New Study Proposes Machine Learning-Based Phases for Multiple Sclerosis
Multiple Sclerosis (MS) is a complex neurological condition that affects the central nervous system. It's usually classified into four types based on its progression, with symptoms varying widely among individuals. A recent study by Dr. Alessia Bianchi proposes a new classification of MS into phases using machine learning.
MS occurs when the immune system mistakenly targets the central nervous system, damaging the myelin sheath that protects nerve fibers. The condition typically progresses through several phases. The early or high risk phase involves initial symptoms like vision changes, numbness, fatigue, and balance issues. This is followed by the relapsing-remitting phase, characterized by periods of symptom worsening (flare-ups) followed by improvement or remission. Around 2 in 3 people with MS will retain the ability to walk throughout their lives, but some may need assistive devices, and MS can shorten life expectancy by up to 7 years.
The progressive phase of MS is less common and involves steadily worsening symptoms with no periods of remission. This phase can be further divided into secondary progressive MS (SPMS), which follows a period of relapsing-remitting MS, and primary progressive MS (PPMS), where progression is evident from the onset. Around 3-5% of people with MS experience pediatric-onset MS, which progresses differently than adult-onset MS and often begins more aggressively. Due to its varied nature, MS is difficult to diagnose and predict before symptoms become visible, leading experts to consider classifying it in terms of stages or phases.
MS is a lifelong condition that may take years for symptoms to develop. Its progression varies widely, with symptoms typically worsening over time but not always following a specific timeline or pattern. Working closely with a healthcare provider is crucial for monitoring and managing the condition effectively. Dr. Bianchi's study suggests that classifying MS into phases using machine learning could improve understanding and treatment of the condition.
