{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:02Z","timestamp":1785545042315,"version":"3.56.0"},"reference-count":34,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n \n Adequate ventilation in mechanically ventilated patients is contingent upon the monitoring of the arterial partial pressure of carbon dioxide (PaCO\n 2<\/jats:sub>\n ) 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.\n <\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n \n This study aimed to develop a machine learning model to continuously estimate PaCO\n 2<\/jats:sub>\n in mechanically ventilated patients, with the goal of potentially improving intraoperative monitoring accuracy under general anesthesia.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n 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\n 2<\/jats:sub>\n measurement event points) were analyzed. The CatBoost regressor model was trained to predict PaCO\n 2<\/jats:sub>\n using noninvasive physiological parameters and clinical information. The model\u2019s performance was evaluated using nested cross-validation across hypocapnic (<35 mm Hg), normocapnic (35\u201045 mm Hg), and hypercapnic (>45 mm Hg) subgroups and compared to conventional estimation methods based on end-tidal carbon dioxide (ETCO\n 2<\/jats:sub>\n ).\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n 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\u2019s estimations fell within the clinically highly acceptable range (error<\u00b15 mm Hg) while only 1.20% of errors exceeded \u00b110 mm Hg. Performance improvements were observed across all PaCO\n 2<\/jats:sub>\n subgroups.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n \n The developed model provides more accurate and reliable estimates of PaCO\n 2<\/jats:sub>\n than traditional ETCO\n 2<\/jats:sub>\n -based methods. This approach shows potential for facilitating real-time monitoring and timely clinical interventions. This study demonstrated the potential of artificial intelligence to enhance continuous monitoring of PaCO\n 2<\/jats:sub>\n ; however, further validation, including prospective studies assessing clinical impact, is necessary.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/64855","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:41:52Z","timestamp":1758044512000},"page":"e64855-e64855","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Estimation of Arterial Partial Pressure of Carbon Dioxide in Patients Undergoing General Anesthesia: Predictive Modeling Study"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1890-2443","authenticated-orcid":false,"given":"Ah Ra","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9424-8589","authenticated-orcid":false,"given":"Jun Ho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8620-4925","authenticated-orcid":false,"given":"Sooyoung","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6518-0602","authenticated-orcid":false,"given":"Ho-Young","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7379-6041","authenticated-orcid":false,"given":"Hyun Ho","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/j.bpa.2015.08.008","article-title":"Effects of anesthesia on the respiratory system","volume":"29","author":"Hedenstierna","journal-title":"Best Pract Res Clin Anaesthesiol"},{"issue":"12","key":"R2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10122656","article-title":"Management of intraoperative mechanical ventilation to prevent postoperative complications after general anesthesia: a narrative review","volume":"10","author":"Fogagnolo","journal-title":"J Clin Med"},{"issue":"5","key":"R3","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1213\/ANE.0000000000006106","article-title":"Ventilation strategies during general anesthesia for noncardiac surgery: a systematic review and meta-analysis","volume":"135","author":"Bolther","journal-title":"Anesth Analg"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1213\/00000539-199107000-00009","article-title":"Continuous measurement of intraarterial pHa, PaCO2, and PaO2 in the operating room","volume":"73","author":"Barker","journal-title":"Anesth Analg"},{"key":"R5","unstructured":"Messina Z Patrick H . Partial pressure of carbon dioxide. In: StatPearls [Internet]. StatPearls Publishing; 2022. URL: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK551648 [Accessed 08-09-2025]"},{"key":"R6","unstructured":"WHO. WHO Guidelines on Drawing Blood: Best Practices in Phlebotomy. World Health Organization; 2010."},{"issue":"4","key":"R7","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djw315","article-title":"Burdensome research procedures in trials: why less is more","volume":"109","author":"Kimmelman","journal-title":"J Natl Cancer Inst"},{"issue":"5","key":"R8","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1177\/1556264620903563","article-title":"Risk assessment of medical study procedures in the documents submitted to a research ethics committee","volume":"15","author":"Happo","journal-title":"J Empir Res Hum Res Ethics"},{"issue":"3","key":"R9","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1097\/ANA.0000000000000322","article-title":"The effect of position on PaCO2 and PETCO2 in patients undergoing cervical spine surgery in supine and prone position","volume":"29","author":"Yadav","journal-title":"J Neurosurg Anesthesiol"},{"issue":"9","key":"R10","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1111\/anae.15501","article-title":"Recommendations for standards of monitoring during anaesthesia and recovery 2021","volume":"76","author":"Klein","journal-title":"Anaesthesia"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/710537","article-title":"Evaluation of differences between PaCO2 and ETCO2 by age as measured during general anesthesia with patients in a supine position","author":"Satoh","journal-title":"J Anesthesiology"},{"issue":"6","key":"R12","doi-asserted-by":"publisher","first-page":"609","DOI":"10.4097\/kjae.2008.54.6.609","article-title":"Is end-tidal carbon dioxide tension useful to predict arterial carbon dioxide tension during one lung ventilation? A comparison with during two lung ventilation","volume":"54","author":"Jin","journal-title":"Korean J Anesthesiol"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","first-page":"288","DOI":"10.4187\/respcare.10550288","article-title":"End-tidal