Study Objectives: Despite frequent sleep disruption in the pediatric intensive care unit, bedside sleep monitoring in real time is currently not available. Supervised machine learning applied to electrocardiography data may provide a solution, because cardiovascular dynamics are directly modulated by the autonomic nervous system during sleep. Methods: This retrospective study used hospital-based polysomnography recordings obtained in noncritically ill children between 2017 and 2021. Six age categories were defined: 6–12 months, 1–3 years, 3–5 years, 5–9 years, 9–13 years, and 13–18 years. Features were derived in time, frequency, and nonlinear domain from preprocessed electrocardiography data. Sleep classification models were developed for 2, 3, 4, and 5 states using logistic regression, random forest, and XGBoost classifiers during 5-fold nested cross-validation. Models were additionally validated across age categories. Results: A total of 90 noncritically ill children were included with a median (Q1, Q3) recording length of 549.0 (494.8, 601.3) minutes. The 3 models obtained an area under the receiver operator characteristic curve of 0.72–0.78 with minimal variation across classifiers and age categories. Balanced accuracies were 0.70–0.72, 0.59–0.61, 0.50–0.51, and 0.41–0.42 for 2, 3, 4, and 5 states, respectively. Generally, the XGBoost model obtained the highest balanced accuracy (P < .05), except for 5 states for which logistic regression excelled (P = .67). Conclusions: Electrocardiography-based machine learning models are a promising and noninvasive method for automated sleep classification directly at the bedside of noncritically ill children aged 6 months–18 years. Models obtained moderate-to-good performance for 2- and 3-state classification.

This study aimed to develop an open-source algorithm for the pressure-reactivity index (PRx) to monitor cerebral autoregulation (CA) in pediatric severe traumatic brain injury (sTBI) and compared derived optimal cerebral perfusion pressure (CPPopt) with real-time CPP in relation to long-term outcome. Retrospective study in children (< 18 years) with sTBI admitted to the pediatric intensive care unit (PICU) for intracranial pressure (ICP) monitoring between 2016 and 2023. ICP was analyzed on an insult basis and correlated with outcome. PRx was calculated as Pearson correlation coefficient between ICP and mean arterial pressure. CPPopt was derived as weighted average of CPP-PRx over time. Outcome was determined via Pediatric Cerebral Performance Category (PCPC) scale at one year post-injury. Logistic regression and mixed effect models were developed to associate PRx and CPPopt with outcome. In total 50 children were included, 35 with favorable (PCPC 1–3) and 15 with unfavorable outcome (PCPC 4–6). ICP insults correlated with unfavorable outcome at 20 mmHg for 7 min duration. Mean CPPopt yield was 75.4% of monitoring time. Mean and median PRx and CPPopt yield associated with unfavorable outcome, with odds ratio (OR) 2.49 (1.38–4.50), 1.38 (1.08–1.76) and 0.95 (0.92–0.97) (p < 0.001). PRx thresholds 0.0, 0.20, 0.25 and 0.30 resulted in OR 1.01 (1.00–1.02) (p < 0.006). CPP in optimal range associated with unfavorable outcome on day one (0.018, p = 0.029) and four (-0.026, p = 0.025). Our algorithm can obtain optimal targets for pediatric neuromonitoring that showed association with long-term outcome, and is now available open source.

STUDY OBJECTIVES: Although sleep is frequently disrupted in the pediatric intensive care unit, it is currently not possible to perform real-time sleep monitoring at the bedside. In this study, spectral band powers of electroencephalography data are used to derive a simple index for sleep classification. METHODS: Retrospective study at Erasmus MC Sophia Children's Hospital, using hospital-based polysomnography recordings obtained in non-critically ill children between 2017 and 2021. Six age categories were defined: 6-12 months, 1-3 years, 3-5 years, 5-9 years, 9-13 years, and 13-18 years. Candidate index measures were derived by calculating spectral band powers in different frequent frequency bands of smoothed electroencephalography. With the best performing index, sleep classification models were developed for two, three, and four states via decision tree and five-fold nested cross-validation. Model performance was assessed across age categories and electroencephalography channels. RESULTS: In total 90 patients with polysomnography were included, with a mean (standard deviation) recording length of 10.3 (1.1) hours. The best performance was obtained with the gamma to delta spectral power ratio of the F4-A1 and F3-A1 channels with smoothing. Balanced accuracy was 0.88, 0.74, and 0.57 for two-, three-, and four-state classification. Across age categories, balanced accuracy ranged between 0.83 and 0.92 and 0.72 and 0.77 for two- and three-state classification, respectively. CONCLUSIONS: We propose an interpretable and generalizable sleep index derived from single-channel electroencephalography for automated sleep monitoring at the bedside in non-critically ill children ages 6 months to 18 years, with good performance for two- and three-state classification. CITATION: van Twist E, Hiemstra FW, Cramer ABG, et al. An electroencephalography-based sleep index and supervised machine learning as a suitable tool for automated sleep classification in children. J Clin Sleep Med. 2024;20(3):389-397.