Machine Learning-Based Classification of Chronic Traumatic Brain Injury Using Hybrid Diffusion Imaging - Original Research

Aug 3, 2026

Traumatic brain injury can drive progressive neuropathology and long-term impairments, creating a need for biomarkers that detect and monitor chronic cases. This study evaluates data-driven analysis of diffusion tensor imaging (DTI) and neurite orientation dispersion imaging (NODDI) to infer symptom severity and assess whether these methods outperform conventional T1-weighted imaging. A supervised machine learning framework was trained on hybrid diffusion imaging features to classify chronic traumatic brain injury outcomes, comparing model accuracy across imaging modalities.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Background and Purpose

Materials and Methods

Results

Conclusion

Keywords

Thomas Jefferson University Jefferson Digital Commons | Marcus Institute of Integrative Health Faculty Papers | Marcus Institute of Integrative Health | | --- | --- | 8-24-2023 Machine Learning-Based Classification of Chronic Traumatic Brain Injury Using Hybrid Diffusion Imaging Jennifer Muller Ruixuan Wang Devon Middleton Mahdi Alizadeh KiChang Kang See next page for additional authors Follow this and additional works at: [https://jdc.jefferson.edu/jmbcimfp](https://jdc.jefferson.edu/jmbcimfp) Part of the Artificial Intelligence and Robotics Commons, Integrative Medicine Commons, Other Medicine and Health Sciences Commons, and the Trauma Commons Let us know how access to this document benefits you This Article is brought to you for free and open access by the Jefferson Digital Commons. The Jefferson Digital Commons is a service of Thomas Jefferson University's Center for Teaching and Learning (CTL) . The Commons is a showcase for Jefferson books and journals, peer-reviewed scholarly publications, unique historical collections from the University archives, and teaching tools. The Jefferson Digital Commons allows researchers and interested readers anywhere in the world to learn about and keep up to date with Jefferson scholarship. This article has been accepted for inclusion in Marcus Institute of Integrative Health Faculty Papers by an authorized administrator of the Jefferson Digital Commons. For more information, please contact: [JeffersonDigitalCommons@jefferson.edu](JeffersonDigitalCommons@jefferson.edu). Authors Jennifer Muller, Ruixuan Wang, Devon Middleton, Mahdi Alizadeh, KiChang Kang, Ryan Hryczyk, George Zabrecky, Chloe Hriso, Emily Navarreto, Nancy Wintering, Anthony J. Bazzan, Chengyuan Wu, Daniel A. Monti, Xun Jiao, Qianhong Wu, Andrew B. Newberg, and Feroze Mohamed TYPE Original Research PUBLISHED 24 August 2023 DOI 10. 3389/fnins.2023.1182509 OPEN ACCESS EDITED BY Andrew S. Nencka, Medical College of Wisconsin, United States REVIEWED BY Yang Yingjian, Northeastern University, China Omar Narvaez, University of Eastern Finland, Finland *CORRESPONDENCE Qianhong Wu [qianhong.wu@villanova.edu](qianhong.wu@villanova.edu) †These authors have contributed equally to this work RECEIVED 08 March 2023 ACCEPTED 30 May 2023 PUBLISHED 24 August 2023 CITATION Muller JJ, Wang R, Milddleton D, Alizadeh M, Kang KC, Hryczyk R, Zabrecky G, Hriso C, Navarreto E, Wintering N, Bazzan AJ, Wu C, Monti DA, Jiao X, Wu Q, Newberg AB and Mohamed FB (2023) Machine learning-based classiﬁcation of chronic traumatic brain injury using hybrid di􀀀usion imaging. Front. Neurosci. 17:1182509 . doi: 10.3389/fnins.2023.1182509 COPYRIGHT © 2023 Muller, Wang, Milddleton, Alizadeh, Kang, Hryczyk, Zabrecky, Hriso, Navarreto, Wintering, Bazzan, Wu, Monti, Jiao, Wu, Newberg and Mohamed. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Machine learning-based classiﬁcation of chronic traumatic brain injury using hybrid di􀀀usion imaging Jennifer J. Muller1,2†, Ruixuan Wang1,2†, Devon Milddleton2 , Mahdi Alizadeh2 , Ki Chang Kang2 , Ryan Hryczyk2 , George Zabrecky3 , Chloe Hriso3 , Emily Navarreto3 , Nancy Wintering3 , Anthony J. Bazzan3 , Chengyuan Wu4 , Daniel A. Monti3 , Xun Jiao1 , Qianhong Wu1*, Andrew B. Newberg3 and Feroze B. Mohamed2 1 College of Engineering, Villanova University, Villanova, PA, United States, 2 Department of Radiology, Thomas Je􀀀erson University, Philadelphia, PA, United States, 3 Marcus Institute of Integrative Health, Thomas Je􀀀erson University, Philadelphia,

FAQs

What problem does the study address regarding chronic traumatic brain injury?

Chronic traumatic brain injury can cause progressive neuropathology and impairments, so the study targets the need for biomarkers to detect and monitor the condition and infer symptom severity.

How was the machine learning model constructed in this research?

The model was trained using hybrid diffusion imaging data by extracting useful HYDI features and applying supervised learning to classify outcomes.

Which imaging approach performed best compared with conventional T1-weighted imaging?

DTI-based machine learning models improved accuracy to 58.7–73.0%, and NODDI-based models achieved 64.0–72.3%, outperforming T1-weighted classification accuracy of 51.7–56.8%.

Aug 3, 2026

Uploaded by Lucas Martin