Treffer: Validation of a novel Bayesian predictive algorithm for detection of carbon dioxide retention using retrospective neonatal ICU data.

Title:
Validation of a novel Bayesian predictive algorithm for detection of carbon dioxide retention using retrospective neonatal ICU data.
Authors:
Viehl LT; Division of Newborn Medicine, Department of Pediatrics, Washington University, St. Louis, MO, USA., Segar JL; Division of Neonatology, Department of Pediatrics, Medical College of Wisconsin, Milwaukee, WI, USA., Vesoulis ZA; Division of Newborn Medicine, Department of Pediatrics, Washington University, St. Louis, MO, USA. vesoulis_z@wustl.edu.
Source:
Journal of perinatology : official journal of the California Perinatal Association [J Perinatol] 2026 Jan; Vol. 46 (1), pp. 31-37. Date of Electronic Publication: 2025 Jul 23.
Publication Type:
Journal Article; Validation Study
Language:
English
Journal Info:
Publisher: Nature Publishing Group Country of Publication: United States NLM ID: 8501884 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1476-5543 (Electronic) Linking ISSN: 07438346 NLM ISO Abbreviation: J Perinatol Subsets: MEDLINE
Imprint Name(s):
Publication: 2001- : New York, NY : Nature Publishing Group
Original Publication: [Philadelphia, Pa. : W.B. Saunders, c1984-
References:
Al-Momani MM. Admission patterns and risk factors linked with neonatal mortality: a hospital-based retrospective study. Pak J Med Sci. 2020;36:1371–6. (PMID: 32968411750103210.12669/pjms.36.6.2281)
Keszler M, Suresh GK (editors). Goldsmith’s assisted ventilation of the neonate: an evidence-based approach to newborn respiratory care. 7th ed. Philadelphia, PA: Elsevier; 2022.
Chakkarapani AA, Adappa R, Mohammad Ali SK, Gupta S, Soni NB, Chicoine L, et al. Current concepts of mechanical ventilation in neonates’ - Part 1: Basics. Int J Pediatr Adolesc Med. 2020;7:13–8. (PMID: 32373697719306810.1016/j.ijpam.2020.03.003)
Mathai SS, Raju U, Kanitkar M. Management of respiratory distress in the newborn. Med J Armed Forces India. 2007;63:269–72. (PMID: 27408014492275510.1016/S0377-1237(07)80152-3)
Stenson BJ, Glover RM, Parry GJ, Wilkie RA, Laing IA, Tarnow-Mordi WO. Static respiratory compliance in the newborn. III: early changes after exogenous surfactant treatment. Arch Dis Child Fetal Neonatal Ed. 1994;70:F19–24. (PMID: 8117122106098210.1136/fn.70.1.F19)
Hentschel R, Bohlin K, Van Kaam A, Fuchs H, Danhaive O. Surfactant replacement therapy: from biological basis to current clinical practice. Pediatr Res. 2020;88:176–83. (PMID: 31926483722323610.1038/s41390-020-0750-8)
Boly TJ, Lozano-Chinga MM, Reyes-Hernandez MA, Elgin TG, Ballas Z, Bermick JR. Reducing capillary leak syndrome mortality in extremely premature infants: a pilot investigation. Clin Pediatr. 2024;64:425–33. (PMID: 10.1177/00099228241272037)
Attar MA, Donn SM. Mechanisms of ventilator-induced lung injury in premature infants. Semin Neonatol. 2002;7:353–60. (PMID: 1246449710.1053/siny.2002.0129)
Jobe AH. An unknown: lung growth and development after very preterm birth. Am J Respir Crit Care Med. 2002;166:1529–30. (PMID: 1247106510.1164/rccm.2209012)
SUPPORT Study Group of the Eunice Kennedy Shriver NICHD Neonatal Research Network, Carlo WA, Finer NN, Walsh MC, Rich W, Gantz MG, Laptook AR, et al. Target ranges of oxygen saturation in extremely preterm infants. N Engl J Med. 2010;362:1959–69. (PMID: 10.1056/NEJMoa0911781)
