Towards Multimodal Machine Learning Prediction of Individual Cognitive Evolution in Multiple Sclerosis

Multiple sclerosis (MS) manifests heterogeneously among persons suffering from it, making its disease course highly challenging to predict. At present, prognosis mostly relies on biomarkers that are unable to predict disease course on an individual level. Machine learning is a promising technique, both in terms of its ability to combine multimodal data and through the capability of making personalized predictions. However, most investigations on machine learning for prognosis in MS were geared towards predicting physical deterioration, while cognitive deterioration, although prevalent and burdensome, remained largely overlooked. This review aims to boost the field of machine learning for cognitive prognosis in MS by means of an introduction to machine learning and its pitfalls, an overview of important elements for study design, and an overview of the current literature on cognitive prognosis in MS using machine learning. Furthermore, the review discusses new trends in the field of machine learning that might be adopted for future studies in the field.

Download Full-text

Machine Learning Use for Prognostic Purposes in Multiple Sclerosis

Life ◽

10.3390/life11020122 ◽

2021 ◽

Vol 11 (2) ◽

pp. 122

Author(s):

Ruggiero Seccia ◽

Silvia Romano ◽

Marco Salvetti ◽

Andrea Crisanti ◽

Laura Palagi ◽

...

Keyword(s):

Machine Learning ◽

Multiple Sclerosis ◽

High Impact ◽

Prognostic Models ◽

Early Prediction ◽

Disease Course ◽

Slow Progression ◽

Relapsing Remitting ◽

Long Time ◽

Effective Drugs

The course of multiple sclerosis begins with a relapsing-remitting phase, which evolves into a secondarily progressive form over an extremely variable period, depending on many factors, each with a subtle influence. To date, no prognostic factors or risk score have been validated to predict disease course in single individuals. This is increasingly frustrating, since several treatments can prevent relapses and slow progression, even for a long time, although the possible adverse effects are relevant, in particular for the more effective drugs. An early prediction of disease course would allow differentiation of the treatment based on the expected aggressiveness of the disease, reserving high-impact therapies for patients at greater risk. To increase prognostic capacity, approaches based on machine learning (ML) algorithms are being attempted, given the failure of other approaches. Here we review recent studies that have used clinical data, alone or with other types of data, to derive prognostic models. Several algorithms that have been used and compared are described. Although no study has proposed a clinically usable model, knowledge is building up and in the future strong tools are likely to emerge.

Download Full-text

Ensemble learning predicts multiple sclerosis disease course in the SUMMIT study

npj Digital Medicine ◽

10.1038/s41746-020-00338-8 ◽

2020 ◽

Vol 3 (1) ◽

Author(s):

Yijun Zhao ◽

◽

Tong Wang ◽

Riley Bove ◽

Bruce Cree ◽

...

Keyword(s):

Machine Learning ◽

Multiple Sclerosis ◽

San Francisco ◽

Ensemble Learning ◽

Disease Onset ◽

Machine Learning Algorithms ◽

Machine Learning Techniques ◽

Learning Approaches ◽

Disease Course ◽

Learning Techniques

AbstractThe rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women’s Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale (EDSS) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients’ clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (SVM, Logistic Regression, and Random Forest) and three ensemble learning approaches (XGBoost, LightGBM, and a Meta-learner L). A “threshold” was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function, and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course.

Download Full-text

Exploration of machine learning techniques in predicting multiple sclerosis disease course

PLoS ONE ◽

10.1371/journal.pone.0174866 ◽

2017 ◽

Vol 12 (4) ◽

pp. e0174866 ◽

Cited By ~ 39

Author(s):

Yijun Zhao ◽

Brian C. Healy ◽

Dalia Rotstein ◽

Charles R. G. Guttmann ◽

Rohit Bakshi ◽

...

