{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:12:49Z","timestamp":1780053169245,"version":"3.54.0"},"reference-count":36,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:00:00Z","timestamp":1779926400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Reports"],"abstract":"<jats:p>Background: Extubation failure (EF) is a significant complication, and it is associated with increased mortality, prolonged hospital stays and extended mechanical ventilation (MV). Determining reliable predictors of EF could improve the clinical decision-making and outcomes. Objectives: Determine the outcomes and predictors of EF in a paediatric intensive care unit (PICU) and develop predictive models using machine learning algorithms. Methods: A retrospective cohort study (n = 824) was conducted in two PICUs in participants who underwent planned extubation (January 2018\u2013December 2022). Demographic characteristics, clinical parameters, ventilator setting, laboratory findings and extubation outcomes were collected. Univariate and multivariate analysis were performed to identify significant predictors of EF. Six machine learning algorithms\u2014Logistic Regression (LR), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Support Vector Machine (SVM) and Decision Tree (DT)\u2014were developed and validated for prediction of EF. Results: The overall EF rate was 231 (28%). Multivariate analysis identified a mechanical ventilation for a duration of 3 days or more (aOR 4.49, 95% CI 3.24\u20136.57, p &lt; 0.001), use of neuromuscular blockade (aOR 1.32, 95% CI 1.07\u20131.63, p = 0.009), and administration of vasopressors (aOR 1.57, 95% CI 1.24\u20132.01, p &lt; 0.001) as significant independent predictors of EF. The ANN and LR models demonstrated the highest performance with AUCROC of 0.87 \u00b1 0.04 and 0.86 \u00b1 0.02, respectively. Conclusions: Extubation failure was common in our setting (28%) compared to other studies. Days of ventilation, undernutrition, use of neuromuscular blockade, use of vasopressors or inotropes and CNS comorbidity were associated with EF. The main cause of EF was upper airway obstruction.<\/jats:p>","DOI":"10.3390\/reports9020169","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T10:06:56Z","timestamp":1780049216000},"page":"169","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predictive Analysis of Extubation Failure in the Paediatric Intensive Care Unit in Bloemfontein, South Africa"],"prefix":"10.3390","volume":"9","author":[{"given":"Mbaya","family":"Buankuna","sequence":"first","affiliation":[{"name":"Department of Paediatrics and Child Health, School of Clinical Medicine, Faculty of Health Sciences, University of the Free State, Bloemfontein 9301, Free State, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph B.","family":"Sempa","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Clinical Medicine, Faculty of Health Sciences, University of the Free State, Bloemfontein 9301, Free State, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olive P.","family":"Khaliq","sequence":"additional","affiliation":[{"name":"Department of Paediatrics and Child Health, School of Clinical Medicine, Faculty of Health Sciences, University of the Free State, Bloemfontein 9301, Free State, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6427-0278","authenticated-orcid":false,"given":"Michael A.","family":"Pienaar","sequence":"additional","affiliation":[{"name":"Department of Paediatrics and Child Health, School of Clinical Medicine, Faculty of Health Sciences, University of the Free State, Bloemfontein 9301, Free State, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Toida, C., Muguruma, T., and Miyamoto, M. (2017). Detection and validation of predictors of successful extubation in critically ill children. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0189787"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"26","DOI":"10.7196\/SAJCC.2022.v38i1.513","article-title":"Risk factors and outcomes of extubation failure in a South African tertiary paediatric intensive care unit","volume":"38","author":"Kilba","year":"2022","journal-title":"S. Afr. J. Crit. Care"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1097\/CCM.0b013e3181ef4460","article-title":"The epidemiology of mechanical ventilation se in the United States","volume":"38","author":"Wunsch","year":"2010","journal-title":"Crit. Care Med."