Browsing by Author "Ozcanhan, Mehmet Hilal"

Now showing 1 - 4 of 4

Development a Machine Learning Model To Prediction of Expanded Disability Status Scale in Multiple Sclerosis Patients
(Sage Publications Ltd, 2024) Ozdogar, Asiye Tuba; Emec, Murat; Zengin, Ela; Ozcanhan, Mehmet Hilal; Ozakbas, Serkan
Development of a Machine Learning Model to Predict the Expanded Disability Status Scale in Multiple Sclerosis Patients
(Elsevier Sci Ltd, 2026) Ozdogar, Asiye Tuba; Emec, Murat; Kaya, Ergi; Zengin, Ela Simay; Ozcanhan, Mehmet Hilal; Ozakbas, Serkan
Objective: The assessment of disability in multiple sclerosis (MS) patients is crucial for treatment decisions and prognosis estimation. The Expanded Disability Status Scale (EDSS) provides a standardized way to quantify disability in MS. However, predicting EDSS scores can be challenging due to the complex and heterogeneous nature of the disease. Machine learning techniques offer a promising approach to predict EDSS scores based on various patient characteristics. Methods: 231 people with MS (pwMS) who had an assessment of physical, psychosocial, and cognitive functions in three timelines (baseline (T0), first year (T1), and second year (T2)) were enrolled. The dataset used for the study consists of 126 features. Feature selection was based on feature saliency and correlation analysis. Three machine learning models -XGBoost, Random Forest, and Linear Regression -were trained on the selected features. Hyperparameter tuning was also carried out on the models. Model performance was evaluated using standard evaluation metrics, including MAE, MSE, and R2. Results: The Machine Learning model based on the XGBoost algorithm performed best in predicting EDSS scores (T2). The MAE value obtained with the XGBoost model is 0.2361, the MSE value is 0.2408, and the R2 value is 0.9705. These results indicate that XGBoost's predictive ability on the current dataset is promising. Conclusion: Our study demonstrates the feasibility of using machine learning techniques to predict EDSS scores in MS patients. The developed models show promising performance and have the potential to enhance clinical decision-making and patient management in MS care.
Integrating Reproductive and Clinical Variables to Predict Postpartum Disability Outcomes in Multiple Sclerosis Using Machine Learning
(Elsevier Sci Ltd, 2026) Samadzade, Ulvi; Emec, Murat; Alizada, Said; Ozcanhan, Mehmet Hilal; Simsek, Yasemin; Ozakbas, Serkan
Background: Pregnancy represents a unique immunological state in women with multiple sclerosis (MS), and postpartum disease reactivation is a major concern. While pregnancy outcomes have been extensively described, the long-term effects of reproductive and obstetric variables on disability progression remain poorly elucidated. Objective: To predict postpartum EDSS-based disability change based on pregnancy-related clinical and demographic variables in women with MS, using validated machine learning models. Methods: This retrospective real-world study included 662 women contributing 909 pregnancies. Engineered features included pre- and post-pregnancy Expanded Disability Status Scale (EDSS) scores, disease duration, maternal age, postpartum relapse, and obstetric variables. Regression and classification models (Random Forest, XGBoost, Elastic Net, Support Vector Classifier) were trained on an 80/20 train-test split with five-fold crossvalidation. Model performance was assessed using R2, mean absolute error (MAE), accuracy, and F1 score. Results: Classification models achieved superior generalization performance (test accuracy 85-88%, F1 0.84-0.87) compared to regression models (test R2 0.31-0.39, MAE 0.41-0.48). Postpartum relapse was the strongest predictor of disability change, followed by disease duration and age at pregnancy. Predictive performance was highest among women with multiple pregnancies, suggesting that cumulative reproductive history carries prognostic value. Obstetric variables such as delivery type and breastfeeding contributed secondary but clinically relevant effects. Conclusion: Machine learning models integrating pregnancy-related variables can provide clinically informative predictions regarding postpartum EDSS-based disability change in women with MS. Postpartum relapse remains the dominant driver of disability change, while reproductive and obstetric factors provide additional prognostic information. These findings highlight the postpartum period as a critical therapeutic window and support incorporating reproductive variables into individualized prognostic frameworks for women with MS.
Pregnancy and Future Disability in MS: Can Machine Learning Help Predict the Trajectory
(Sage Publications Ltd, 2025) Emec, Murat; Kaya, Ergi; Simsek, Yasemin; Ozcanhan, Mehmet Hilal; Ozakbas, Serkan