Author

Mohammadali Sahraian

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Open access Aug 2026

Application of the 2024 McDonald Criteria

The evolution of multiple sclerosis (MS) diagnostic criteria over the past 4 decades has shortened the time to diagnosis of MS, enabling earlier institution of immunomodulatory therapy and therefore improved clinical outcomes. In response to a recent expansion of knowledge related to approaches and paraclinical tools that may aid diagnosis of MS and identify causes of MS misdiagnosis, the 2024 McDonald criteria reflect substantive changes and introduce new pathways to MS diagnosis. These revisions carry potential for both earlier and more accurate diagnosis of MS, yet require expertise for their appropriate application in clinical practice and introduce new challenges for global implementation. These changes include expansion of anatomical locations that represent dissemination in space, new paraclinical findings that can substitute for dissemination in time, inclusion of patients with asymptomatic or nonspecific clinical presentations, and recommendations for diagnostic approaches in specific patient populations. These changes also incorporate new paraclinical tools for the first time, including MRI central vein sign and paramagnetic rim lesions, CSF kappa free light chains, and optical coherence tomography. The revised criteria have now unified the diagnostic pathway for clinical presentations typical of MS with attack or progressive onset, and established a new pathway for patients without symptoms or with nonspecific clinical presentations accompanied by MRI findings typical of MS. The 2024 revisions continue to rely on recognition of typical clinical and MRI findings of MS, and additionally recommend specific approaches to pediatric patients, patients with vascular comorbidities, and older patients to further reduce the risk of misdiagnosis. Previous data suggest barriers to implementation, and misunderstanding and misapplication of prior revisions to MS diagnostic criteria that may be associated with misdiagnosis. Implementation of the revised 2024 McDonald criteria globally, particularly in low and low-middle income countries, will require educational outreach, leveraging and maximizing existing resources, and engagement of health care systems to improve access to new technology. This review contextualizes the implications of key revisions in the 2024 criteria for routine clinical care, while providing accessible guidance for its appropriate application with a lens toward nonspecialist clinicians and trainees globally, to ensure early and accurate MS diagnosis.

A. J. Solomon, W. Brownlee, Shanthi Viswanathan et al. · Neurology · 0 citations

Open access Jul 2026

A Data-Driven Approach for Handling Missing Data in a Real Multiple Sclerosis Dataset Based on Machine Learning

Background and Objective: Reliable medical research depends on data integrity, yet clinical datasets often contain real and systematically missing values. This study aimed to develop a robust, clinically realistic imputation framework for a raw Multiple Sclerosis (MS) dataset affected by real-world missingness. Methods: We propose an innovative data-driven approach called the Sequential Multiple Imputation Bootstrapping (SMIB) model, which orders imputation based on feature correlation and incorporates bootstrapping to enhance stability and generalizability. Relevant features were identified using RF importance and Mutual Information scores and imputed using a hybrid machine learning framework that combines Random Forest (RF), Multilayer Perceptron (MLP), k-Nearest Neighbors (kNN), and a multiple imputation (MI) algorithm. The proposed method was evaluated using 15-fold cross-validation and a masking-based evaluation strategy. Model performance was assessed using accuracy, precision, recall, specificity, F1 score, Mean Squared Error (MSE), Mean Absolute Error (MAE), and R2. Results: RF-based SMIB achieved superior performance, with final imputation accuracy reaching up to 97% for categorical outcomes and strong numerical performance (R2 up to 0.999; MSE as low as 2.48 × 10−5). Sequential ordering and weighted bootstrapping improved stability in imbalanced clinical data under real-world missingness. Compared with the widely adopted Multiple Imputation by Chained Equations (MICE) approach, the proposed SMIB framework consistently demonstrated superior predictive performance across all evaluated categorical and numerical outcomes. Conclusions: The SMIB framework provides a robust and clinically aligned strategy for handling real-world missing values in MS datasets, improving imputation accuracy while preserving feature dependencies and feature relationships. The method supports reliable predictive analytics in healthcare contexts.

Shima Pilehvari, Wei Peng, Mohammadali Sahraian et al. · Sclerosis · 0 citations