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Igarashi, Y., Ogawa, K., Nishimura, K., Osawa, S., Ohwada, H., and Yokobori, S. (2022). Machine learning for predicting successful extubation in patients receiving mechanical ventilation. Front. Med., 9.","DOI":"10.3389\/fmed.2022.961252"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"150960","DOI":"10.1109\/ACCESS.2019.2946980","article-title":"Prediction of Extubation Failure for Intensive Care Unit Patients Using Light Gradient Boosting Machine","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1186\/s13054-021-03864-3","article-title":"Predictors for extubation failure in COVID-19 patients using a machine learning approach","volume":"25","author":"Fleuren","year":"2021","journal-title":"Crit. Care"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tanaka, A., Kabata, D., Hirao, O., Kosaka, J., Furushima, N., Maki, Y., Uchiyama, A., Egi, M., Shintani, A., and Morimatsu, H. (2022). Prediction Model of Extubation Outcomes in Critically Ill Patients: A Multicenter Prospective Cohort Study. J. Clin. Med., 11.","DOI":"10.3390\/jcm11092520"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.bjae.2021.11.004","article-title":"Weaning from ventilation and extubation of children in critical care","volume":"22","author":"Egbuta","year":"2022","journal-title":"BJA Educ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.4187\/respcare.07810","article-title":"Ventilator liberation in the Pediatric ICU","volume":"65","author":"Newth","year":"2020","journal-title":"Respir. Care."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhao, Q.Y., Wang, H., Luo, J.C., Luo, M.H., Liu, L.P., Yu, S.J., Liu, K., Zhang, Y.J., Sun, P., and Tu, G.W. (2021). Development and Validation of a Machine-Learning Model for Prediction of Extubation Failure in Intensive Care Units. Front. Med., 8.","DOI":"10.3389\/fmed.2021.676343"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Dong, Z., Zhao, Q., Zhang, J., Han, S., Gong, J., and Wang, Y. (2021). A Prediction Model of Extubation Failure Risk in Preterm Infants. Front. Pediatr., 9.","DOI":"10.3389\/fped.2021.693320"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cuevas-Asturias, S., Alexander, E.C., Ormond, J., Aw, T.C., and Aramburo, A. (2025). Machine Learning Models for dynamic assessment of extubation readiness in Pediatric critical care. medRxiv.","DOI":"10.1101\/2025.02.06.25321800"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"S328","DOI":"10.1097\/01.ccm.0001001012.12057.45","article-title":"711: Predicting pediatric extubation failure using machine learning","volume":"52","author":"Moore","year":"2023","journal-title":"Crit. Care Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"6820975","DOI":"10.1155\/2018\/6820975","article-title":"A Decision for Predicting Successful Extubation of Patients in Intensive Care Unit","volume":"2018","author":"Tu","year":"2018","journal-title":"Biomed. Res. Int."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1017\/S1047951121004959","article-title":"Prediction of extubation failure in the paediatric cardiac ICU using machine learning and high-frequency physiologic data","volume":"32","author":"Rooney","year":"2021","journal-title":"Cardiol. Young"},{"key":"ref_16","unstructured":"Asch, M. (2022). Chapter 5: Machine Learning. A Toolbox for Digital Twins: From Model-Based to Data-Driven, Society for Industrial and Applied Mathematics. Available online: https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/1.9781611976977.fm."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and Variable Selection Via the Elastic Net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"ref_18","unstructured":"Kluyver, T., Ragan-Kelley, B., P\u00e9rez, F., Granger, B., Bussonnier, M., Frederic, J., Kelley, K., Hamrick, J., Grout, J., and Corlay, S. (2016). Jupyter Notebooks\u2014A publishing format for reproducible computational workflows. Positioning and Power in Academic Publishing: Players, Agents and Agendas, IOS Press."},{"key":"ref_19","unstructured":"Python Software Foundation (2026, May 05). Python, Available online: https:\/\/www.python.org."},{"key":"ref_20","unstructured":"(2025, December 05). Available online: https:\/\/hylkedonker.gitlab.io\/statkit."},{"key":"ref_21","unstructured":"(2011). Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res., 12, 2825\u20132830."