Keyword(s):

Machine Learning ◽

Multiple Sclerosis ◽

Machine Learning Techniques ◽

Disease Course ◽

Learning Techniques ◽

Multiple Sclerosis Disease

Download Full-text

Interferon beta-1b therapy in relapsing-remitting multiple sclerosis: Study design and preliminary results

Electroencephalography and Clinical Neurophysiology ◽

10.1016/s0013-4694(97)88414-7 ◽

1997 ◽

Vol 103 (1) ◽

pp. 99

Author(s):

G Salemi

Keyword(s):

Multiple Sclerosis ◽

Study Design ◽

Interferon Beta ◽

Preliminary Results ◽

Relapsing Remitting ◽

Remitting Multiple Sclerosis ◽

Relapsing Remitting Multiple Sclerosis

Download Full-text

Faculty Opinions recommendation of Electrophysiological markers and predictors of the disease course in primary progressive multiple sclerosis.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.718018944.793478763 ◽

2013 ◽

Author(s):

Marco Rovaris

Keyword(s):

Multiple Sclerosis ◽

Progressive Multiple Sclerosis ◽

Primary Progressive Multiple Sclerosis ◽

Disease Course ◽

Primary Progressive

Download Full-text

A Machine Learning Approach to Study Glycosidase Activities from Bifidobacterium

Microorganisms ◽

10.3390/microorganisms9051034 ◽

2021 ◽

Vol 9 (5) ◽

pp. 1034

Author(s):

Carlos Sabater ◽

Lorena Ruiz ◽

Abelardo Margolles

Keyword(s):

Machine Learning ◽

Supervised Classification ◽

Machine Learning Algorithms ◽

Learning Approach ◽

Human Milk Oligosaccharides ◽

Future Studies ◽

High Fiber ◽

Machine Learning Approach ◽

Prebiotic Oligosaccharides

This study aimed to recover metagenome-assembled genomes (MAGs) from human fecal samples to characterize the glycosidase profiles of Bifidobacterium species exposed to different prebiotic oligosaccharides (galacto-oligosaccharides, fructo-oligosaccharides and human milk oligosaccharides, HMOs) as well as high-fiber diets. A total of 1806 MAGs were recovered from 487 infant and adult metagenomes. Unsupervised and supervised classification of glycosidases codified in MAGs using machine-learning algorithms allowed establishing characteristic hydrolytic profiles for B. adolescentis, B. bifidum, B. breve, B. longum and B. pseudocatenulatum, yielding classification rates above 90%. Glycosidase families GH5 44, GH32, and GH110 were characteristic of B. bifidum. The presence or absence of GH1, GH2, GH5 and GH20 was characteristic of B. adolescentis, B. breve and B. pseudocatenulatum, while families GH1 and GH30 were relevant in MAGs from B. longum. These characteristic profiles allowed discriminating bifidobacteria regardless of prebiotic exposure. Correlation analysis of glycosidase activities suggests strong associations between glycosidase families comprising HMOs-degrading enzymes, which are often found in MAGs from the same species. Mathematical models here proposed may contribute to a better understanding of the carbohydrate metabolism of some common bifidobacteria species and could be extrapolated to other microorganisms of interest in future studies.

Download Full-text

MicroRNA expression classification for pediatric multiple sclerosis identification

Journal of Ambient Intelligence and Humanized Computing ◽

10.1007/s12652-021-03091-2 ◽

2021 ◽

Author(s):

Gabriella Casalino ◽

Giovanna Castellano ◽

Arianna Consiglio ◽

Nicoletta Nuzziello ◽

Gennaro Vessio

Keyword(s):

Machine Learning ◽

Multiple Sclerosis ◽

Expression Profiles ◽

Healthy Children ◽

Multifactorial Diseases ◽

Hyperactivity Disorder ◽

Pediatric Multiple Sclerosis ◽

Mirna Expression Profiles ◽

Selection Algorithms ◽

Expression Classification

Abstract MicroRNAs (miRNAs) are a set of short non-coding RNAs that play significant regulatory roles in cells. The study of miRNA data produced by Next-Generation Sequencing techniques can be of valid help for the analysis of multifactorial diseases, such as Multiple Sclerosis (MS). Although extensive studies have been conducted on young adults affected by MS, very little work has been done to investigate the pathogenic mechanisms in pediatric patients, and none from a machine learning perspective. In this work, we report the experimental results of a classification study aimed at evaluating the effectiveness of machine learning methods in automatically distinguishing pediatric MS from healthy children, based on their miRNA expression profiles. Additionally, since Attention Deficit Hyperactivity Disorder (ADHD) shares some cognitive impairments with pediatric MS, we also included patients affected by ADHD in our study. Encouraging results were obtained with an artificial neural network model based on a set of features automatically selected by feature selection algorithms. The results obtained show that models developed on automatically selected features overcome models based on a set of features selected by human experts. Developing an automatic predictive model can support clinicians in early MS diagnosis and provide new insights that can help find novel molecular pathways involved in MS disease.

