Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 28;13(1):e60.
doi: 10.22037/aaemj.v13i1.2709. eCollection 2025.

Machine Learning Models for Predicting Abnormal Brain CT Scan Findings in Mild Traumatic Brain Injury Patients

Amirmohammad Toloui  1 , Amir Ghaffari Jolfayi  2 , Hamed Zarei  1 , Arash Ansarian  1 , Amir Azimi  1   2 , Seyed Mohammad Forouzannia  1 , Rosita Khatamian Oskooi  3 , Gholamreza Faridaalaee  4 , Shayan Roshdi Dizaji  1 , Seyed Ali Forouzannia  1 , Seyedeh Niloufar Rafiei Alavi  1 , Mohammadreza Alizadeh  1 , Hadis Najafimehr  5 , Saeed Safari  6   7 , Alireza Baratloo  8 , Mostafa Hosseini  5 , Mahmoud Yousefifard  1
Affiliations

Machine Learning Models for Predicting Abnormal Brain CT Scan Findings in Mild Traumatic Brain Injury Patients

Amirmohammad Toloui et al. Arch Acad Emerg Med. .

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.

Keywords: Brain injuries; Glasgow coma scale; Machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflict of interest.

Figures

Flow chart 1
Flow chart 1
Flowchart of the machine learning pipeline for predicting abnormal brain computed tomography (CT) findings in mild traumatic brain injury (mTBI) patients.
Figure 1
Figure 1
Correlation of clinical and demographic variables.
Figure 2
Figure 2
Area Under the Curve (AUC) for the Performance of Various Machine Learning Models.
Figure 3
Figure 3
SHAP analysis of findings (A) The importance of each parameter in the final prediction of the model. (B) The influence of parameter variations on the model’s predicted outcomes.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. 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. - PubMed
    1. 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. - PMC - PubMed
    1. 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. - PMC - PubMed
    1. 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. - PubMed
    1. 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. - PubMed

LinkOut - more resources