Predicting Multiple Sclerosis: Challenges and Opportunities

Shifting our attention earlier in the multiple sclerosis disease course

PURPOSE OF REVIEW

Revisions of multiple sclerosis (MS) diagnostic criteria enable clinicians to diagnose patients earlier in the biologic disease course. Prompt initiation of therapy correlates with improved clinical outcomes. This has led to increased attention on the earliest stages of MS, including the MS prodrome and radiologically isolated syndrome (RIS). Here, we review current understanding and approach to patients with preclinical MS.

RECENT FINDINGS

MS disease biology often begins well before the onset of typical MS symptoms, and we are increasingly able to recognize preclinical and prodromal stages of MS. RIS represents the best characterized aspect of preclinical MS, and its diagnostic criteria were recently revised to better capture patients at highest risk of conversion to clinical MS. The first two randomized control trials evaluating disease modifying therapy use in RIS also found that treatment could delay or prevent onset of clinical disease.

SUMMARY

Despite progress in our understanding of the earliest stages of the MS disease course, additional research is needed to systematically identify patients with preclinical MS as well as capture those at risk for developing clinical disease. Recent data suggests that preventive immunomodulatory therapies may be beneficial for high-risk patients with RIS; though management remains controversial.

Explainable machine learning for predicting conversion to neurological disease: Results from 52,939 medical records

Objective

This study assesses the application of interpretable machine learning modeling using electronic medical record data for the prediction of conversion to neurological disease.

Methods

A retrospective dataset of Cleveland Clinic patients diagnosed with Alzheimer's disease, amyotrophic lateral sclerosis, multiple sclerosis, or Parkinson's disease, and matched controls based on age, sex, race, and ethnicity was compiled. Individualized risk prediction models were created using eXtreme Gradient Boosting for each neurological disease at four timepoints in patient history. The prediction models were assessed for transparency and fairness.

Results

At timepoints 0-months, 12-months, 24-months, and 60-months prior to diagnosis, Alzheimer's disease models achieved the area under the receiver operating characteristic curve on a holdout test dataset of 0.794, 0.742, 0.709, and 0.645; amyotrophic lateral sclerosis of 0.883, 0.710, 0.658, and 0.620; multiple sclerosis of 0.922, 0.877, 0.849, and 0.781; and Parkinson's disease of 0.809, 0.738, 0.700, and 0.651, respectively.

Conclusions

The results demonstrate that electronic medical records contain latent information that can be used for risk stratification for neurological disorders. In particular, patient-reported outcomes, sleep assessments, falls data, additional disease diagnoses, and longitudinal changes in patient health, such as weight change, are important predictors.

Decision trees to evaluate the risk of developing multiple sclerosis

Introduction

Multiple sclerosis (MS) is a persistent neurological condition impacting the central nervous system (CNS). The precise cause of multiple sclerosis is still uncertain; however, it is thought to arise from a blend of genetic and environmental factors. MS diagnosis includes assessing medical history, conducting neurological exams, performing magnetic resonance imaging (MRI) scans, and analyzing cerebrospinal fluid. While there is currently no cure for MS, numerous treatments exist to address symptoms, decelerate disease progression, and enhance the quality of life for individuals with MS.

Methods

This paper introduces a novel machine learning (ML) algorithm utilizing decision trees to address a key objective: creating a predictive tool for assessing the likelihood of MS development. It achieves this by combining prevalent demographic risk factors, specifically gender, with crucial immunogenetic risk markers, such as the alleles responsible for human leukocyte antigen (HLA) class I molecules and the killer immunoglobulin-like receptors (KIR) genes responsible for natural killer lymphocyte receptors.

Results

The study included 619 healthy controls and 299 patients affected by MS, all of whom originated from Sardinia. The gender feature has been disregarded due to its substantial bias in influencing the classification outcomes. By solely considering immunogenetic risk markers, the algorithm demonstrates an ability to accurately identify 73.24% of MS patients and 66.07% of individuals without the disease.

Discussion

Given its notable performance, this system has the potential to support clinicians in monitoring the relatives of MS patients and identifying individuals who are at an increased risk of developing the disease.

Polygenic risk score prediction of multiple sclerosis in individuals of South Asian ancestry

