A key barrier in identifying subtypes of these disorders is to stitch together observations from cross-sectional or longitudinal studies (which are rarely more than a few years long). Neurodegenerative disorders have a long prodromal period and are lifelong. MRI is a strong candidate for data-driven disease classification, because it better reflects the MS pathogenic mechanisms than purely clinical descriptions 5. If we could instead delineate well-defined subtypes that are aligned with underpinning pathobiological changes, we would be able to identify subgroups to which treatment mechanisms do or do not apply and address these long-standing ambiguities. SPMS and PPMS share many MRI features and pathogenic similarities 4. The precise timing of these transitions is challenging to ascertain, because they are often based on the subjective recollection of symptoms and interpretation of signs. Imaging, immunologic, or pathologic investigations often show more similarities than differences across the MS clinical phenotypes: CIS patients may evolve into RRMS, and the majority of RRMS patients transition into SPMS over time 2, 3. Phenotypes and their descriptors are routinely used in clinical trials to select patients and to guide treatment assignment. Two descriptors underly these phenotypes: (i) disease activity, as evidenced by relapses or new activity on magnetic resonance imaging (MRI) and (ii) progression of disability 3. Current practice divides MS into four phenotypes: clinically isolated syndrome (CIS), relapsing-remitting MS (RRMS), primary-progressive MS (PPMS) and secondary progressive MS (SPMS) 3. Multiple sclerosis (MS), which affects more than 2.8 million people globally, is primarily classified according to clinical symptoms rather than on well-defined pathological mechanisms 2. Such methods, applied to visible abnormalities on MRI scans, have great promise in classifying patients who share similar pathobiological mechanisms rather than common clinical features 1. New technologies, such as artificial intelligence and machine learning, can evaluate multidimensional data to identify groups with similar features. The consequences of redefining disease subtypes based on biology rather than on clinical grounds alone are that clinical trials should be better able to recruit patients who are likely to benefit from the medication under investigation. There is a pressing need in neurology to define disease phenotypes based on their underpinning mechanisms, as an important step towards stratified medicine. Our findings suggest that MRI-based subtypes predict MS disability progression and response to treatment and may be used to define groups of patients in interventional trials. People with the lesion-led MS subtype show positive treatment response in selected clinical trials. People with the lesion-led subtype have the highest risk of confirmed disability progression (CDP) and the highest relapse rate. Based on the earliest abnormalities, we define MS subtypes as cortex-led, normal-appearing white matter-led, and lesion-led. We use a training dataset from 6322 MS patients to define MRI-based subtypes and an independent cohort of 3068 patients for validation. Here, to classify MS subtypes based on pathological features, we apply unsupervised machine learning to brain MRI scans acquired in previously published studies. ![]() ![]() Machine learning can identify groups with similar features using multidimensional data. The pathophysiological boundaries of these phenotypes are unclear, limiting treatment stratification. Multiple sclerosis (MS) can be divided into four phenotypes based on clinical evolution.
0 Comments
Leave a Reply. |