Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants

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 post 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.

Authors

Institutions

Publication Details

Journal
Journal of Clinical Monitoring and Computing
Published
2025-05-17
DOI
https://doi.org/10.1007/s10877-025-01301-2
Primary Topic
Anesthesia and Sedative Agents
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants

Justin Skowno, Fuchiang Tsui, Asif Padiyath, Ian Yuan et al.
Journal of Clinical Monitoring and Computing
Anesthesia and Sedative Agents
article

Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants

Justin Skowno, Fuchiang Tsui, Asif Padiyath, Ian Yuan, Mazhong Zhang, Vanessa A. Olbrecht, Andrew Davidson, Yifei Jiang, Jurgen C. de Graaff, Britta Sylvia von Ungern-Sternberg, László Vutskits, Allan F. Simpao, Yunxia Zuo, Hua‐Cheng Liu, J. Nick Pratap, Olivia Nelson, Jianming Zhang, Ping Zhao, Xingrong Song, Ting Xu, Rachit Kumar, Peter Szmuk, C. Dean Kurth
article en

Abstract

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 post 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.

Journal of Clinical Monitoring and ComputingVol. 39(5)
University of Geneva (CH), The University of Sydney (AU), Children's Hospital of Philadelphia (US), Johns Hopkins University (US), Thomas Jefferson University (US), Outcomes Research Consortium (US), The University of Melbourne (AU), The Kids Research Institute Australia (AU), The University of Western Australia (AU), Shanghai Jiao Tong University (CN), Cornell University (US), Sichuan University (CN), Wenzhou Medical University (CN), Johns Hopkins Medicine (US), Princess Margaret Hospital for Children (AU), Children's Hospital at Westmead (AU), West China Hospital of Sichuan University (CN), Shanghai Children's Medical Center (CN), Second Affiliated Hospital & Yuying Children's Hospital of Wenzhou Medical University (CN), University Hospital of Geneva (CH), Admiraal De Ruyter Ziekenhuis (NL), Weill Cornell Medicine (US), Perth Children's Hospital, University of Pennsylvania (US), China Medical University (CN)
Openalex Percentile: Top 81%
Anesthesia and Sedative Agents
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.