BOOST II United Kingdom Collaborative Group, BOOST II Australia Collaborative Group, BOOST II New Zealand Collaborative Group, Stenson BJ, Tarnow-Mordi WO, Darlow BA, Simes J, Juszczak E, Askie L, et al. Oxygen saturation and outcomes in preterm infants. N Engl J Med. 2013;368:2094–104. (PMID: 10.1056/NEJMoa1302298)
Shiao S-YPK, Ou C-N. Validation of oxygen saturation monitoring in neonates. Am J Crit Care. 2007;16:168–78. (PMID: 17322018193148410.4037/ajcc2007.16.2.168)
Hay WW. History of pulse oximetry in neonatal medicine. Neoreviews. 2005;6:e533–e538. (PMID: 10.1542/neo.6-12-e533)
Sankaran D, Zeinali L, Iqbal S, Chandrasekharan P, Lakshminrusimha S. Non-invasive carbon dioxide monitoring in neonates: methods, benefits, and pitfalls. J Perinatol. 2021;41:2580–9. (PMID: 34148068821437410.1038/s41372-021-01134-2)
Chandrakantan A, Jasiewicz R, Reinsel RA, Khmara K, Mintzer J, DeCristofaro JD, et al. Transcutaneous CO2 versus end-tidal CO2 in neonates and infants undergoing surgery: a prospective study. Med Devices. 2019;12:165–72. (PMID: 10.2147/MDER.S198707)
Chatterjee M, Ge X, Kostov Y, Tolosa L, Rao G. A novel approach toward noninvasive monitoring of transcutaneous CO2. Med Eng Phys. 2014;36:136–9. (PMID: 2393198810.1016/j.medengphy.2013.07.001)
Borenstein-Levin L, Avishay N, Soffer O, Arnon S, Riskin A, Dinur G, et al. Transcutaneous CO2 monitoring in extremely low birth weight premature infants. J Clin Med. 2023;12:5757. (PMID: 376858231048837110.3390/jcm12175757)
Berardesca E, Maibach H. Transcutaneous CO2 and O2 diffusion. Ski Pharmacol Physiol. 1993;6:3–9. (PMID: 10.1159/000211078)
Thome UH, Carlo WA. Permissive hypercapnia. Semin Neonatol. 2002;7:409–19. (PMID: 1246450310.1053/siny.2002.0135)
Wong SK, Chim M, Allen J, Butler A, Tyrrell J, Hurley T, et al. Carbon dioxide levels in neonates: what are safe parameters? Pediatr Res. 2022;91:1049–56. (PMID: 3423062110.1038/s41390-021-01473-y)
Kaiser JR, Gauss CH, Pont MM, Williams DK. Hypercapnia during the first 3 days of life is associated with severe intraventricular hemorrhage in very low birth weight infants. J Perinatol. 2006;26:279–85. (PMID: 1655484710.1038/sj.jp.7211492)
Fabres J, Carlo WA, Phillips V, Howard G, Ambalavanan N. Both extremes of arterial carbon dioxide pressure and the magnitude of fluctuations in arterial carbon dioxide pressure are associated with severe intraventricular hemorrhage in preterm infants. Pediatrics. 2007;119:299–305. (PMID: 1727261910.1542/peds.2006-2434)
Brown MK, Poeltler DM, Hassen KO, Lazarus DV, Brown VK, Stout JJ, et al. Incidence of hypocapnia, hypercapnia, and acidosis and the associated risk of adverse events in preterm neonates. Respir Care. 2018;63:943–9. (PMID: 2961548310.4187/respcare.05801)
Weeke LC, Dix LML, Groenendaal F, Lemmers PMA, Dijkman KP, Andriessen P, et al. Severe hypercapnia causes reversible depression of aEEG background activity in neonates: an observational study. Arch Dis Child Fetal Neonatal Ed. 2017;102:F383–F388. (PMID: 2813024610.1136/archdischild-2016-311770)
Abbas PI, Cass DL, Olutoye OO, Zamora IJ, Akinkuotu AC, Sheikh F, et al. Persistent hypercarbia after resuscitation is associated with increased mortality in congenital diaphragmatic hernia patients. J Pediatr Surg. 2015;50:739–43. (PMID: 2578337610.1016/j.jpedsurg.2015.02.028)
