Real-Time Estimation of Arterial Partial Pressure of Carbon Dioxide in Patients Undergoing General Anesthesia: Predictive Modeling Study
JMIR Medical Informatics · 2025-09-16 · 13 · e64855-e64855
DOI: 10.2196/64855 ↗At a glance
Journal article in JMIR Medical Informatics, published on 2025-09-16. Written by Ah Ra Lee and 4 co-authors. Institution: Office of eHealth Research and Business, Seoul National University Bundang Hospital, 172, Dolma-ro, Bundang-gu, Seongnam-si, 13605, Republic of Korea. Major MEDLINE topics: Carbon Dioxide, Anesthesia, General, Monitoring, Intraoperative. Cited 1 times so far (Crossref); 34 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Adequate ventilation in mechanically ventilated patients is contingent upon the monitoring of the arterial partial pressure of carbon dioxide (PaCO 2 ) during general anesthesia. Despite its significance, continuous monitoring remains challenging due to the imprecision of noninvasive estimations and the invasive nature of traditional methods such as arterial blood gas analysis.
Objective
This study aimed to develop a machine learning model to continuously estimate PaCO 2 in mechanically ventilated patients, with the goal of potentially improving intraoperative monitoring accuracy under general anesthesia.
Methods
This retrospective study used the VitalDB dataset from Seoul National University Hospital, comprising records of 6388 noncardiac surgery patients between August 2016 and June 2017. After applying inclusion and exclusion criteria, data from 2304 surgical cases (4651 PaCO 2 measurement event points) were analyzed. The CatBoost regressor model was trained to predict PaCO 2 using noninvasive physiological parameters and clinical information. The model’s performance was evaluated using nested cross-validation across hypocapnic (45 mm Hg) subgroups and compared to conventional estimation methods based on end-tidal carbon dioxide (ETCO 2 ).
Results
The developed model demonstrated superior overall performance compared to traditional estimations. It achieved a mean absolute error of 2.38 mm Hg and an average intraclass correlation coefficient of 0.87. Furthermore, 90.02% of the model’s estimations fell within the clinically highly acceptable range (error
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Office of eHealth Research and Business, Seoul National University Bundang Hospital, 172, Dolma-ro, Bundang-gu, Seongnam-si, 13605, Republic of Korea.
- Department of Anesthesiology and Pain Medicine, Jeonbuk National University Medical School and Hospital, Jeonju, Republic of Korea.
- Department of Nuclear Medicine, Seoul National University Bundang Hospital, Seongnam-si, Republic of Korea.
- Department of Pediatrics, Jeonbuk National University School of Medicine, 20, Geonji-ro, Deokjin-gu, Jeonju, 54907, Republic of Korea, 82 632501460.
- Research Institute of Clinical Medicine, Jeonbuk National University-Biomedical Research Institute on Jeonbuk National University Hospital, Jeonju, Republic of Korea.
ORCID profiles: Ah Ra Lee, Jun Ho Lee, Sooyoung Yoo, Ho-Young Lee, Hyun Ho Kim
Cite
APA
Lee, A. R., Lee, J. H., Yoo, S., Lee, H. Y., & Kim, H. H. (2025). Real-Time Estimation of Arterial Partial Pressure of Carbon Dioxide in Patients Undergoing General Anesthesia: Predictive Modeling Study. JMIR Medical Informatics. https://doi.org/10.2196/64855
Vancouver
Lee AR, Lee JH, Yoo S, Lee HY, Kim HH. Real-Time Estimation of Arterial Partial Pressure of Carbon Dioxide in Patients Undergoing General Anesthesia: Predictive Modeling Study. JMIR Medical Informatics. 2025. doi:10.2196/64855
BibTeX
@article{Lee2025,
author = {Lee, Ah Ra and Lee, Jun Ho and Yoo, Sooyoung and Lee, Ho-Young and Kim, Hyun Ho},
title = {Real-Time Estimation of Arterial Partial Pressure of Carbon Dioxide in Patients Undergoing General Anesthesia: Predictive Modeling Study},
journal = {JMIR Medical Informatics},
year = {2025},
doi = {10.2196/64855}
}
EUVIMED