A Novel NICU Sleep State Stratification: Multiperspective Features, Adaptive Feature Selection and Ensemble Model

• Published in: IEEE transactions on biomedical engineering Vol. 72; no. 9; pp. 2684 - 2697
• Main Authors: Irfan, Muhammad, Subasi, Abdulhamit, Tang, Zhenning, Wang, Laishuan, Xu, Yan, Chen, Chen, Westerlund, Tomi, Chen, Wei
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2025
• Subjects: Accuracy; Adaptation models; Adaptive feature selection; Algorithms; and stacking model; Brain modeling; Classification algorithms; EEG; Electroencephalography; Electroencephalography - methods; Feature extraction; Female; Humans; Infant, Newborn; Intensive Care Units, Neonatal; Machine Learning; Male; multiperspective feature extraction and fusion; neonatal sleep; Pediatrics; Principal Component Analysis; Recording; Signal Processing, Computer-Assisted; Sleep; Sleep - physiology; Sleep Stages - physiology; Wavelet Analysis; Wavelet transforms

The examination of sleep patterns in newborns, particularly premature infants, is crucial for understanding neonatal development. This study presents an automated multi-sleep state classification approach for infants in neonatal intensive care units (NICU) using multiperspective feature extraction m...