Vesoulis ZA, Husain AN, Cole FS. Improving child health through Big Data and data science. Pediatr Res. 2023;93:342–9. (PMID: 3597416210.1038/s41390-022-02264-9)
McGregor C. Big data in neonatal intensive care. Computer. 2013;46:54–59. (PMID: 10.1109/MC.2013.157)
Rhine WD. Technology – Considerations for the NICU of the future. Newborn Infant Nurs Rev. 2016;16:208–12. (PMID: 10.1053/j.nainr.2016.09.005)
Kuzniewicz MW, Puopolo KM, Fischer A, Walsh EM, Li S, Newman TB, et al. A quantitative, risk-based approach to the management of neonatal early-onset sepsis. JAMA Pediatr. 2017;171:365. (PMID: 2824125310.1001/jamapediatrics.2016.4678)
Greenberg RG, McDonald SA, Laughon MM, Tanaka D, Jensen E, Van Meurs K, et al. Online clinical tool to estimate risk of bronchopulmonary dysplasia in extremely preterm infants. Arch Dis Child Fetal Neonatal Ed. 2022;107:638–43. (PMID: 10.1136/archdischild-2021-323573)
Griffin MP, Lake DE, Bissonette EA, Harrell FE, O’Shea TM, Moorman JR. Heart rate characteristics: novel physiomarkers to predict neonatal infection and death. Pediatrics. 2005;116:1070–4. (PMID: 1626399110.1542/peds.2004-2461)
Griffin MP, Moorman JR. Toward the early diagnosis of neonatal sepsis and sepsis-like illness using novel heart rate analysis. Pediatrics. 2001;107:97–104. (PMID: 1113444110.1542/peds.107.1.97)
Mathieson SR, Stevenson NJ, Low E, Marnane WP, Rennie JM, Temko A, et al. Validation of an automated seizure detection algorithm for term neonates. Clin Neurophysiol. 2016;127:156–68. (PMID: 26055336472750410.1016/j.clinph.2015.04.075)
Navakatikyan MA, Colditz PB, Burke CJ, Inder TE, Richmond J, Williams CE. Seizure detection algorithm for neonates based on wave-sequence analysis. Clin Neurophysiol. 2006;117:1190–203. (PMID: 1662169010.1016/j.clinph.2006.02.016)
Wynn JL, Polin RA. A neonatal sequential organ failure assessment score predicts mortality to late-onset sepsis in preterm very low birth weight infants. Pediatr Res. 2020;88:85–90. (PMID: 3139456610.1038/s41390-019-0517-2)
Mikhno A, Ennett CM. Prediction of extubation failure for neonates with respiratory distress syndrome using the MIMIC-II clinical database. Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:5094–7. (PMID: 23367074)
Natarajan A, Lam G, Liu J, Beam AL, Beam KS, Levin JC. Prediction of extubation failure among low birthweight neonates using machine learning. J Perinatol. 2023;43:209–14. (PMID: 366111071034882210.1038/s41372-022-01591-3)
Brown JM, Campbell JP, Beers A, Chang K, Ostmo S, Chan RVP, et al. Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA Ophthalmol. 2018;136:803–10. (PMID: 29801159613604510.1001/jamaophthalmol.2018.1934)
Kim SH, Oh YJ, Son J, Jung D, Kim D, Ryu SR, et al. Machine learning-based analysis for prediction of surgical necrotizing enterocolitis in very low birth weight infants using perinatal factors: a nationwide cohort study. Eur J Pediatr. 2024;183:2743–51. (PMID: 385541731109886910.1007/s00431-024-05505-7)
Zubrow AB, Hulman S, Kushner H, Falkner B. Determinants of blood pressure in infants admitted to neonatal intensive care units: a prospective multicenter study. Philadelphia Neonatal Blood Pressure Study Group. J Perinatol. 1995;15:470–9. (PMID: 8648456)
