Sage Journals: Discover world-class research

Abstract

Traumatic brain injury (TBI) affects 69 million people worldwide each year, and acute traumatic epidural hematoma (atEDH) is a frequent and severe consequence of TBI. The aim of the study is to use machine learning (ML) algorithms to predict in-hospital death, non-home discharges, prolonged length of stay (LOS), prolonged length of intensive care unit stay (ICU-LOS), and major complications in patients with atEDH and incorporate the resulting ML models into a user-friendly web application for use in the clinical settings. The American College of Surgeons (ACS) Trauma Quality Program (TQP) database was used to identify patients with atEDH. Four ML algorithms (XGBoost, LightGBM, CatBoost, and Random Forest) were utilized, and the best performing models were incorporated into an open-access web application to predict the outcomes of interest. The study found that the ML algorithms had high area under the receiver operating characteristic curve (AUROC) values in predicting outcomes for patients with atEDH. In particular, the algorithms had an AUROC value range of between 0.874 to 0.956 for in-hospital mortality, 0.776 to 0.798 for non-home discharges, 0.737 to 0.758 for prolonged LOS, 0.712 to 0.774 for prolonged ICU-LOS, and 0.674 to 0.733 for major complications. The following link will take users to the open-access web application designed to generate predictions for individual patients based on their characteristics: huggingface.co/spaces/MSHS-Neurosurgery-Research/TQP-atEDH. This study aimed to improve the prognostication of patients with atEDH using ML algorithms and developed a web application for easy integration in clinical practice. It found that ML algorithms can aid in risk stratification and have significant potential for predicting in-hospital outcomes. Results demonstrated excellent performance for predicting in-hospital death and fair performance for non-home discharges, prolonged LOS and ICU-LOS, and poor performance for major complications.

Get full access to this article

View all access options for this article.

References

Dewan

, Rattani

, Gupta

, et al. Estimating the global incidence of traumatic brain injury. J Neurosurg, 2019; 130(4):1080–1097; doi:10.3171/2017.10.JNS17352

Soon

, Marcus

, Wilson

. Traumatic acute extradural haematoma – Indications for surgery revisited. Br J Neurosurg, 2016; 30(2):233–234; doi:10.3109/02688697.2015.1119237

Maas

AIR

, Steyerberg

, Butcher

, et al. prognostic value of computerized tomography scan characteristics in traumatic brain injury: results from the IMPACT Study. J Neurotrauma, 2007; 24(2):303–314; doi:10.1089/neu.2006.0033

Teasdale

, Jennett

. Assessment of coma and impaired consciousness. The Lancet, 1974; 304(7872):81–84; doi:10.1016/S0140-6736(74)91639-0

Final results of MRC

CRASH

, a randomised placebo-controlled trial of intravenous corticosteroid in adults with head injury—outcomes at 6 months. The Lancet, 2005; 365(9475):1957–1959; doi:10.1016/S0140-6736(05)66552-X

Steyerberg

, Mushkudiani

, Perel

, et al. Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics. Singer M, ed. PLoS Med, 2008; 5(8):e165; doi:10.1371/journal.pmed.0050165

Eftekhar

, Mohammad

, Ardebili

, et al. Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data. BMC Med Inform Decis Mak, 2005; 5(1):3; doi:10.1186/1472-6947-5-3

Hale

, Stonko

, Brown

, et al. Machine-learning analysis outperforms conventional statistical models and CT classification systems in predicting 6-month outcomes in pediatric patients sustaining traumatic brain injury. Neurosurg Focus, 2018; 45(5):E2; doi:10.3171/2018.8.FOCUS17773

Rau

, Kuo

, Chien

, et al. Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models. Kou YR, ed. PLoS One. 2018; 13(11):e0207192. doi:10.1371/journal.pone.0207192

10.

Raj

, Luostarinen

, Pursiainen

, et al. Machine learning-based dynamic mortality prediction after traumatic brain injury. Sci Rep, 2019; 9(1):17672; doi:10.1038/s41598-019-53889-6

11.

Abujaber

, Fadlalla

, Gammoh

, et al. Prediction of in-hospital mortality in patients on mechanical ventilation post traumatic brain injury: machine learning approach. BMC Med Inform Decis Mak, 2020; 20(1):336; doi:10.1186/s12911-020-01363-z

12.

Matsuo

, Aihara

, Nakai

, et al. Machine learning to predict in-hospital morbidity and mortality after traumatic brain injury. J Neurotrauma, 2020; 37(1):202–210. doi:10.1089/neu.2018.6276

13.

About

NTDB.

ACS. Available from: https://www.facs.org/quality-programs/trauma/quality/national-trauma-data-bank/about-ntdb/ [Last accessed September 29, 2022 ]

14.

