A Random Forest–Driven Clinical Decision Model for Early Detection of Clinically Definite Multiple Sclerosis Using Multimodal Diagnostic Data
DOI:
https://doi.org/10.52098/airdj.20266169Keywords:
multiple sclerosis, Machine learning, early classification, multimodal diagnostic features, random forestAbstract
Early and precise diagnosis of Clinically Definite Multiple Sclerosis (CDMS) continues to be a significant issue in neurology, especially during the progression from initial symptoms to a conclusive diagnosis. This study introduces a machine learning-driven predictive model that utilizes multimodal diagnostic data—comprising MRI results, somatosensory evoked potentials (LLSSEP and ULSSEP), visual and auditory evoked potentials (VEP, BAEP), and clinical-demographic variables—to categorize patients as CDMS or non-CDMS. A Random Forest classifier was developed and verified using a dataset of 273 actual patients. The model had a very high predictive performance, with an area under the ROC curve (AUC) of more than 0.90 and very good precision-recall metrics. Feature importance analysis indicated that spinal cord MRI, oligoclonal bands, and lower limb SSEPs are the most significant predictors of CDMS. These results correspond with established biomarkers of MS development, illustrating the model's clinical significance. The suggested framework provides understandable, highly accurate decision assistance that could help neurologists diagnose MS early and figure out how likely someone is to have it. This research advances the emerging domain of AI-driven neurodiagnostics and underscores the efficacy of integrating electrophysiological, imaging, and historical patient data for precise classification of neuroinflammatory illnesses. Future validation in multi-center cohorts may facilitate its implementation in clinical decision systems.
References
Polman, C. H., Reingold, S. C., Banwell, B., Clanet, M., Cohen, J. A., Filippi, M., ... & Wolinsky, J. S. (2011). Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria. Annals of neurology, 69(2), 292-302.
Thabet, R. M., Shedeed, H. A., Al-Berry, M., & Khattab, D. (2025). Multiple sclerosis classification and segmentation in neuroimaging MRI using different machine and deep learning techniques: a review. Artificial Intelligence Review, 58(8), 255.
Eshaghi, A., Young, A. L., Wijeratne, P. A., Prados, F., Arnold, D. L., Narayanan, S., ... & Ciccarelli, O. (2021). Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data. Nature communications, 12(1), 2078.
Abusham, E. E., Ngo, D., & Teoh, A. (2006). Comparing the performance of principal component analysis and rbf network for face recognition using locally linear embedding. IJCSNS, 6(4), 25.
Abusham, E. E., & Wong, E. K. (2009). Locally linear discriminate embedding for face recognition. Discrete Dynamics in Nature and Society, 2009(1), 916382.
Abusham, E. A. (2014). Face verification using local graph stucture (LGS). In 2014 International Symposium on Biometrics and Security Technologies (ISBAST) (pp. 79-83). IEEE.
Abusham, E. E. A., Jin, A. T., Kiong, W. E., & Debashis, G. (2008). Face recognition based on nonlinear feature approach. American Journal of Applied Sciences, 5(5), 574-580.
Bashier, H. K., Abusham, E. E., Abdullah, M. F. A., Liew, T. H., Yusof, I., & Lau, S. H. (2013). Real time face tracker based on local graph structure threshold (LGS-TH). Australian Journal of Basic and Applied Sciences, 7(2), 632-638.
Yousef, H., Malagurski Tortei, B., & Castiglione, F. (2024). Predicting multiple sclerosis disease progression and outcomes with machine learning and MRI-based biomarkers: a review. Journal of neurology, 271(10), 6543-6572.
Andorra, M., Freire, A., Zubizarreta, I., de Rosbo, N. K., Bos, S. D., Rinas, M., ... & Villoslada, P. (2024). Predicting disease severity in multiple sclerosis using multimodal data and machine learning. Journal of Neurology, 271(3), 1133-1149.
Pinto, M. F., Oliveira, H., Batista, S., Cruz, L., Pinto, M., Correia, I., ... & Teixeira, C. (2020). Prediction of disease progression and outcomes in multiple sclerosis with machine learning. Scientific reports, 10(1), 21038.
Branco, D., Martino, B. D., Esposito, A., Tedeschi, G., Bonavita, S., & Lavorgna, L. (2022). Machine learning techniques for prediction of multiple sclerosis progression. Soft Computing, 26(22), 12041-12055.
Pellegrini, F., Copetti, M., Sormani, M. P., Bovis, F., de Moor, C., Debray, T. P., & Kieseier, B. C. (2020). Predicting disability progression in multiple sclerosis: Insights from advanced statistical modeling. Multiple Sclerosis Journal, 26(14), 1828-1836.
Ramanujam, R., Zhu, F., Fink, K., Karrenbauer, V. D., Lorscheider, J., Benkert, P., ... & BeAMS Study group. (2021). Accurate classification of secondary progression in multiple sclerosis using a decision tree. Multiple Sclerosis Journal, 27(8), 1240-1249.
Cairns, J., Vavasour, I. M., Traboulsee, A., Carruthers, R., Kolind, S. H., Li, D. K., ... & Laule, C. (2022). Diffusely abnormal white matter in multiple sclerosis. Journal of Neuroimaging, 32(1), 5-16.
Westman, E., Muehlboeck, J. S., & Simmons, A. (2012). Combining MRI and CSF measures for classification of Alzheimer's disease and prediction of mild cognitive impairment conversion. Neuroimage, 62(1), 229-238.
De Leon, D., Mosconi, L., Blennow, K., DeSanti, S., Zinkowski, R., Mehta, P. D., ... & Rusinek, H. (2007). Imaging and CSF studies in the preclinical diagnosis of Alzheimer's disease. Annals of the New York Academy of Sciences, 1097(1), 114-145.
Cohen, A. B., Neema, M., Arora, A., Dell’Oglio, E., Benedict, R. H., Tauhid, S., ... & Bakshi, R. (2012). The relationships among MRI‐defined spinal cord involvement, brain involvement, and disability in multiple sclerosis. Journal of Neuroimaging, 22(2), 122-128.
Schlaeger, R., Papinutto, N., Panara, V., Bevan, C., Lobach, I. V., Bucci, M., ... & Henry, R. G. (2014). Spinal cord gray matter atrophy correlates with multiple sclerosis disability. Annals of neurology, 76(4), 568-580.
Hardmeier, M., Leocani, L., & Fuhr, P. (2017). A new role for evoked potentials in MS? Repurposing evoked potentials as biomarkers for clinical trials in MS. Multiple Sclerosis Journal, 23(10), 1309-1319.
Covey, T. J., Golan, D., Doniger, G. M., Sergott, R., Zarif, M., Srinivasan, J., ... & Gudesblatt, M. (2021). Visual evoked potential latency predicts cognitive function in people with multiple sclerosis. Journal of Neurology, 268(11), 4311-4320.
Kline, A., Wang, H., Li, Y., Dennis, S., Hutch, M., Xu, Z., ... & Luo, Y. (2022). Multimodal machine learning in precision health: A scoping review. NPJ digital medicine, 5(1), 171.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Author(s) and ACAA permit unrestricted use, distribution, and reproduction in any medium, provided the original work with proper citation. This work is open access and licensed under Creative Commons Attribution International License (CC BY 4.0).
This work is licensed under a Creative Commons Attribution 4.0 International License.
ACAA applies the Creative Commons Attribution (CC BY 4.0) license to all published work. All ACAA content is open access that freely available for the public to unrestricted use, distribution, and reproduction in any medium, provided the original work with proper citation.
