Tilmanne Joëlle, Urbain Jérôme, Kothare Mayuresh V, Wouwer Alain Vande, Kothare Sanjeev V
Service de Théorie des Circuits et Traitement du Signal, Faculté Polytechnique de Mons, Mons, Belgium.
J Sleep Res. 2009 Mar;18(1):85-98. doi: 10.1111/j.1365-2869.2008.00706.x.
The aim of this study was to investigate two new scoring algorithms employing artificial neural networks and decision trees for distinguishing sleep and wake states in infants using actigraphy and to validate and compare the performance of the proposed algorithms with known actigraphy scoring algorithms. The study employed previously recorded longitudinal physiological infant data set from the Collaborative Home Infant Monitoring Evaluation (CHIME) study conducted between 1994 and 1998 [http://dccwww.bumc.bu.edu/ChimeNisp/Main_Chime.asp; Sleep26 (1997) 553] at five clinical sites around the USA. The original CHIME data set contains recordings of 1079 infants <1 year old. In our study, we used the overnight polysomnography scored data and ankle actimeter (Alice 3) raw data for 354 infants from this data set. The participants were heterogeneous and grouped into four categories: healthy term, preterm, siblings of SIDS and infants with apparent life-threatening events (apnea of infancy). The selection of the most discriminant actigraphy features was carried out using Fisher's discriminant analysis. Approximately 80% of all the epochs were used to train the artificial neural network and decision tree models. The models were then validated on the remaining 20% of the epochs. The use of artificial neural networks and decision trees was able to capture potentially nonlinear classification characteristics, when compared to the previously reported linear combination methods and hence showed improved performance. The quality of sleep-wake scoring was further improved by including more wake epochs in the training phase and by employing rescoring rules to remove artifacts. The large size of the database (approximately 337,000 epochs for 354 patients) provided a solid basis for determining the efficacy of actigraphy in sleep scoring. The study also suggested that artificial neural networks and decision trees could be much more routinely utilized in the context of clinical sleep search.
本研究的目的是调查两种采用人工神经网络和决策树的新评分算法，用于通过活动记录仪区分婴儿的睡眠和清醒状态，并验证和比较所提出算法与已知活动记录仪评分算法的性能。该研究使用了1994年至1998年在美国五个临床地点进行的协作家庭婴儿监测评估（CHIME）研究中先前记录的纵向生理婴儿数据集[http://dccwww.bumc.bu.edu/ChimeNisp/Main_Chime.asp；Sleep26（1997）553]。原始的CHIME数据集包含1079名1岁以下婴儿的记录。在我们的研究中，我们使用了该数据集中354名婴儿的夜间多导睡眠图评分数据和脚踝活动计（Alice 3）原始数据。参与者具有异质性，分为四类：健康足月儿、早产儿、婴儿猝死综合征的兄弟姐妹以及有明显危及生命事件（婴儿呼吸暂停）的婴儿。使用Fisher判别分析进行最具判别力的活动记录仪特征选择。所有时段中约80%用于训练人工神经网络和决策树模型。然后在其余20%的时段上对模型进行验证。与先前报道的线性组合方法相比，人工神经网络和决策树的使用能够捕捉潜在的非线性分类特征，因此表现出更好的性能。通过在训练阶段纳入更多清醒时段并采用重新评分规则以去除伪迹，睡眠-清醒评分的质量得到了进一步提高。数据库的规模较大（354名患者约337,000个时段）为确定活动记录仪在睡眠评分中的有效性提供了坚实的基础。该研究还表明，人工神经网络和决策树在临床睡眠检查的背景下可以更常规地使用。