Polygenic risk scores aggregate an individual's burden of risk alleles to estimate the overall genetic risk for a specific trait or disease. Polygenic risk scores derived from genome-wide association studies of European populations perform poorly for other ancestral groups. Given the potential for future clinical utility, underperformance of polygenic risk scores in South Asian populations has the potential to reinforce health inequalities. To determine whether European-derived polygenic risk scores underperform at multiple sclerosis prediction in a South Asian-ancestry population compared with a European-ancestry cohort, we used data from two longitudinal genetic cohort studies: Genes & Health (2015-present), a study of ∼50 000 British-Bangladeshi and British-Pakistani individuals, and UK Biobank (2006-present), which is comprised of ∼500 000 predominantly White British individuals. We compared individuals with and without multiple sclerosis in both studies (Genes & Health: N Cases = 42, N Control = 40 490; UK Biobank: N Cases = 2091, N Control = 374 866). Polygenic risk scores were calculated using clumping and thresholding with risk allele effect sizes obtained from the largest multiple sclerosis genome-wide association study to date. Scores were calculated with and without the major histocompatibility complex region, the most influential locus in determining multiple sclerosis risk. Polygenic risk score prediction was evaluated using Nagelkerke's pseudo-R 2 metric adjusted for case ascertainment, age, sex and the first four genetic principal components. We found that, as expected, European-derived polygenic risk scores perform poorly in the Genes & Health cohort, explaining 1.1% (including the major histocompatibility complex) and 1.5% (excluding the major histocompatibility complex) of disease risk. In contrast, multiple sclerosis polygenic risk scores explained 4.8% (including the major histocompatibility complex) and 2.8% (excluding the major histocompatibility complex) of disease risk in European-ancestry UK Biobank participants. These findings suggest that polygenic risk score prediction of multiple sclerosis based on European genome-wide association study results is less accurate in a South Asian population. Genetic studies of ancestrally diverse populations are required to ensure that polygenic risk scores can be useful across ancestries.

Multiple sclerosis risk variants influence the peripheral B-cell compartment early in life in the general population

BACKGROUND AND PURPOSE

Multiple sclerosis (MS) is associated with abnormal B-cell function, and MS genetic risk alleles affect multiple genes that are expressed in B cells. However, how these genetic variants impact the B-cell compartment in early childhood is unclear. In the current study, we aim to assess whether polygenic risk scores (PRSs) for MS are associated with changes in the blood B-cell compartment in children from the general population.

METHODS

Six-year-old children from the population-based Generation R Study were included. Genotype data were used to calculate MS-PRSs and B-cell subset-enriched MS-PRSs, established by designating risk loci based on expression and function. Analyses of variance were performed to examine the effect of MS-PRSs on total B-cell numbers (n = 1261) as well as naive and memory subsets (n = 675).

RESULTS

After correction for multiple testing, no significant associations were observed between MS-PRSs and total B-cell numbers and frequencies of subsets therein. A naive B-cell-MS-PRS (n = 26 variants) was significantly associated with lower relative, but not absolute, naive B-cell numbers (p = 1.03 × 10^-4 and p = 0.82, respectively), and higher frequencies and absolute numbers of CD27⁺ memory B cells (p = 8.83 × 10^-4 and p = 4.89 × 10^-3 , respectively). These associations remained significant after adjustment for Epstein-Barr virus seropositivity and the HLA-DRB1*15:01 genotype.

CONCLUSIONS

The composition of the blood B-cell compartment is associated with specific naive B-cell-associated MS risk variants during childhood, possibly contributing to MS pathophysiology later in life. Cell subset-specific PRSs may offer a more sensitive tool to define the impact of genetic risk on the immune system in diseases such as MS.

Addressing the Challenges and Barriers to the Integration of Machine Learning into Clinical Practice: An Innovative Method to Hybrid Human-Machine Intelligence

Machine learning (ML) models have proven their potential in acquiring and analyzing large amounts of data to help solve real-world, complex problems. Their use in healthcare is expected to help physicians make diagnoses, prognoses, treatment decisions, and disease outcome predictions. However, ML solutions are not currently deployed in most healthcare systems. One of the main reasons for this is the provenance, transparency, and clinical utility of the training data. Physicians reject ML solutions if they are not at least based on accurate data and do not clearly include the decision-making process used in clinical practice. In this paper, we present a hybrid human-machine intelligence method to create predictive models driven by clinical practice. We promote the use of quality-approved data and the inclusion of physician reasoning in the ML process. Instead of training the ML algorithms on the given data to create predictive models (conventional method), we propose to pre-categorize the data according to the expert physicians' knowledge and experience. Comparing the results of the conventional method of ML learning versus the hybrid physician-algorithm method showed that the models based on the latter can perform better. Physicians' engagement is the most promising condition for the safe and innovative use of ML in healthcare.

Genetics of multiple sclerosis: lessons from polygenicity

Large-scale mapping studies have identified 236 independent genetic variants associated with an increased risk of multiple sclerosis. However, none of these variants are found exclusively in patients with multiple sclerosis. They are located throughout the genome, including 32 independent variants in the MHC and one on the X chromosome. Most variants are non-coding and seem to act through cell-specific effects on gene expression and splicing. The likely functions of these variants implicate both adaptive and innate immune cells in the pathogenesis of multiple sclerosis, provide pivotal biological insight into the causes and mechanisms of multiple sclerosis, and some of the variants implicated in multiple sclerosis also mediate risk of other autoimmune and inflammatory diseases. Genetics offers an approach to showing causality for environmental factors, through Mendelian randomisation. No single variant is necessary or sufficient to cause multiple sclerosis; instead, each increases total risk in an additive manner. This combined contribution from many genetic factors to disease risk, or polygenicity, has important consequences for how we interpret the epidemiology of multiple sclerosis and how we counsel patients on risk and prognosis. Ongoing efforts are focused on increasing cohort sizes, increasing diversity and detailed characterisation of study populations, and translating these associations into an understanding of the biology of multiple sclerosis.