在混合队列环境中使用深度残差网络进行自动睡眠阶段分类
Automatic sleep stage classification with deep residual networks in a mixed-cohort setting
摘要：
研究目的：睡眠阶段评分由睡眠专家手动执行，并且易于对评分规则进行主观解释，评分者内部和评分者之间的可靠性较低。许多自动化系统依赖于一些小规模的数据库来开发模型，因此对新数据集的泛化能力是未知的。我们研究了一种新的深度神经网络，以评估几个大规模队列的可推广性。方法：使用来自5个不同队列的15684个多导睡眠图研究开发了深度神经网络模型。我们应用了四种不同的场景：1）模型中不同时间尺度的影响; 2）相对于其他队列对单个队列的表现，单个队列对其他更小、更大或相等规模的队列的表现; 3）与使用单源数据相比，改变混合队列训练数据的比例;以及4）比较在来自2、3和4个群组的数据的组合上训练的模型。结果如下：随着训练数据比例的增加，整体分类精度得到提高（0.25 $\%$：0.782 $\pm$ 0.097，95 $\%$ CI [0.777-0.787]; 100 $\%$：0.869 $\pm$ 0.064，95 $\%$ CI [0.864-0.872]），且数据源数量增加（2：0.788 $\pm$ 0.102，95 PDMATHAMM CI [0.787-0.790]; 3：0.808 $\pm$ 0.092，95 PDMATHAMM CI [0.807-0.810]; 4：0.821 $\pm$ 0.085，95 $\%$ CI [0.819-0.823]）。不同的组群对其他组群的概括程度不同。结论：基于深度学习算法的自动睡眠阶段评分系统应考虑尽可能多的数据，以确保适当的泛化。应当为今后的研究提供用于基准测试的公共数据集。
英文摘要：
Study Objectives: Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts. Methods: A deep neural network model was developed using 15684 polysomnography studies from five different cohorts. We applied four different scenarios: 1) impact of varying time-scales in the model; 2) performance of a single cohort on other cohorts of smaller, greater or equal size relative to the performance of other cohorts on a single cohort; 3) varying the fraction of mixed-cohort training data compared to using single-origin data; and 4) comparing models trained on combinations of data from 2, 3, and 4 cohorts. Results: Overall classification accuracy improved with increasing fractions of training data (0.25$\%$: 0.782 $\pm$ 0.097, 95$\%$ CI [0.777-0.787]; 100$\%$: 0.869 $\pm$ 0.064, 95$\%$ CI [0.864-0.872]), and with increasing number of data sources (2: 0.788 $\pm$ 0.102, 95$\%$ CI [0.787-0.790]; 3: 0.808 $\pm$ 0.092, 95$\%$ CI [0.807-0.810]; 4: 0.821 $\pm$ 0.085, 95$\%$ CI [0.819-0.823]). Different cohorts show varying levels of generalization to other cohorts. Conclusions: Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.
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。
