Paper Title
EDSS Estimation by Static Posturography Using Machine Learning Boosting Algorithms

Abstract
Multiple sclerosis is a chronic autoimmune demyelinating disease of the central nervous system. It causes the brain tissues to be damaged by its immune system, resulting in inflammation. Just like how water gets leaked from a broken pipeline, damaged tissue can lead to improper, slow, or even blocked passage of message signals from/to the brain. DMTs can slow down the damage caused by MS. EDSS scale is used to quantify the disability. It is widely used in clinical trials as the default scoring system for MS. By the EDSS of a person, we can determine his/her balance impairment. And by using machine learning, based on their balance impairment we can estimate the EDSS of a person. Static Posturography is considered the best way to pin down the balance impairment in People with Multiple Sclerosis (PwMS). In this study, a prevalence study Static Posturography dataset was used for training the model. Kaplan–Meier estimator was used to determining which features need to be considered for the training. XG Boosting with a depth-first approach was used to build a ML model. We then compared the results obtained to another analysis conducted with the same dataset using a statistical approach. Keywords- Machine learning, EDSS, DMT, Boosting, Static Posturography, Algorithms.