Machine Learning Models for Predicting Abnormal Brain CT Scan Findings in Mild Traumatic Brain Injury Patients
Archives of Academic Emergency Medicine,
Vol. 13 No. 1 (2025),
6 Shahrivar 2025
,
Page e60
https://doi.org/10.22037/aaemj.v13i1.2709
Abstract
Introduction: Traumatic Brain Injury (TBI) is one of the leading causes of mortality and severe disability worldwide. This study aimed to develop and optimize machine learning (ML) algorithms to predict abnormal brain computed tomography (CT) scans in patients with mild TBI.
Methods: In this retrospective analyses, the outcome was dichotomized into normal or abnormal CT scans, and univariate analyses were employed for feature selection. Then SMOTE was applied to address class imbalance. The dataset was split 80:20 for training/testing, and multiple ML algorithms were evaluated using accuracy, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). SHAP analysis was used to interpret feature contributions.
Results: The data included 424 patients with an average age of 40.3 ± 19.1 years (76.65% male). Abnormal brain CT scan findings were more common in older males, patients with lower Glasgow Coma Scale (GCS) scores, suspected fractures, hematomas, and visible injuries above the clavicle. Among the ML models, XGBoost performed best (AUC 0.9611, accuracy 0.8937), followed by Random Forest, while Naive Bayes showed high recall but poor specificity. SHAP analysis highlighted that lower GCS scores, decreased SpO2 levels, and tachypnea were strong predictors of abnormal brain CT findings.
Conclusion: XGBoost and Random Forest achieved high predictive accuracy, sensitivity, and specificity. GCS, SpO2, and respiratory rate were key predictors. These models may reduce unnecessary CT scans and optimize resource use. Further multicenter validation is needed to confirm their clinical utility.
- Machine learning
- Brain injuries
- Glasgow coma scale
How to Cite
References
Maas AI, Menon DK, Adelson PD, Andelic N, Bell MJ, Belli A, et al. Traumatic brain injury: integrated approaches to improve prevention, clinical care, and research. The Lancet Neurology. 2017;16(12):987-1048.
Guan B, Anderson DB, Chen L, Feng S, Zhou H. Global, regional and national burden of traumatic brain injury and spinal cord injury, 1990–2019: a systematic analysis for the Global Burden of Disease Study 2019. BMJ open. 2023;13(10):e075049.
Maas AI, Menon DK, Manley GT, Abrams M, Åkerlund C, Andelic N, et al. Traumatic brain injury: progress and challenges in prevention, clinical care, and research. The Lancet Neurology. 2022;21(11):1004-60.
Holm L, Cassidy JD, Carroll LJ, Borg J. Summary of the WHO collaborating centre for neurotrauma task force on mild traumatic brain injury. Journal of rehabilitation medicine. 2005;37(3):137-41.
Vos PE, Alekseenko Y, Battistin L, Ehler E, Gerstenbrand F, Muresanu DF, et al. Mild traumatic brain injury. European journal of neurology. 2012;19(2):191-8.
Obiano KS, Singh R, Dawson J. Post-concussion symptoms 1-year after traumatic brain injury: using the Rivermead Post-concussion Questionnaire to identify predictors of severity. Brain injury. 2022;36(12-14):1323-30.
Schneider AL, Huie JR, Boscardin WJ, Nelson L, Barber JK, Yaffe K, et al. Cognitive outcome 1 year after mild traumatic brain injury: results from the TRACK-TBI study. Neurology. 2022;98(12):e1248-e61.
Theadom A, Parag V, Dowell T, McPherson K, Starkey N, Barker-Collo S, et al. Persistent problems 1 year after mild traumatic brain injury: a longitudinal population study in New Zealand. British Journal of General Practice. 2016;66(642):e16-e23.
Zadegan SA, Rahimi-Movaghar V. Indications for Brain Computed Tomography Scan After Mild Traumatic Brain Injury. Traumatic Brain Injury: IntechOpen; 2014.
Smits M, Dippel DW, de Haan GG, Dekker HM, Vos PE, Kool DR, et al. External validation of the Canadian CT Head Rule and the New Orleans Criteria for CT scanning in patients with minor head injury. Jama. 2005;294(12):1519-25.
Jones LA, Morley EJ, Grant WD, Wojcik SM, Paolo WF. Adherence to head computed tomography guidelines for mild traumatic brain injury. Western Journal of Emergency Medicine. 2014;15(4):459.
Stiell IG, Wells GA, Vandemheen K, Clement C, Lesiuk H, Laupacis A, et al. The Canadian CT Head Rule for patients with minor head injury. The Lancet. 2001;357(9266):1391-6.
