Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Artificial Intelligence in Medical Issues
Yulinda, Nurul Kholifah
Unknown Affiliation
Computer Science & IT Dentistry Health Professions Medicine & Pharmacology Public Health

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Predicting the Conversion from Clinically Isolated Syndrome to Multiple Sclerosis in Mexican Mestizo Patients Using Gaussian Naive Bayes Classifier: A Prospective Cohort Study Yulinda, Nurul Kholifah
International Journal of Artificial Intelligence in Medical Issues Vol. 2 No. 1 (2024): International Journal of Artificial Intelligence in Medical Issues
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijaimi.v2i1.139

Abstract

This study explores the application of the Gaussian Naive Bayes (GNB) classifier to predict the conversion from Clinically Isolated Syndrome (CIS) to Multiple Sclerosis (MS) among Mexican mestizo patients. Utilizing a dataset gathered from the National Institute of Neurology and Neurosurgery in Mexico City, which included patients diagnosed with CIS between 2006 and 2010, we employed a prospective cohort study design. Our approach involved preprocessing the data to handle missing values and scale normalization followed by splitting it into training and testing subsets. The GNB model's performance was assessed through a 5-fold cross-validation, focusing on accuracy, precision, recall, and F1-score. Results demonstrated the model's capability to predict MS conversion with reasonable precision, highlighted by a significant peak in performance metrics in the third fold of the validation. The study addresses a gap in predictive diagnostics for MS within a specific demographic group, providing valuable insights for early intervention strategies. Despite some limitations such as the model's sensitivity to data heterogeneity and the demographic specificity of the cohort, the findings underscore the potential for predictive models in clinical settings. Recommendations for future research include the use of more sophisticated algorithms and broader demographic studies to enhance predictive accuracy and generalizability.
Co-Authors