦睡眠医学中心(DCSM;81例PD,36例iRBD,87例睡眠诊所对照组)的独立数据集上进行了评估。一组PSG在人类评分者与模型之间一致性的较低(Cohen的κ < 0.6)被重新评分由第二位盲评人类评分者以确定分歧源。最后,我们应用基于置信度的阈值来优化REM睡眠分期。预训练的模型在PUB中实现了平均κ=0.81,但直接应用于PACE/CBC时κ=0.66。通过微调模型,我们开发了一个通用模型,在PACE/CBC上κ=0.74(p < 0.001 vs. 预训练模型)。在DCSM中,平均和中位数κ从0.60增加到0.64(p < 0.001)和0.64增加到0.69(p < 0.001)。在评分者研究中,PSG在模型和初始评分者之间一致性较低时,人类评分者之间也表现出相似的低一致性。应用置信度阈值将正确识别的REM睡眠片段比例从85%提高到95.5%,同时保持95%的受试者有足够的(>5分钟)REM睡眠。

英文摘要:

Isolated REM sleep behavior disorder (iRBD) is a key prodromal marker of Parkinson's disease (PD), and video-polysomnography (vPSG) remains the diagnostic gold standard. However, manual sleep staging is particularly challenging in neurodegenerative diseases due to EEG abnormalities and fragmented sleep, making PSG assessments a bottleneck for deploying new RBD screening technologies at scale. We adapted U-Sleep, a deep neural network, for generalizable sleep staging in PD and iRBD. A pretrained U-Sleep model, based on a large, multisite non-neurodegenerative dataset (PUB; 19,236 PSGs across 12 sites), was fine-tuned on research datasets from two centers (Lundbeck Foundation Parkinson's Disease Research Center (PACE) and the Cologne-Bonn Cohort (CBC); 112 PD, 138 iRBD, 89 age-matched controls. The resulting model was evaluated on an independent dataset from the Danish Center for Sleep Medicine (DCSM; 81 PD, 36 iRBD, 87 sleep-clinic controls). A subset of PSGs with low agreement between the human rater and the model (Cohen's $κ$ < 0.6) was re-scored by a second blinded human rater to identify sources of disagreement. Finally, we applied confidence-based thresholds to optimize REM sleep staging. The pretrained model achieved mean $κ$ = 0.81 in PUB, but $κ$ = 0.66 when applied directly to PACE/CBC. By fine-tuning the model, we developed a generalized model with $κ$ = 0.74 on PACE/CBC (p < 0.001 vs. the pretrained model). In DCSM, mean and median $κ$ increased from 0.60 to 0.64 (p < 0.001) and 0.64 to 0.69 (p < 0.001), respectively. In the interrater study, PSGs with low agreement between the model and the initial scorer showed similarly low agreement between human scorers. Applying a confidence threshold increased the proportion of correctly identified REM sleep epochs from 85% to 95.5%, while preserving sufficient (> 5 min) REM sleep for 95% of subjects.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