Haydel MJ, Preston CA, Mills TJ, Luber S, Blaudeau E, DeBlieux PM. Indications for computed tomography in patients with minor head injury. New England Journal of Medicine. 2000;343(2):100-5.
guideline NG232 N. Head Injury: assessment and early management. 2023.
Mower WR, Hoffman JR, Herbert M, Wolfson AB, Pollack Jr CV, Zucker MI, et al. Developing a decision instrument to guide computed tomographic imaging of blunt head injury patients. Journal of Trauma and Acute Care Surgery. 2005;59(4):954-9.
Servadei F, Teasdale G, Merry G. Defining acute mild head injury in adults: a proposal based on prognostic factors, diagnosis, and management. Journal of neurotrauma. 2001;18(7):657-64.
Sakkas A, Weiß C, Wilde F, Ebeling M, Scheurer M, Thiele OC, et al. Justification of Indication for Cranial CT Imaging after Mild Traumatic Brain Injury According to the Current National Guidelines. Diagnostics. 2023;13(11):1826.
Żyluk A. Indications for CT scanning in minor head injuries: A review. Neurologia i neurochirurgia polska. 2015;49(1):52-7.
Courville E, Kazim SF, Vellek J, Tarawneh O, Stack J, Roster K, et al. Machine learning algorithms for predicting outcomes of traumatic brain injury: A systematic review and meta-analysis. Surgical neurology international. 2023;14.
Terabe ML, Massago M, Iora PH, Hernandes Rocha TA, de Souza JVP, Huo L, et al. Applicability of machine learning technique in the screening of patients with mild traumatic brain injury. Plos one. 2023;18(8):e0290721.
Klement W, Wilk S, Michalowski W, Farion KJ, Osmond MH, Verter V. Predicting the need for CT imaging in children with minor head injury using an ensemble of Naive Bayes classifiers. Artificial intelligence in medicine. 2012;54(3):163-70.
Miyagawa T, Saga M, Sasaki M, Shimizu M, Yamaura A. Statistical and machine learning approaches to predict the necessity for computed tomography in children with mild traumatic brain injury. Plos one. 2023;18(1):e0278562.
Molaei S, Korley FK, Soroushmehr SR, Falk H, Sair H, Ward K, et al., editors. A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2016: IEEE.
Pan Y, Wei M, Jin M, Liang Y, Yi T, Tu J, et al. An interpretable machine learning model based on optimal feature selection for identifying CT abnormalities in patients with mild traumatic brain injury. eClinicalMedicine. 2025;82.
Forouzannia SM, Najafimehr H, Oskooi RK, Faridaalaee G, Dizaji SR, Toloui A, et al. Clinical decision rules in predicting computed tomography scan findings and need for neurosurgical intervention in mild traumatic brain injury: a prospective observational study. European Journal of Trauma and Emergency Surgery. 2024;50(4):1199-207.
Jain S, Iverson LM. Glasgow Coma Scale. StatPearls. Treasure Island (FL): StatPearls Publishing
Copyright © 2025, StatPearls Publishing LLC.; 2025.
Marcílio WE, Eler DM, editors. From explanations to feature selection: assessing SHAP values as feature selection mechanism. 2020 33rd SIBGRAPI conference on Graphics, Patterns and Images (SIBGRAPI); 2020: Ieee.
Lee HS, Kim JH, Son J, Park H, Choi J. Machine learning models for predicting early hemorrhage progression in traumatic brain injury. Scientific reports. 2024;14(1):11690.
Cao Y, Forssten MP, Sarani B, Montgomery S, Mohseni S. Development and Validation of an XGBoost-Algorithm-Powered Survival Model for Predicting In-Hospital Mortality Based on 545,388 Isolated Severe Traumatic Brain Injury Patients from the TQIP Database. Journal of Personalized Medicine [Internet]. 2023; 13(9).
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research. 2002;16:321-57.
Fernández A, Garcia S, Herrera F, Chawla NV. SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. Journal of artificial intelligence research. 2018;61:863-905.
Blagus R, Lusa L. SMOTE for high-dimensional class-imbalanced data. BMC bioinformatics. 2013;14:1-16.
Pradipta GA, Wardoyo R, Musdholifah A, Sanjaya INH, Ismail M, editors. SMOTE for handling imbalanced data problem: A review. 2021 sixth international conference on informatics and computing (ICIC); 2021: IEEE.
- Abstract Viewed: 436 times
- pdf Downloaded: 836 times
Download Statastics
Make a Submission
SJR
COPE
