Medicine Science (Dec 2023)
The role of advanced machine learning approach in predicting multiple sclerosis development and progression
Abstract
This study aims to utilize a fine-tuned gradient boosting trees algorithm to predict the onset and progression of Multiple Sclerosis (MS) based on a comprehensive set of demographic and clinical variables. The goal was to enhance early diagnosis and enable individualized treatment approaches using artificial intelligence. The research utilized Dataset, a publicly accessible dataset derived from a prospective cohort study of individuals of Mexican mestizo descent diagnosed with Clinically Isolated Syndrome (CIS). The study spanned from 2006 to 2010, systematically collecting and analyzing data on various individual traits to explore correlations with MS development. The gradient boosting trees algorithm was employed to construct predictive models, harnessing patient-specific variables, including demographic factors and clinical data. The classifier exhibited outstanding performance, with a mean accuracy of 99.63% and minimal standard deviation. The confusion matrix indicated one false positive and no false negatives. Key metrics such as precision, recall, and AUC all approached 1, demonstrating the classifier's ability to distinguish between the two classes with high confidence. Comparative analysis with similar studies in the literature revealed superior performance, highlighting the classifier's accuracy and effectiveness in predicting MS. The application of the gradient boosting trees algorithm to predict MS based on demographic and clinical variables offers a promising avenue for early diagnosis and tailored treatment. This research demonstrates the potential of AI to transform healthcare, particularly in the context of MS. The predictive models developed have the capacity to enhance early detection, improve patient quality of life, and pave the way for further AI-based solutions in healthcare. [Med-Science 2023; 12(4.000): 1315-9]
Keywords
