{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T02:31:12Z","timestamp":1792895472210,"version":"4.5.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Ventilator-associated pneumonia significantly increases morbidity, mortality, and healthcare costs among patients with traumatic brain injury. Accurately predicting risk can facilitate earlier interventions and improve patient outcomes. This study leveraged the MIMIC III database, identifying traumatic brain injury cases through standardized clinical criteria. A rigorous data preprocessing workflow included missing value imputation, correlation checks, and expert-driven feature selection, reducing an initial set of features to a subset of critical predictors encompassing demographics, comorbidities, laboratory values, and clinical interventions. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied within a five-fold cross-validation framework, ensuring a balanced training set while maintaining an unbiased validation process. Six machine learning models, including Support Vector Machine, Logistic Regression, Random Forest, XGBoost, Artificial Neural Network, and AdaBoost, were trained using extensive hyperparameter tuning. Comprehensive evaluations were conducted based on multiple metrics, including Area Under the Curve (AUC), accuracy, F1 score, sensitivity, specificity, Positive Predictive Value, and Negative Predictive Value. XGBoost emerged as the top performing algorithm, achieving an AUC of 0.94 and an accuracy of 0.875 on the test set, marking substantial improvements over previously reported best results. An ablation study validated the necessity of each retained feature, indicating that any feature removal led to a decline in model performance. Furthermore, SHAP analysis underscored ICU length of stay, hospital length of stay, serum potassium, and blood urea nitrogen as key contributors to ventilator associated pneumonia risk. Overall, the results demonstrate that advanced ensemble learning, meticulous feature selection, and effective class imbalance handling can significantly enhance early detection in traumatic brain injury cases. These findings have meaningful clinical implications, offering a framework for more timely interventions, optimized resource allocation, and improved patient care in critical settings.<\/jats:p>","DOI":"10.1038\/s41598-025-95779-0","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:56:32Z","timestamp":1743792992000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Enhanced prediction of ventilator-associated pneumonia in patients with traumatic brain injury using advanced machine learning techniques"],"prefix":"10.1038","volume":"15","author":[{"given":"Negin","family":"Ashrafi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armin","family":"Abdollahi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamiar","family":"Alaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maryam","family":"Pishgar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,2]]},"reference":[{"key":"95779_CR1","doi-asserted-by":"crossref","unstructured":"Fatuki, T., Zvonarev, V. & Rodas, A. Prevention of traumatic brain injury in the united states: Significance, new findings, and practical applications. Cureus (2020).","DOI":"10.7759\/cureus.11225"},{"key":"95779_CR2","doi-asserted-by":"crossref","first-page":"e783","DOI":"10.1016\/j.wneu.2019.01.025","volume":"124","author":"CY Rodr\u00edguez-Trivi\u00f1o","year":"2019","unstructured":"Rodr\u00edguez-Trivi\u00f1o, C. Y., Castro, I. T. & Due\u00f1as, Z. Hypochloremia in patients with severe traumatic brain injury: A possible risk factor for increased mortality. World Neurosurg. 124, e783\u2013e788 (2019).","journal-title":"World Neurosurg."},{"key":"95779_CR3","doi-asserted-by":"crossref","first-page":"1637","DOI":"10.1016\/j.apmr.2010.05.017","volume":"91","author":"DK Menon","year":"2010","unstructured":"Menon, D. K. et al. Position statement: Definition of traumatic brain injury. Arch. Phys. Med. Rehabil. 