Shafi

, Nathens

, Cryer

, et al. The Trauma Quality Improvement Program of the American College of Surgeons Committee on Trauma. J Am Coll Surg, 2009; 209(4):521–530e1; doi:10.1016/j.jamcollsurg.2009.07.001

15.

Hemmila

, Nathens

, Shafi

, et al. The Trauma Quality Improvement Program: pilot study and initial demonstration of feasibility. J Trauma Inj Infect Crit Care, 2010; 68(2):253–262; doi:10.1097/TA.0b013e3181cfc8e6

16.

Trauma Quality Programs Participant Use File. ACS. Available from: https://www.facs.org/quality-programs/trauma/quality/national-trauma-data-bank/datasets/ [Last accessed September 29, 2022 ]

17.

Collins

, Reitsma

, Altman

, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement. BMC Med, 2015; 13(1):1; doi:10.1186/s12916-014-0241-z

18.

Journal of Medical Internet Research - Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View. Available from: https://www.jmir.org/2016/12/e323/ [Last accessed September 29, 2022 ]

19.

Lilley

, Scott

, Weissman

, et al. End-of-life care in older patients after serious or severe traumatic brain injury in low-mortality hospitals compared with all other hospitals. JAMA Surg, 2018; 153(1):44–50; doi:10.1001/jamasurg.2017.3148

20.

sklearn.impute.KNNImputer. scikit-learn. Available from: https://scikit-learn/stable/modules/generated/sklearn.impute.KNNImputer.html [Last accessed September 29, 2022 ]

21.

sklearn.preprocessing.MinMaxScaler. scikit-learn. Available from: https://scikit-learn/stable/modules/generated/sklearn.preprocessing.MinMaxScaler.html [Last accessed September 29, 2022 ]

22.

Chawla

, Bowyer

, Hall

, et al. SMOTE: Synthetic Minority Over-sampling Technique. J Artif Intell Res, 2002; 16:321–357; doi:10.1613/jair.953

23.

, Ma

, eds. Imbalanced Learning: Foundations, Algorithms, and Applications. John Wiley & Sons, Inc: Hoboken, New Jersey; 2013.

24.

Akiba

, Sano

, Yanase

, et al. Optuna: A next-generation hyperparameter optimization framework. Published online July 25,, 2019; doi:10.4855/0/arXiv.1907.10902

25.

Platt

Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif. 1999; 10(3):61–74.

26.

Niculescu-Mizil

, Caruana

Predicting good probabilities with supervised learning. In: Proceedings of the 22nd International Conference on Machine Learning - ICML ’05. ACM Press: New York, New York; 2005:625–632; doi:10.1145/1102351.1102430

27.

Prediction Tools | Memorial Sloan Kettering Cancer Center. Available at: https://www.mskcc.org/nomograms. [Last accessed January 2, 2023 .]

28.

Senders

, Staples

, Karhade

, et al. Machine learning and neurosurgical outcome prediction: a systematic review. World Neurosurg, 2018; 109:476–486.e1; doi:10.1016/j.wneu.2017.09.149

29.

Camarano

, Ratliff

, Korst

, et al. Predicting in-hospital mortality after traumatic brain injury: External validation of CRASH-basic and IMPACT-core in the national trauma data bank. Injury, 2021; 52(2):147–153; doi:10.1016/j.injury.2020.10.051

30.

Hanley

, McNeil

. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 1982; 143(1):29–36; doi:10.1148/radiology.143.1.7063747

31.

Feng

, Zhou

, Tong

. Imbalanced classification: A paradigm-based review. Stat Anal Data Min ASA Data Sci J, 2021; 14(5):383–406; doi:10.1002/sam.11538

32.

Galar

, Fernandez

, Barrenechea

, et al. A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern Part C Appl Rev, 2012; 42(4):463–484; doi:10.1109/TSMCC.2011.2161285

33.

Mullick

, Datta

, Dhekane

, et al. Appropriateness of performance indices for imbalanced data classification: an analysis. Published online, 2020; doi:10.4855/0/ARXIV.2008.11752

34.

Saito

, Rehmsmeier

. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. Brock G, ed. PLoS One. 2015; 10(3):e0118432; doi:10.1371/journal.pone.0118432

35.

Hashmi

, Kaji

, Nathens

. Practical guide to surgical data sets: National Trauma Data Bank (NTDB). JAMA Surg, 2018; 153(9):852; doi:10.1001/jamasurg.2018.0483

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.03 MB

0.17 MB

3.34 MB

Prognosis at Your Fingertips: A Machine Learning-Based Web Application for Outcome Prediction in Acute Traumatic Epidural Hematoma

Abstract

Get full access to this article

References

Supplementary Material