Noninvasive Estimation of PaCO from Volumetric Capnography in Animals with Injured Lungs: an Artificial Intelligence Approach

Overview

Journal J Clin Monit Comput

Publisher Springer

Specialties Anesthesiology
General Medicine
Medical Informatics

Date 2024 Dec 26

PMID 39725812

Authors

Gerardo Tusman

Adriana G Scandurra

Stephan H Bohm

Noelia I Echeverria

Gustavo Meschino

P Kremeier

Fernando Suarez Sipmann

Affiliations

Soon will be listed here.

Abstract

To investigate the feasibility of non-invasively estimating the arterial partial pressure of carbon dioxide (PaCO) using a computational Adaptive Neuro-Fuzzy Inference System (ANFIS) model fed by noninvasive volumetric capnography (VCap) parameters. In 14 lung-lavaged pigs, we continuously measured PaCO with an optical intravascular catheter and VCap on a breath-by-breath basis. Animals were mechanically ventilated with fixed settings and subjected to 0 to 22 cmHO of positive end-expiratory pressure steps. The resultant 8599 pairs of data points - one PaCO value matched with twelve Vcap and ventilatory parameters derived in one breath - fed the ANFIS model. The data was separated into 7370 data points for training the model (85%) and 1229 for testing (15%). The ANFIS analysis was repeated 10 independent times, randomly mixing the total data points. Bland-Altman plot (accuracy and precision), root mean square error (quality of prediction) and four-quadrant and polar plots concordance indexes (trending ability) between reference and estimated PaCO were analyzed. The Bland-Altman plot performed in 10 independent tested ANFIS models showed a mean bias between reference and estimated PaCO of 0.03 ± 0.03 mmHg, with limits of agreement of 2.25 ± 0.42 mmHg, and a root mean square error of 1.15 ± 0.06 mmHg. A good trending ability was confirmed by four quadrant and polar plots concordance indexes of 95.5% and 94.3%, respectively. In an animal lung injury model, the Adaptive Neuro-Fuzzy Inference System model fed by noninvasive volumetric capnography parameters can estimate PaCO with high accuracy, acceptable precision, and good trending ability.

References

Guggenberger H, Lenz G, Federle R . Early detection of inadvertent oesophageal intubation: pulse oximetry vs. capnography. Acta Anaesthesiol Scand. 1989; 33(2):112-5. DOI: 10.1111/j.1399-6576.1989.tb02871.x. View

Walsh B, Crotwell D, Restrepo R . Capnography/Capnometry during mechanical ventilation: 2011. Respir Care. 2011; 56(4):503-9. DOI: 10.4187/respcare.01175. View

Rackley C . Monitoring During Mechanical Ventilation. Respir Care. 2020; 65(6):832-846. DOI: 10.4187/respcare.07812. View

McSwain S, Hamel D, Smith P, Gentile M, Srinivasan S, Meliones J . End-tidal and arterial carbon dioxide measurements correlate across all levels of physiologic dead space. Respir Care. 2010; 55(3):288-93. PMC: 2837928. View

Razi E, Moosavi G, Omidi K, Khakpour Saebi A, Razi A . Correlation of end-tidal carbon dioxide with arterial carbon dioxide in mechanically ventilated patients. Arch Trauma Res. 2014; 1(2):58-62. PMC: 3876523. DOI: 10.5812/atr.6444. View

Satoh K, Kamada S, Kumagai M, Sato M, Kuji A, Joh S . Effect of lidocaine on swine lingual and pulmonary arteries. J Anesth. 2015; 29(4):529-34. DOI: 10.1007/s00540-014-1965-9. View

Tavernier B, Rey D, Thevenin D, Triboulet J, Scherpereel P . Can prolonged expiration manoeuvres improve the prediction of arterial PCO2 from end-tidal PCO2?. Br J Anaesth. 1997; 78(5):536-40. DOI: 10.1093/bja/78.5.536. View

Plewa M, Sikora S, Engoren M, Tome D, Thomas J, Deuster A . Evaluation of capnography in nonintubated emergency department patients with respiratory distress. Acad Emerg Med. 1995; 2(10):901-8. DOI: 10.1111/j.1553-2712.1995.tb03106.x. View

Bhardwaj A, Kishore S, Pandey D . Artificial Intelligence in Biological Sciences. Life (Basel). 2022; 12(9). PMC: 9505413. DOI: 10.3390/life12091430. View

10.

Miller D, Brown E . Artificial Intelligence in Medical Practice: The Question to the Answer?. Am J Med. 2017; 131(2):129-133. DOI: 10.1016/j.amjmed.2017.10.035. View

11.

Suarez-Sipmann F, Bohm S, Tusman G . Volumetric capnography: the time has come. Curr Opin Crit Care. 2014; 20(3):333-9. DOI: 10.1097/MCC.0000000000000095. View

12.

Tusman G, Suarez-Sipmann F, Bohm S, Borges J, Hedenstierna G . Capnography reflects ventilation/perfusion distribution in a model of acute lung injury. Acta Anaesthesiol Scand. 2011; 55(5):597-606. DOI: 10.1111/j.1399-6576.2011.02404.x. View

13.

Tusman G, Acosta C, Wallin M, Hallback M, Esperatti M, Peralta G . Perioperative Continuous Noninvasive Cardiac Output Monitoring in Cardiac Surgery Patients by a Novel Capnodynamic Method. J Cardiothorac Vasc Anesth. 2022; 36(8 Pt B):2900-2907. DOI: 10.1053/j.jvca.2022.02.002. View

14.

Suarez-Sipmann F, Bohm S, Tusman G, Pesch T, Thamm O, Reissmann H . Use of dynamic compliance for open lung positive end-expiratory pressure titration in an experimental study. Crit Care Med. 2006; 35(1):214-21. DOI: 10.1097/01.CCM.0000251131.40301.E2. View

15.

Tusman G, Bohm S, Suarez-Sipmann F, Scandurra A, Hedenstierna G . Lung recruitment and positive end-expiratory pressure have different effects on CO2 elimination in healthy and sick lungs. Anesth Analg. 2010; 111(4):968-77. DOI: 10.1213/ANE.0b013e3181f0c2da. View

16.

Tusman G, Scandurra A, Bohm S, Suarez-Sipmann F, Clara F . Model fitting of volumetric capnograms improves calculations of airway dead space and slope of phase III. J Clin Monit Comput. 2009; 23(4):197-206. DOI: 10.1007/s10877-009-9182-z. View

17.

Palmer T, Cumpston P, Foster W, Jones R . Continuous intravascular blood gas analysis during aortic aneurysm repair: the Paratrend 7. Anaesth Intensive Care. 1995; 23(2):200-2. DOI: 10.1177/0310057X9502300214. View

18.

Venkatesh B, Clutton-Brock T, Hendry S . Evaluation of the Paratrend 7 intravascular blood gas monitor during cardiac surgery: comparison with the C4000 in-line blood gas monitor during cardiopulmonary bypass. J Cardiothorac Vasc Anesth. 1995; 9(4):412-9. DOI: 10.1016/s1053-0770(05)80096-5. View

19.

Critchley L, Lee A, Ho A . A critical review of the ability of continuous cardiac output monitors to measure trends in cardiac output. Anesth Analg. 2010; 111(5):1180-92. DOI: 10.1213/ANE.0b013e3181f08a5b. View

20.

Critchley L, Yang X, Lee A . Assessment of trending ability of cardiac output monitors by polar plot methodology. J Cardiothorac Vasc Anesth. 2011; 25(3):536-46. DOI: 10.1053/j.jvca.2011.01.003. View