Download Full-text

Study protocol: randomised controlled trial evaluating exercise therapy as a supplemental treatment strategy in early multiple sclerosis: the Early Multiple Sclerosis Exercise Study (EMSES)

BMJ Open ◽

10.1136/bmjopen-2020-043699 ◽

2021 ◽

Vol 11 (1) ◽

pp. e043699

Author(s):

Morten Riemenschneider ◽

Lars G Hvid ◽

Steffen Ringgaard ◽

Mikkel K E Nygaard ◽

Simon F Eskildsen ◽

...

Keyword(s):

Multiple Sclerosis ◽

Randomised Controlled Trial ◽

Usual Care ◽

Treatment Strategy ◽

Controlled Trial ◽

Treatment Strategies ◽

Control Group ◽

Disease Course ◽

Disability Progression ◽

Randomised Controlled

IntroductionIn the relapsing remitting type of multiple sclerosis (MS) reducing relapses and neurodegeneration is crucial in halting the long-term impact of the disease. Medical disease-modifying treatments have proven effective, especially when introduced early in the disease course. However, patients still experience disease activity and disability progression, and therefore, supplemental early treatment strategies are warranted. Exercise appear to be one of the most promising supplemental treatment strategies, but a somewhat overlooked ‘window of opportunity’ exist early in the disease course. The objective of this study is to investigate exercise as a supplementary treatment strategy early in the disease course of MS.Methods and analysisThe presented Early Multiple Sclerosis Exercise Study is a 48-week (plus 1-year follow-up) national multicentre single-blinded parallel group randomised controlled trial comparing two groups receiving usual care plus supervised high-intense exercise or plus health education (active control). Additionally, data will be compared with a population-based control group receiving usual care only obtained from the Danish MS Registry. The primary outcomes are annual relapse rate and MRI derived global brain atrophy. The secondary outcomes are disability progression, physical and cognitive function, MS-related symptoms, and exploratory MRI outcomes. All analyses will be performed as intention to treat.Ethics and disseminationThe study is approved by The Central Denmark Region Committees on Health Research Ethics (1-10-72-388-17) and registered at the Danish Data Protection Agency (2016-051-000001 (706)). All study findings will be published in scientific peer-reviewed journals and presented at relevant scientific conferences.Trial registration numberNCT03322761.

Download Full-text

Association of apolipoprotein E and myeloperoxidase genotypes to clinical course of familial and sporadic multiple sclerosis

Multiple Sclerosis Journal ◽

10.1191/1352458504ms1015oa ◽

2004 ◽

Vol 10 (3) ◽

pp. 266-271 ◽

Cited By ~ 33

Author(s):

B Zakrzewska-Pniewska ◽

M Styczynska ◽

A Podlecka ◽

R Samocka ◽

B Peplonska ◽

...

Keyword(s):

Multiple Sclerosis ◽

Apolipoprotein E ◽

Brain Atrophy ◽

Genetic Factors ◽

Clinical Course ◽

Progression Rate ◽

Disease Course ◽

Familial Cases ◽

Sporadic Cases ◽

The Relationship

The importance of apolipoprotein E (ApoE) and myeloperoxidase (MPO) genotypes in the clinical characteristics of multiple sclerosis (MS) has been recently emphasized. In a large group of Polish patients we have tested the hypothesis that polymorphism in ApoE and MPO genes may influence the course of the disease. G enotypes were determined in 117 MS patients (74 females and 43 males; 99 sporadic and 18 familial cases) with mean EDSS of 3.6, mean age of 44.1 years, mean duration of the disease 12.8 years and mean onset of MS at 31.2 years, and in 100 healthy controls. The relationship between ApoE and MPO genes’ polymorphism and the MS activity as well as the defect of remyelination (diffuse demyelination) and brain atrophy on MRI were analysed. The ApoE o4 allele was not related to the disease course or the ApoE o2 to the intensity of demyelination on MRI. The genotype MPO G/G was found in all familial MS and in 57% (56/99) of sporadic cases. This genotype was also related to more pronounced brain atrophy on MRI. The MPO G/G subpopulation was characterized by a significantly higher proportion of patients with secondary progressive MS (PB- 0.05) and by a higher value of EDSS. A ccording to our results the MPO G allele is frequently found (in 96% of cases) among Polish patients with MS. More severe nervous tissue damage in the MPO G/G form can be explained by the mechanism of accelerated oxidative stress. It seems that MPO G/G genotype may be one of the genetic factors influencing the progression rate of disability in MS patients.

Download Full-text