91, 1637\u20131640 (2010).","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"95779_CR4","first-page":"61","volume":"22","author":"M Ahmadipour","year":"2023","unstructured":"Ahmadipour, M., Lashkari, M. & Ahmadinejad, M. Comparison of morbidity, mortality, and costs of vap patients with non-vap patients in the tertiary referral hospital of kerman, iran. Tanaffos 22, 61 (2023).","journal-title":"Tanaffos"},{"key":"95779_CR5","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.hrtlng.2023.08.002","volume":"62","author":"R Wang","year":"2023","unstructured":"Wang, R. et al. Machine learning algorithms for prediction of ventilator associated pneumonia in traumatic brain injury patients from the mimic-iii database. Heart Lung 62, 225\u2013232 (2023).","journal-title":"Heart Lung"},{"key":"95779_CR6","doi-asserted-by":"crossref","first-page":"2292","DOI":"10.1016\/j.chest.2020.06.064","volume":"158","author":"C Robba","year":"2020","unstructured":"Robba, C. et al. Incidence, risk factors, and effects on outcome of ventilator-associated pneumonia in patients with traumatic brain injury: analysis of a large, multicenter, prospective, observational longitudinal study. Chest 158, 2292\u20132303 (2020).","journal-title":"Chest"},{"key":"95779_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12879-020-05706-z","volume":"21","author":"W Luo","year":"2021","unstructured":"Luo, W., Xing, R. & Wang, C. The effect of ventilator-associated pneumonia on the prognosis of intensive care unit patients within 90 days and 180 days. BMC Infect. Dis. 21, 1\u20137 (2021).","journal-title":"BMC Infect. Dis."},{"key":"95779_CR8","volume":"49","author":"N Ashrafi","year":"2024","unstructured":"Ashrafi, N. et al. Deep learning model utilization for mortality prediction in mechanically ventilated icu patients. Inf. Med. Unlocked 49, 101562 (2024).","journal-title":"Inf. Med. Unlocked"},{"key":"95779_CR9","doi-asserted-by":"crossref","first-page":"1762","DOI":"10.1080\/21681163.2023.2187244","volume":"11","author":"RK Patel","year":"2023","unstructured":"Patel, R. K. & Kashyap, M. Machine learning-based lung disease diagnosis from ct images using gabor features in littlewood paley empirical wavelet transform (lpewt) and lle. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 11, 1762\u20131776 (2023).","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"95779_CR10","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1002\/ima.22865","volume":"33","author":"RK Patel","year":"2023","unstructured":"Patel, R. K. & Kashyap, M. Automated diagnosis of covid stages using texture-based gabor features in variational mode decomposition from ct images. Int. J. Imaging Syst. Technol. 33, 807\u2013821 (2023).","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"95779_CR11","doi-asserted-by":"crossref","first-page":"L1","DOI":"10.1152\/ajplung.00485.2016","volume":"313","author":"PJ Hu","year":"2017","unstructured":"Hu, P. J., Pittet, J.-F., Kerby, J. D., Bosarge, P. L. & Wagener, B. M. Acute brain trauma, lung injury, and pneumonia: More than just altered mental status and decreased airway protection. Am. J. Physiol. Lung Cell. Mol. Physiol. 313, L1\u2013L15 (2017).","journal-title":"Am. J. Physiol. Lung Cell. Mol. Physiol."},{"key":"95779_CR12","doi-asserted-by":"crossref","first-page":"1077371","DOI":"10.3389\/fmed.2023.1077371","volume":"10","author":"E Caceres","year":"2023","unstructured":"Caceres, E. et al. Risk factors and outcomes of lower respiratory tract infections after traumatic brain injury: A retrospective observational study. Front. Med. 10, 1077371 (2023).","journal-title":"Front. Med."},{"key":"95779_CR13","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1007\/s40121-023-00820-2","volume":"12","author":"A Alnimr","year":"2023","unstructured":"Alnimr, A. Antimicrobial resistance in ventilator-associated pneumonia: Predictive microbiology and evidence-based therapy. Infect. Dis. Ther. 12, 1527\u20131552 (2023).","journal-title":"Infect. Dis. Ther."