The role of machine learning in developing non-magnetic resonance imaging based biomarkers for multiple sclerosis: a systematic review

Abstract

Background Multiple sclerosis (MS) is a neurological condition whose symptoms, severity, and progression over time vary enormously among individuals. Ideally, each person living with MS should be provided with an accurate prognosis at the time of diagnosis, precision in initial and subsequent treatment decisions, and improved timeliness in detecting the need to reassess treatment regimens. To manage these three components, discovering an accurate, objective measure of overall disease severity is essential. Machine learning (ML) algorithms can contribute to finding such a clinically useful biomarker of MS through their ability to search and analyze datasets about potential biomarkers at scale. Our aim was to conduct a systematic review to determine how, and in what way, ML has been applied to the study of MS biomarkers on data from sources other than magnetic resonance imaging. Methods Systematic searches through eight databases were conducted for literature published in 2014–2020 on MS and specified ML algorithms. Results Of the 1, 052 returned papers, 66 met the inclusion criteria. All included papers addressed developing classifiers for MS identification or measuring its progression, typically, using hold-out evaluation on subsets of fewer than 200 participants with MS. These classifiers focused on biomarkers of MS, ranging from those derived from omics and phenotypical data (34.5% clinical, 33.3% biological, 23.0% physiological, and 9.2% drug response). Algorithmic choices were dependent on both the amount of data available for supervised ML (91.5%; 49.2% classification and 42.3% regression) and the requirement to be able to justify the resulting decision-making principles in healthcare settings. Therefore, algorithms based on decision trees and support vector machines were commonly used, and the maximum average performance of 89.9% AUC was found in random forests comparing with other ML algorithms. Conclusions ML is applicable to determining how candidate biomarkers perform in the assessment of disease severity. However, applying ML research to develop decision aids to help clinicians optimize treatment strategies and analyze treatment responses in individual patients calls for creating appropriate data resources and shared experimental protocols. They should target proceeding from segregated classification of signals or natural language to both holistic analyses across data modalities and clinically-meaningful differentiation of disease. Supplementary Information The online version contains supplementary material available at 10.1186/s12911-022-01985-5.

Predicting disease severity in multiple sclerosis using multimodal data and machine learning

“…Random forest allows developing algorithms for classification (dichotomous outcomes) or regression (continuous outcomes) by constructing decision trees, ranking variables by importance, and without overfitting the training set. For these reasons, they are being applied to omics and imaging classification problems [ 18 , 19 ] and are the most commonly used in MS [ 20 – 22 ]. Other machine learning techniques can be applied to this type of datasets, such as neural networks, linear regression or least absolute shrinkage and selection operator (LASSO) regression methods, support vector machines or Bayesian networks, which may differ in their performance depending on the size of the dataset and quality of the data as well as on the type of prediction or clinical question [ 16 , 57 – 60 ].…”

“…Besides, we explore further reducing dimensionality using principal component analysis on the features selected. The search of classifiers was done using Random Forest algorithms, considering they are better in handling unbalanced data, high dimensionality, multi-collinear features and have a lower risk of overfitting, which is a common problem in biomedical datasets [ 44 ], when studying complex disorders such as MS [ 20 ]. For a classification of the clinical endpoints, we calculated the entropy, defined as the measure of impurity, following the formula: where is the probability of class j.…”

The Immune Signature of CSF in Multiple Sclerosis with and without Oligoclonal Bands: A Machine Learning Approach to Proximity Extension Assay Analysis

“…This innovative approach enhances the precision of biomarker exploration. (iii) To interpret the complexity of data generated by PEA, we applied a machine learning statistical approach that enhances the robustness of our findings [ 41 ], and we built training and validation sets to test the accuracy of biomarkers in discriminating between groups.…”

Examining electroencephalogram signatures of people with multiple sclerosis using a nonlinear dynamics approach: a systematic review and bibliographic analysis

“…Among all the neuroimaging methods, MRI is currently the most widely used in MS diagnosis. Although it can be a useful technique, MRI does not correspond well with clinical manifestations of disease, and it is invasive, expensive, and time-consuming ( Hossain et al, 2022 ). Aside from considering initial symptoms, past neurological disorders, medical conditions, etc., other methods for diagnosing MS include cerebrospinal fluid (CSF) analysis, evoked potential (EP), and blood samples analysis ( Ghasemi et al, 2017 ).…”