Miall-Allen VM, de Vries LS, Whitelaw AG. Mean arterial blood pressure and neonatal cerebral lesions. Arch Dis Child. 1987;62:1068–9. (PMID: 3314723177867910.1136/adc.62.10.1068)
Peeples ES, Comstock BA, Heagerty PJ, Juul SE. Preterm Erythropoietin Neuroprotection (PENUT) Trial Investigators. Blood pressure values and hypotension management in extremely preterm infants: a multi-center study. J Perinatol. 2022;42:1169–75. (PMID: 3571560010.1038/s41372-022-01425-2)
Noori S, Seri I. Neonatal blood pressure support: the use of inotropes, lusitropes, and other vasopressor agents. Clin Perinatol. 2012;39:221–38. (PMID: 2234154810.1016/j.clp.2011.12.010)
Alderliesten T, Lemmers PMA, van Haastert IC, de Vries LS, Bonestroo HJC, Baerts W, et al. Hypotension in preterm neonates: low blood pressure alone does not affect neurodevelopmental outcome. J Pediatr. 2014. https://doi.org/10.1016/j.jpeds.2013.12.042 .
Lipton ZC. The Mythos of model interpretability. 2016. https://doi.org/10.48550/ARXIV.1606.03490 .
Doshi-Velez F, Kim B. Towards a rigorous science of interpretable machine learning. [Preprint]. 2017. Available from: https://doi.org/10.48550/ARXIV.1702.08608 .
Pappas A, Shankaran S, Laptook AR, Langer JC, Bara R, Ehrenkranz RA, et al. Hypocarbia and adverse outcome in neonatal hypoxic-ischemic encephalopathy. J Pediatr. 2011;158:752–758.e1. (PMID: 2114618410.1016/j.jpeds.2010.10.019)
Substance Nomenclature:
142M471B3J (Carbon Dioxide)
Entry Date(s):
Date Created: 20250723 Date Completed: 20260119 Latest Revision: 20260119
Update Code:
20260120
DOI:
10.1038/s41372-025-02369-z
PMID:
40702156
Database:
MEDLINE

Weitere Informationen

Objective: To validate a novel Bayesian prediction algorithm (IVCO2 index) to calculate the probability of CO <subscript>2</subscript> retention in neonates using existing medical device outputs.
Study Design: A retrospective validation study from two level IV NICUs between September 2021 and May 2023. The algorithm calculated probabilities of PaCO <subscript>2</subscript> exceeding 50 mmHg (IVCO2_50) and 60 mmHg (IVCO2_60) using multimodal physiologic data. Performance was assessed through ROC analysis, range utilization, and resolution/limitation analysis.
Results: Among 180 included neonates, 1092 arterial blood gas measurements were analyzed. IVCO2_50 and IVCO2_60 demonstrated excellent discriminatory performance (AUC 0.87, 95% CI 0.85-0.89 and AUC 0.90, 95% CI 0.68-0.93, respectively). The risk of elevated PaCO <subscript>2</subscript> scaled linearly with increasing index quartiles. Minimum scores (<1) showed >6-fold reduction in hypercapnia risk, while maximum scores (>99) demonstrated >3-fold reduction in normocapnia risk.
Conclusion: The IVCO2 index accurately predicts CO <subscript>2</subscript> retention in neonates, offering potential for early detection of ventilation inadequacy without additional invasive monitoring.
(© 2025. The Author(s), under exclusive licence to Springer Nature America, Inc.)

Competing interests: The authors declare no competing interests. Ethics approval and consent to participate: IRB approval was obtained at each institution under a waiver of informed consent (consistent with 45 CFR46.101(b)(4): Existing Data & Specimens - No Identifiers). The study was performed in accordance with the Declaration of Helsinki.