},{"key":"95779_CR14","doi-asserted-by":"crossref","first-page":"2238182","DOI":"10.1080\/07853890.2023.2238182","volume":"55","author":"A Bailey","year":"2023","unstructured":"Bailey, A., Eltawil, M., Gohel, S. & Byham-Gray, L. Machine learning models using non-linear techniques improve the prediction of resting energy expenditure in individuals receiving hemodialysis. Ann. Med. 55, 2238182 (2023).","journal-title":"Ann. Med."},{"key":"95779_CR15","doi-asserted-by":"crossref","first-page":"515","DOI":"10.3390\/diagnostics10080515","volume":"10","author":"Z Qutrio Baloch","year":"2020","unstructured":"Qutrio Baloch, Z., Raza, S. A., Pathak, R., Marone, L. & Ali, A. Machine learning confirms nonlinear relationship between severity of peripheral arterial disease, functional limitation and symptom severity. Diagnostics 10, 515 (2020).","journal-title":"Diagnostics"},{"key":"95779_CR16","doi-asserted-by":"crossref","unstructured":"Mahajan, P., Uddin, S., Hajati, F. & Moni, M.\u00a0A. Ensemble learning for disease prediction: A review. In Healthcare, vol.\u00a011, 1808 (MDPI, 2023).","DOI":"10.3390\/healthcare11121808"},{"key":"95779_CR17","doi-asserted-by":"crossref","unstructured":"Simopoulos, D., Kosmidis, D., Anastassopoulos, G. & Iliadis, L. A stacked ensemble deep learning model for predicting the intensive care unit patient mortality. Artif. Intell. Health 4981 (2024).","DOI":"10.36922\/aih.4981"},{"key":"95779_CR18","doi-asserted-by":"crossref","first-page":"3852","DOI":"10.1038\/s41467-020-17431-x","volume":"11","author":"SM Lauritsen","year":"2020","unstructured":"Lauritsen, S. M. et al. Explainable artificial intelligence model to predict acute critical illness from electronic health records. Nat. Commun. 11, 3852 (2020).","journal-title":"Nat. Commun."},{"key":"95779_CR19","doi-asserted-by":"crossref","first-page":"E1027","DOI":"10.1503\/cmaj.240132","volume":"196","author":"AA Verma","year":"2024","unstructured":"Verma, A. A. et al. Clinical evaluation of a machine learning-based early warning system for patient deterioration. CMAJ 196, E1027\u2013E1037 (2024).","journal-title":"CMAJ"},{"key":"95779_CR20","unstructured":"Johnson, A., Pollard, T. & Mark, R. The mimic-iii clinical database. PhysioNet (2016). Version 1.4."},{"key":"95779_CR21","unstructured":"dhs.wisconsin. Wish injury-related traumatic brain injury icd-9-cm codes (2024)."},{"key":"95779_CR22","first-page":"69","volume":"1","author":"R Rana","year":"2015","unstructured":"Rana, R. & Singhal, R. Chi-square test and its application in hypothesis testing. J. Prim. Care Spec. 1, 69\u201371 (2015).","journal-title":"J. Prim. Care Spec."},{"key":"95779_CR23","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1128\/CMR.00051-05","volume":"19","author":"SM Koenig","year":"2006","unstructured":"Koenig, S. M. & Truwit, J. D. Ventilator-associated pneumonia: Diagnosis, treatment, and prevention. Clin. Microbiol. Rev. 19, 637\u2013657 (2006).","journal-title":"Clin. Microbiol. Rev."},{"key":"95779_CR24","doi-asserted-by":"crossref","unstructured":"Marapelli, B., Kadiyala, S. & Potluri, C. Performance analysis and classification of class imbalanced dataset using complement naive bayes approach. In 2023 Advanced Computing and Communication Technologies for High Performance Applications (ACCTHPA), 1\u20137 (2023).","DOI":"10.1109\/ACCTHPA57160.2023.10083369"},{"key":"95779_CR25","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N. V. et al. Smote: Synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002).","journal-title":"J. Artif. Intell. Res."},{"key":"95779_CR26","doi-asserted-by":"crossref","first-page":"2839","DOI":"10.1109\/JBHI.2021.3130110","volume":"26","author":"P Xuan","year":"2021","unstructured":"Xuan, P. et al. Graph triple-attention network for disease-related lncrna prediction. IEEE J. Biomed. Health Inform. 26, 2839\u20132849 (2021).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"95779_CR27","doi-asserted-by":"crossref","unstructured":"Fan, Z., Gou, J. & Weng, S. A feature importance-based multi-layer catboost for student performance prediction. In IEEE Transactions on Knowledge and Data Engineering, 1\u201313 (2024).","DOI":"10.1109\/TKDE.2024.3393472"},{"key":"95779_CR28","doi-asserted-by":"crossref","first-page":"3342","DOI":"10.1109\/JBHI.2022.3157592","volume":"26","author":"Y Chen","year":"2022","unstructured":"Chen, Y. et al. Privacy-preserving multi-class support vector machine model on medical diagnosis. IEEE J. Biomed. Health Inform. 