Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants
Journal of Clinical Monitoring and Computing · 17.05.2025 · 39 (5) · 999-1014
DOI: 10.1007/s10877-025-01301-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Monitoring and Computing, online erschienen am 17.05.2025. Verfasst von Rachit Kumar und 23 weiteren Autor:innen. Beteiligte Einrichtung: Genomics and Computational Biology Graduate Group at the Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA. Hauptthemen laut MEDLINE: Electroencephalography, Sevoflurane, Machine Learning, Anesthetics, Inhalation. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Stan Perron Charitable Foundation and a National Health and Medical Research Council Investigator Grant.
Abstract (Originalsprache)
Processed electroencephalography (EEG) indices used to guide anesthetic dosing in adults are not validated in young infants. Raw EEG can be processed mathematically, yielding quantitative EEG parameters (qEEG). We hypothesized that machine learning combined with qEEG can accurately classify expired sevoflurane concentrations in young infants. Knowledge from this may contribute to development of future infant-specific EEG algorithms. Frontal EEG collected from infants ≤ 3 months were time-matched as one-minute epochs to expired sevoflurane (eSevo). Fifteen qEEG parameters were extracted from each epoch and eight machine learning models combined the qEEG to classify each epoch into one of four eSevo levels (%): 0.1–1.0, 1.0–2.1, 2.1–2.9, and > 2.9. 64 epochs formed the p ost hoc SHAP dataset to determine the qEEG that contributed most to the model. The remaining epochs were randomly split 50 times into 80/20 training/testing sets. Accuracy and F1-score determined model performance. 42 infants provided 4574 epochs. The top classifiers K-nearest neighbors, default multi-layer perceptron, and support vector machine achieved 67.5–68.7% accuracy. Burst suppression ratio and entropy β were the top contributors to the models. Post hoc analysis performed without burst suppression ratio yielded similar prediction performance. In young infants, machine learning applied to qEEG predicted eSevo levels with moderate success. Burst suppression ratio, the most important contributor, represented an efficient EEG feature that encapsulated underlying EEG changes seen on other qEEG features. These results provided insight into EEG parameter selection and optimal machine learning models used for future development of infant-specific EEG algorithms.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Genomics and Computational Biology Graduate Group at the Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA.
- Department of Anaesthesia, The Children's Hospital at Westmead, Sydney, Australia.
- School of Child and Adolescent Health, The University of Sydney, Sydney, Australia.
- Department of Anaesthesia and Pain Medicine, Perth Children's Hospital, Perth, Australia.
- Perioperative Care Program, Perioperative Medicine Team, Telethon Kids Institute, Perth, Australia.
- Institute for Paediatric Perioperative Excellence, The University of Western Australia, Perth, Australia.
Förderung
- Stan Perron Charitable Foundation and a National Health and Medical Research Council Investigator Grant
Zitieren
APA
Kumar, R., Skowno, J., von Ungern-Sternberg, B. S., Davidson, A., Xu, T., Zhang, J., Song, X., Zhang, M., Zhao, P., Liu, H., Jiang, Y., Zuo, Y., de Graaff, J. C., Vutskits, L., Olbrecht, V. A., Szmuk, P., Simpao, A. F., Tsui, F. R., Pratap, J. N., …, & BRAIN Collaborative Investigators (2025). Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants. Journal of Clinical Monitoring and Computing, 39(5), 999-1014. https://doi.org/10.1007/s10877-025-01301-2
Vancouver
Kumar R, Skowno J, von Ungern-Sternberg BS, Davidson A, Xu T, Zhang J, et al. Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants. Journal of Clinical Monitoring and Computing. 2025;39(5):999-1014. doi:10.1007/s10877-025-01301-2
BibTeX
@article{Kumar2025,
author = {Kumar, Rachit and Skowno, Justin and von Ungern-Sternberg, Britta S and Davidson, Andrew and Xu, Ting and Zhang, Jianmin and Song, XingRong and Zhang, Mazhong and Zhao, Ping and Liu, Huacheng and Jiang, Yifei and Zuo, Yunxia and de Graaff, Jurgen C and Vutskits, Laszlo and Olbrecht, Vanessa A and Szmuk, Peter and Simpao, Allan F and Tsui, Fuchiang Rich and Pratap, Jayant Nick and Padiyath, Asif and Nelson, Olivia and Kurth, Charles D and Yuan, Ian and BRAIN Collaborative Investigators, BRAIN Collaborative Investigators},
title = {Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants},
journal = {Journal of Clinical Monitoring and Computing},
year = {2025},
volume = {39},
number = {5},
pages = {999--1014},
doi = {10.1007/s10877-025-01301-2}
}
EUVIMED