},{"key":"ref_22","first-page":"1","article-title":"Mice: Multivariate Imputation by Chained Equations in R","volume":"45","year":"2011","journal-title":"J. Stat. Softw."},{"key":"ref_23","unstructured":"(2025, December 06). Available online: https:\/\/www.tensorflow.org\/tutorials\/structured_data\/imbalanced_data."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"86","DOI":"10.7196\/SAJCC.2021.v37i3.446","article-title":"Failed extubation in a tertiary level hospital intensive care unit, Pretoria, South Africa","volume":"37","author":"Mogase","year":"2021","journal-title":"S. Afr. J. Crit. Care"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e798\u2013805","DOI":"10.1097\/CCM.0000000000002433","article-title":"Risk factors for pediatric extubation failure: The importance of respiratory muscle strength","volume":"45","author":"Khemani","year":"2017","journal-title":"Crit. Care Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.25060\/residpediatr-2022.v12n4-591","article-title":"Fatores de risco relacionados \u00e0 falha de extuba\u00e7\u00e3o em unidade de terapia intensiva pedi\u00e1trica","volume":"12","author":"Carvalho","year":"2022","journal-title":"Resid\u00eancia Pedi\u00e1trica"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.nut.2016.05.002","article-title":"Nutritional status as a predictor of duration of mechanical ventilation in critically ill children","volume":"33","author":"Grippa","year":"2017","journal-title":"Nutrition"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2204","DOI":"10.1097\/CCM.0b013e31824e18a8","article-title":"Nutritional practices and their relationship to clinical outcomes in critically ill children-An international multicenter cohort study","volume":"40","author":"Mehta","year":"2012","journal-title":"Crit. Care Med."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Q., Hu, J., Zhou, F., Liu, C., Li, J., Fu, Y., and Dang, H. (2022). Characteristics and Risk Factors of Children Requiring Prolonged Mechanical Ventilation vs. Non-prolonged Mechanical Ventilation in the PICU: A Prospective Single-Center Study. Front. Pediatr., 10.","DOI":"10.3389\/fped.2022.830075"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1177\/08850666231204208","article-title":"Factors Associated with Post-Extubation Stridor in Infants Intubated in the Pediatric ICU","volume":"39","author":"Lewis","year":"2024","journal-title":"J. Intensive Care Med."},{"key":"ref_31","first-page":"516","article-title":"Predictors and outcomes of extubation failures in a pediatric intensive care unit: A retrospective study","volume":"19","year":"2024","journal-title":"J. Taibah Univ. Med. Sci."},{"key":"ref_32","first-page":"87","article-title":"Prevalence of extubation and associated risk factors at a tertiary care pediatric intensive care unit","volume":"117","author":"Simonassi","year":"2019","journal-title":"Arch. Argent. Pediatr."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1164\/rccm.202204-0795SO","article-title":"Executive Summary: International Clinical Practice Guidelines for Pediatric Ventilator Liberation, A Pediatric Acute Lung Injury and Sepsis Investigators (PALISI) Network Document","volume":"207","author":"Iyer","year":"2023","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Tao, Y., Ding, X., and Guo, W.L. (2024). Using machine-learning models to predict extubation failure in neonates with bronchopulmonary dysplasia. BMC Pulm. Med., 24.","DOI":"10.1186\/s12890-024-03133-3"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hsieh, M.H., Hsieh, M.J., Chen, C.M., Hsieh, C.C., Chao, C.M., and Lai, C.C. (2018). An artificial neural network model for predicting successful extubation in intensive care units. J. Clin. Med., 7.","DOI":"10.3390\/jcm7090240"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: A novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Decis. Mak."}],"container-title":["Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2571-841X\/9\/2\/169\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T10:43:52Z","timestamp":1780051432000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2571-841X\/9\/2\/169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["reports9020169"],"URL":"https:\/\/doi.org\/10.3390\/reports9020169","relation":{},"ISSN":["2571-841X"],"issn-type":[{"value":"2571-841X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,28]]}}}