26, 3342\u20133353 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"95779_CR29","doi-asserted-by":"crossref","unstructured":"Qin, J. & Lou, Y. L1-2 regularized logistic regression. In 2019 53rd Asilomar Conference on Signals, Systems, and Computers, 779\u2013783 (2019).","DOI":"10.1109\/IEEECONF44664.2019.9048830"},{"key":"95779_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, J. et al. Prediction of in-hospital mortality for icu patients with heart failure. medRxiv 2024\u201306 (2024).","DOI":"10.1101\/2024.06.25.24309448"},{"key":"95779_CR31","volume":"9","author":"P Probst","year":"2019","unstructured":"Probst, P., Wright, M. N. & Boulesteix, A. Hyperparameters and tuning strategies for random forest. Wiley Interdiscipl. Rev. 9, e1301 (2019).","journal-title":"Wiley Interdiscipl. Rev."},{"key":"95779_CR32","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1186\/s12911-024-02630-z","volume":"24","author":"J Gao","year":"2024","unstructured":"Gao, J. et al. Prediction of sepsis mortality in icu patients using machine learning methods. BMC Med. Inform. Decis. Mak. 24, 228 (2024).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"95779_CR33","doi-asserted-by":"crossref","unstructured":"Barkiah, I. & Sari, Y. Overcoming overfitting challenges with hog feature extraction and xgboost-based classification for concrete crack monitoring. Int. J. Electron. Telecommun. 571\u2013577 (2023).","DOI":"10.24425\/ijet.2023.146509"},{"key":"95779_CR34","doi-asserted-by":"crossref","first-page":"4258","DOI":"10.1109\/JBHI.2022.3171673","volume":"26","author":"S Liu","year":"2022","unstructured":"Liu, S., Fu, B., Wang, W., Liu, M. & Sun, X. Dynamic sepsis prediction for intensive care unit patients using xgboost-based model with novel time-dependent features. IEEE J. Biomed. Health Inform. 26, 4258\u20134269 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"95779_CR35","volume":"19","author":"H Li","year":"2024","unstructured":"Li, H. et al. A machine learning-based prediction of hospital mortality in mechanically ventilated icu patients. PLoS ONE 19, e0309383 (2024).","journal-title":"PLoS ONE"},{"key":"95779_CR36","doi-asserted-by":"crossref","unstructured":"Waoo, A.\u00a0A. & Soni, B.\u00a0K. Performance analysis of sigmoid and relu activation functions in deep neural network. In Intelligent Systems: Proceedings of SCIS 2021 (2021).","DOI":"10.1007\/978-981-16-2248-9_5"},{"key":"95779_CR37","unstructured":"Abdollahi, A., Ashrafi, N. & Pishgar, M. Advanced predictive modeling for enhanced mortality prediction in icu stroke patients using clinical data. http:\/\/arxiv.org\/abs\/2407.14211 (2024)."},{"key":"95779_CR38","first-page":"745","volume":"39","author":"C Ying","year":"2013","unstructured":"Ying, C. et al. Advance and prospects of adaboost algorithm. Acta Autom. Sin. 39, 745\u2013758 (2013).","journal-title":"Acta Autom. Sin."},{"key":"95779_CR39","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1186\/s12911-024-02629-6","volume":"24","author":"Z Yu","year":"2024","unstructured":"Yu, Z., Ashrafi, N., Li, H., Alaei, K. & Pishgar, M. Prediction of 30-day mortality for icu patients with sepsis-3. BMC Med. Inform. Decis. Mak. 24, 223 (2024).","journal-title":"BMC Med. Inform. Decis. Mak."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-95779-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-95779-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-95779-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T11:48:23Z","timestamp":1744285703000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-95779-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,2]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["95779"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-95779-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,2]]},"assertion":[{"value":"10 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"11363"}}