and arterial carbon dioxide measurements correlate across all levels of physiologic dead space","volume":"55","author":"McSwain","journal-title":"Respir Care"},{"issue":"2","key":"R14","doi-asserted-by":"publisher","first-page":"58","DOI":"10.5812\/atr.6444","article-title":"Correlation of end-tidal carbon dioxide with arterial carbon dioxide in mechanically ventilated patients","volume":"1","author":"Razi","journal-title":"Arch Trauma Res"},{"issue":"3","key":"R15","doi-asserted-by":"publisher","first-page":"305","DOI":"10.5005\/jp-journals-10071-23762","article-title":"Correlation of PaCO2 and ETCO2 in COPD patients with exacerbation on mechanical ventilation","volume":"25","author":"Govindagoudar","journal-title":"Indian J Crit Care Med"},{"issue":"3","key":"R16","doi-asserted-by":"publisher","first-page":"212","DOI":"10.5152\/TurkThoracJ.2021.20032","article-title":"Limitations of end-tidal CO2 measured with a portable capnometer to estimate PaCO2 for patients with respiratory disease","volume":"22","author":"Enomoto","journal-title":"Turk Thorac J"},{"issue":"2","key":"R17","doi-asserted-by":"publisher","first-page":"170","DOI":"10.4103\/ejb.ejb_90_17","article-title":"Assessment of gradient between partial pressure of arterial carbon dioxide and end-tidal carbon dioxide in acute respiratory distress syndrome","volume":"13","author":"Abdalrazik","journal-title":"Egypt J Bronchol"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","first-page":"37","DOI":"10.4103\/abr.abr_10_20","article-title":"PaCO2\u2013EtCO2 gradient and D-dimer in the diagnosis of suspected pulmonary embolism","volume":"10","author":"Khajebashi","journal-title":"Adv Biomed Res"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1177\/1751143720970356","article-title":"The PaCO-ETCO gradient in pre-hospital intubations of all aetiologies from a single UK helicopter emergency medicine service 2015-2018","volume":"23","author":"Hibberd","journal-title":"J Intensive Care Soc"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1111\/cts.12884","article-title":"Precision medicine, AI, and the future of personalized health care","volume":"14","author":"Johnson","journal-title":"Clin Transl Sci"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01411-5","article-title":"VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients","volume":"9","author":"Lee","journal-title":"Sci Data"},{"key":"R22","unstructured":"Zheng A Casari A . Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O\u2019Reilly Media, Inc; 2018. ISBN: 9781491953235"},{"issue":"8","key":"R23","doi-asserted-by":"publisher","DOI":"10.2196\/24762","article-title":"Development and validation of an arterial pressure-based cardiac output algorithm using a convolutional neural network: retrospective study based on prospective registry data","volume":"9","author":"Yang","journal-title":"JMIR Med Inform"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-6-10","article-title":"Cross-validation pitfalls when selecting and assessing regression and classification models","volume":"6","author":"Krstajic","journal-title":"J Cheminform"},{"key":"R25","unstructured":"Prokhorenkova L Gusev G Dorogush AV Gulin A . CatBoost: unbiased boosting with categorical features. Presented at: 32nd International Conference on Neural Information Processing System; Dec 3-8, 2018:6639-6649; Montr\u00e9al, Canada."},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Akiba T Sano S Yanase T Ohta T Koyama M . Optuna: a next-generation hyperparameter optimization framework. Presented at: KDD \u201919: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining; Aug 4-8, 2019:2623-2631; Anchorage, AK. [doi: 10.1145\/3292500.3330701]","DOI":"10.1145\/3292500.3330701"},{"issue":"4","key":"R27","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.tjem.2018.09.001","article-title":"Bland-Altman analysis: a paradigm to understand correlation and agreement","volume":"18","author":"Do\u011fan","journal-title":"Turk J Emerg Med"},{"issue":"2","key":"R28","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","journal-title":"J Chiropr Med"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1109\/TBME.2020.3001441","article-title":"Arterial partial pressures of carbon dioxide estimation using non-invasive parameters in mechanically ventilated children","volume":"68","author":"Tannoury","journal-title":"IEEE Trans Biomed Eng"},{"key":"R30","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: 31st International Conference on Neural Information Processing Systems; Dec 4-9, 2017; Long Beach, CA. URL: https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/8a20a8621978632d76c43dfd28b67767-Abstract.html [Accessed 08-09-2025]"},{"issue":"3","key":"R31","doi-asserted-by":"publisher","first-page":"103","DOI":"10.4103\/arwy.arwy_21_22","article-title":"Influence of protective lung ventilation on arterial-to-end tidal carbon dioxide gradient during one lung ventilation: a prospective observational study","volume":"5","author":"Pendyala","journal-title":"Airway"},{"issue":"2","key":"R32","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1378\/chest.127.2.579","article-title":"Evaluation of capnography using a genetic algorithm to predict PaCO2","volume":"127","author":"Engoren","journal-title":"Chest"},{"issue":"3","key":"R33","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1161\/circ.128.suppl_22.a202","article-title":"Multivariate analysis of the volumetric capnograph for PaCO2 estimation","volume":"5","author":"Belenkiy","journal-title":"Int J Burns Trauma"},{"issue":"3","key":"R34","doi-asserted-by":"publisher","first-page":"583","DOI":"10.4103\/aer.AER_88_19","article-title":"Evaluation of arterial to end-tidal carbon dioxide pressure differences during laparoscopic renal surgery in the lateral decubitus position","volume":"13","author":"Mahajan","journal-title":"Anesth Essays Res"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e64855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:30:08Z","timestamp":1785537008000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e64855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":34,"URL":"https:\/\/doi.org\/10.2196\/64855","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"article-number":"v13i3e64855"}}