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

Journal: Journal of clinical monitoring and computing
Published Date: May 17, 2025

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.

Authors

  • Rachit Kumar
    Genomics and Computational Biology Graduate Group at the Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA.
  • Justin Skowno
    Department of Anaesthesia, The Children's Hospital at Westmead, Sydney, Australia.
  • Britta S von Ungern-Sternberg
    Department of Anaesthesia and Pain Medicine, Perth Children's Hospital, Perth, Australia.
  • Andrew Davidson
    Department of Computer Science and Software Engineering, University of Canterbury, Christchurch, New Zealand. andrew.davidson@pg.canterbury.ac.nz.
  • Ting Xu
    Bioresources Green Transformation Collaborative Innovation Center of Hubei Province, College of Life Sciences, Hubei University, Wuhan 430062, Hubei, China.
  • Jianmin Zhang
    Department of Neurosurgery, Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China.
  • Xingrong Song
    Department of Anesthesiology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, Guangdong, China.
  • Mazhong Zhang
    Department of Anesthesiology, Shanghai Children's Medical Center, Shanghai, China.
  • Ping Zhao
    Department of Information, Research Institute of Field Surgery, Daping Hospital of Army Medical University, 10 Changjiang Access Road, Chongqing, 400042, China.
  • Huacheng Liu
    Department of Anesthesiology and Perioperative Medicine, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, China.
  • Yifei Jiang
    Department of Chemistry, University of Washington, Seattle, Washington 98195, USA.
  • Yunxia Zuo
    Department of Anesthesiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
  • Jurgen C de Graaff
    Department of Anesthesiology, Adrz-Erasmus MC, Goes, The Netherlands.
  • Laszlo Vutskits
    Department of Anesthesiology, Pharmacology, Intensive Care, and Emergency Medicine, University Hospitals of Geneva, Geneva, Switzerland.
  • Vanessa A Olbrecht
    Department of Anesthesiology and Perioperative Medicine, Nemours Children's Hospital, Wilmington, DE, USA.
  • Peter Szmuk
    Department of Anesthesiology and Pain Management, Division of Anesthesiology, Children's Health System of Texas, University of Texas Southwestern Medical Center, Dallas, TX, USA.
  • Allan F Simpao
    Department of Anesthesiology and Critical Care Medicine, Children's Hospital of Philadelphia, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania.
  • Fuchiang Rich Tsui
    Department of Biomedical Informatics, University of Pittsburgh School of Medicine, 5607 Baum Boulevard, Pittsburgh, PA, United States; Intelligent System Program, University of Pittsburgh Dietrich School of Arts and Sciences, 210 South Bouquet Street, Pittsburgh, PA, United States. Electronic address: tsui2@pitt.edu.
  • Jayant Nick Pratap
    Department of Anesthesiology and Critical Care Medicine, The Children's Hospital of Philadelphia and the Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Asif Padiyath
    Department of Anesthesiology and Critical Care, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA.
  • Olivia Nelson
    Department of Anesthesiology and Critical Care Medicine, The Children's Hospital of Philadelphia and the Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Charles D Kurth
    Department of Anesthesiology and Critical Care Medicine and Neurology and Pediatrics, The Children's Hospital of Philadelphia and the Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Ian Yuan
    Department of Anesthesiology and Critical Care Medicine, The Children's Hospital of Philadelphia and the Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA. iyuan02@gmail.com.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals