Multiple sclerosis risk factors contribute to onset heterogeneity

An analytical review on the use of artificial intelligence and machine learning in diagnosis, prediction, and risk factor analysis of multiple sclerosis

Medical research offers potential for disease prediction, like Multiple Sclerosis (MS). This neurological disorder damages nerve cell sheaths, with treatments focusing on symptom relief. Manual MS detection is time-consuming and error prone. Though MS lesion detection has been studied, limited attention has been paid to clinical analysis and computational risk factor prediction. Artificial intelligence (AI) techniques and Machine Learning (ML) methods offer accurate and effective alternatives to mapping MS progression. However, there are challenges in accessing clinical data and interdisciplinary collaboration. By analyzing 103 papers, we recognize the trends, strengths and weaknesses of AI, ML, and statistical methods applied to MS diagnosis. AI/ML-based approaches are suggested to identify MS risk factors, select significant MS features, and improve the diagnostic accuracy, such as Rule-based Fuzzy Logic (RBFL), Adaptive Fuzzy Inference System (ANFIS), Artificial Neural Network methods (ANN), Support Vector Machine (SVM), and Bayesian Networks (BNs). Meanwhile, applications of the Expanded Disability Status Scale (EDSS) and Magnetic Resonance Imaging (MRI) can enhance MS diagnostic accuracy. By examining established risk factors like obesity, smoking, and education, some research tackled the issue of disease progression. The performance metrics varied across different aspects of MS studies: Diagnosis: Sensitivity ranged from 60 % to 98 %, specificity from 60 % to 98 %, and accuracy from 61 % to 97 %. Prediction: Sensitivity ranged from 76 % to 98 %, specificity from 65 % to 98 %, and accuracy from 62 % to 99 %. Segmentation: Accuracy ranged up to 96.7 %. Classification: Sensitivity ranged from 78 % to 97.34 %, specificity from 65 % to 99.32 %, and accuracy from 71 % to 97.94 %. Furthermore, the literature shows that combining techniques can improve efficiency, exploiting their strengths for better overall performance.

Explainable machine learning on baseline MRI predicts multiple sclerosis trajectory descriptors

Multiple sclerosis (MS) is a multifaceted neurological condition characterized by challenges in timely diagnosis and personalized patient management. The application of Artificial Intelligence (AI) to MS holds promises for early detection, accurate diagnosis, and predictive modeling. The objectives of this study are: 1) to propose new MS trajectory descriptors that could be employed in Machine Learning (ML) regressors and classifiers to predict patient evolution; 2) to explore the contribution of ML models in discerning MS trajectory descriptors using only baseline Magnetic Resonance Imaging (MRI) studies. This study involved 446 MS patients who had a baseline MRI, at least two measurements of Expanded Disability Status Scale (EDSS), and a 1-year follow-up. Patients were divided into two groups: 1) for model development and 2) for evaluation. Three descriptors: β1, β2, and EDSS(t), were related to baseline MRI parameters using regression and classification XGBoost models. Shapley Additive Explanations (SHAP) analysis enhanced model transparency by identifying influential features. The results of this study demonstrate the potential of AI in predicting MS progression using the proposed patient trajectories and baseline MRI scans, outperforming classic Multiple Linear Regression (MLR) methods. In conclusion, MS trajectory descriptors are crucial; incorporating AI analysis into MRI assessments presents promising opportunities to advance predictive capabilities. SHAP analysis enhances model interpretation, revealing feature importance for clinical decisions.

Adaptive and Innate Immunity Are Key Drivers of Age at Onset of Multiple Sclerosis

Background and Objectives

Multiple sclerosis (MS) age at onset (AAO) is a clinical predictor of long-term disease outcomes, independent of disease duration. Little is known about the genetic and biological mechanisms underlying age of first symptoms. We conducted a genome-wide association study (GWAS) to investigate associations between individual genetic variation and the MS AAO phenotype.

Methods

The study population was comprised participants with MS in 6 clinical trials: ADVANCE (N = 655; relapsing-remitting [RR] MS), ASCEND (N = 555; secondary-progressive [SP] MS), DECIDE (N = 1,017; RRMS), OPERA1 (N = 581; RRMS), OPERA2 (N = 577; RRMS), and ORATORIO (N = 529; primary-progressive [PP] MS). Altogether, 3,905 persons with MS of European ancestry were analyzed. GWAS were conducted for MS AAO in each trial using linear additive models controlling for sex and 10 principal components. Resultant summary statistics across the 6 trials were then meta-analyzed, for a total of 8.3 × 10-6 single nucleotide polymorphisms (SNPs) across all trials after quality control and filtering for heterogeneity. Gene-based tests of associations, pathway enrichment analyses, and Mendelian randomization analyses for select exposures were also performed.

Results

Four lead SNPs within 2 loci were identified (p < 5 × 10-8), including a) 3 SNPs in the major histocompatibility complex and their effects were independent of HLA-DRB1*15:01 and b) a LOC105375167 variant on chromosome 7. At the gene level, the top association was HLA-C (p = 1.2 × 10-7), which plays an important role in antiviral immunity. Functional annotation revealed the enrichment of pathways related to T-cell receptor signaling, autoimmunity, and the complement cascade. Mendelian randomization analyses suggested a link between both earlier age at puberty and shorter telomere length and earlier AAO, while there was no evidence for a role for either body mass index or vitamin D levels.

Discussion

Two genetic loci associated with MS AAO were identified, and functional annotation demonstrated an enrichment of genes involved in adaptive and complement immunity. There was also evidence supporting a link with age at puberty and telomere length. The findings suggest that AAO in MS is multifactorial, and the factors driving onset of symptoms overlap with those influencing MS risk.

Pediatric Onset Multiple Sclerosis and Obesity: Defining the Silhouette of Disease Features in Overweight Patients

Obesity has been suggested as an environmental risk factor for multiple sclerosis (MS) and may negatively effect the progression of the disease. The aim of this study is to determine any correlation between overweight/obesity and the clinical and neuroradiological features at the onset of pediatric onset multiple sclerosis (POMS). Were included patients referred to the POMS Unit of the Bambino Gesù Children's Hospital between June 2012 and June 2021. The diagnosis of MS with an onset of less than 18 years was required. For all included subjects, we considered for the analysis the following data at the onset of symptoms: general data (age, sex, functional system compromised by neurological signs, weight and height), brain and spinal magnetic resonance imaging (MRI), cerebrospinal fluid exams. We identified 55 pediatric cases of POMS and divided them into two groups according to the body mass index (BMI): 60% were healthy weight (HW) and 40% were overweight/obese (OW/O). OW/O patients experienced a two-year age difference in disease onset compared to the HW patients (12.7 ± 3.8 years vs. 14.6 ± 4.1 years; p < 0.05). Onset of polyfocal symptoms was seen more frequently in OW/O patients than in HW (72.7% vs. 21.2%; p < 0.05). The pyramidal functions were involved more frequently in the OW/O group than in the HW group (50% vs. 25%; p < 0.005). Black holes were detected more frequently in OW/O patients in onset MRI scans compared to the HW group (50% vs. 15.5%; p < 0.05). Our findings suggest that being overweight/obese affects the risk of developing MS at an earlier age and is associated with an unfavorable clinical-radiological features at onset. Weight control can be considered as a preventive/therapeutic treatment.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

The effects of different types of smoking on recovery from attack in hospitalized multiple sclerosis patients

BACKGROUND

Several studies demonstrated the association between tobacco smoking and higher risk and increased progression of multiple sclerosis (MS). Data about the effect of smoking during the recovery from MS attacks is limited. Furthermore, different types of tobacco exposures such as water pipe and passive smoking are not well assessed separately. So this study evaluated the effect of different types of smokes, cigarette and water pipe as well as passive smoking on the function recovery of relapsing-remitting MS (RRMS) attacks METHODS: This cohort study evaluated the adult patients with RRMS and Expanded Disability Status Scale (EDSS) < 5 in the attack phase. Patients were divided into two groups: smokers and non-smokers. The smokers included those who use cigarette, water pipe as well as passive smokers as subgroups for more analyses later. EDSS was monitored after relapse and two months after relapse. Change of EDSS considered as the criteria for functional recovery. The correlation between the amount of consumption and disability level was assessed among smokers by Pearson's correlation test. While, the difference of EDSS between smoker and non-smoker were assessed by Independent samples T-test.

RESULTS

142 patients were evaluated. 79 (55.6%) were smokers (43% male) while 63 (44.4%) were non-smokers (36.5% male). There was a statistically significant difference in change of EDSS between smoker and non-smoker groups, which change of EDSS was higher in non-smoker (-2.62 ± 0.90 non-smoker vs. -1.75 ± 0.76 smoker, P < 0.001). Also, only there was a significantly lesser decline in EDSS after two months in the cigarette smokers in subgroups analyses (P < 0.001). A correlation analysis revealed a significant positive correlation between the number per day of cigarette smoking and EDSS after relapse (r = 0.3, P = 0.03) and a significant positive correlation between minutes per month of smoking of water pipe and EDSS two months after relapse (r = ‎0.6‎‎, P > 0.001).

CONCLUSION

Tobacco smoking especially cigarette smoking is associated with a negative effect on recovery from the attack in patients with RRMS.

Assessing the utility of magnetic resonance imaging-based "SuStaIn" disease subtyping for precision medicine in relapsing-remitting and secondary progressive multiple sclerosis

BACKGROUND

Patient stratification and individualized treatment decisions based on multiple sclerosis (MS) clinical phenotypes are arbitrary. Subtype and Staging Inference (SuStaIn), a published machine learning algorithm, was developed to identify data-driven disease subtypes with distinct temporal progression patterns using brain magnetic resonance imaging; its clinical utility has not been assessed. The objective of this study was to explore the prognostic capability of SuStaIn subtyping and whether it is a useful personalized predictor of treatment effects of natalizumab and dimethyl fumarate.

METHODS

Subtypes were available from the trained SuStaIn model for 3 phase 3 clinical trials in relapsing-remitting and secondary progressive MS. Regression models were used to determine whether baseline SuStaIn subtypes could predict on-study clinical and radiological disease activity and progression. Differences in treatment responses relative to placebo between subtypes were determined using interaction terms between treatment and subtype.

RESULTS

Natalizumab and dimethyl fumarate reduced inflammatory disease activity in all SuStaIn subtypes (all p < 0.001). SuStaIn MS subtyping alone did not discriminate responder heterogeneity based on new lesion formation and disease progression (p > 0.05 across subtypes).

CONCLUSION

SuStaIn subtypes correlated with disease severity and functional impairment at baseline but were not predictive of disability progression and could not discriminate treatment response heterogeneity.

Trends in the environmental risks associated with earlier onset in multiple sclerosis

BACKGROUND

Several environmental and lifestyle factors relating to sunlight/vitamin D, body mass index (BMI), and smoking are associated with the risk of developing multiple sclerosis (MS). However, their relation to disease progression, particularly age at symptomatic onset, remains inconsistent, which may be the result of significant changes in human-environment interactions over the last century. This study investigates historical trends in the association between common MS environmental risk factors and age at disease onset.

METHODS

Using a narrative approach, we evaluated the current literature for published studies assessing the association between vitamin-D, BMI, and tobacco smoking exposures with the risk of early/pediatric-onset MS and direct correlations with age at MS onset using MEDLINE, EMBASE, and Web of Science. Measures were plotted by the average calendar year of disease onset for each cohort to examine trends over time. In total, 25, 9, and 11 articles were identified for vitamin D, BMI, and smoking-related exposures, respectively.

RESULTS

Higher sun exposure habits and residential solar radiation were associated with older age at onset. On the contrary, two studies observed a negative correlation between age at onset and serum 25-hydroxyvitamin D (25(OH)D) levels. Higher adolescent BMI was generally associated with younger age at onset, although genetic susceptibility for childhood obesity was not significantly associated. Tobacco smoking was associated with later disease onset, despite being a risk factor for MS. Association with age at onset was inflated for more recent studies relating to smoking, while often weaker for serum vitamin D and BMI.

CONCLUSION

Current findings indicate a likely association between age at onset and environmental risk factors, such as sun exposure, adolescent BMI, and tobacco smoking, in certain populations. However, findings are often inconsistent and assessment of the relationships and potential changes over time require further investigation.

The age at onset of relapsing-remitting multiple sclerosis has increased over the last five decades

BACKGROUND

Patients with relapsing-remitting multiple sclerosis (RRMS) most commonly experience their first symptoms between 20 and 40 years of age. The objective of this study was to investigate how the age at which the first symptoms of RRMS occur has changed over the past decades.

METHODS

Patients who were followed up in our unit after an initial diagnosis of RRMS using the Poser or McDonald criteria and who experienced their first symptoms between January 1970 and December 2019 were included in the study. The cohort was divided into five groups according to the decade in which the first symptoms appeared. The age at disease onset was compared across decades. Changes in age were also determined after excluding patients with early-onset disease (<18 years of age) and those with late-onset disease (>50 years of age) to avoid bias.

RESULTS

The cohort included 1,622 patients with RRMS, 67.6% of whom were women. Among them, 5.9% and 4% had early-onset and late-onset disease, respectively. The mean age ± standard deviation at onset was 31.11 ± 9.82 years, with no differences between men and women. The mean ages at onset were 23.79 ± 10.19 years between 1970 and 1979, 27.86 ± 9.22 years between 1980 and 1989, 30.07 ± 9.32 years between 1990 and 1999, 32.12 ± 9.47 between 2000 and 2009, and 34.28 ± 9.83 years between 2010 and 2019. The ages at disease onset were progressively higher in the later decades; this trend was statistically significant (p < 0.001), with a Pearson linear correlation coefficient R of 0.264 and R² of 0.070 (p < 0.001). The results were similar when analysing men and women separately. We conducted an analysis of 1,460 patients (mean age at onset: 31.10 ± 7.99 years), after excluding patients with early-onset and late-onset disease. In this specific subgroup, the mean ages at disease onset were 28.38 ± 8.17 years between 1970 and 1979, 29.22 ± 7.51 years between 1980 and 1989, 30.06 ± 8.02 years between 1990 and 1999, 31.46 ± 7.77 years between 2000 and 2009, and 33.37 ± 7.97 years between 2010 and 2019. The trend was also statistically significant (p < 0.001), with a Pearson linear correlation coefficient R of 0.193 and R² of 0.037 (p < 0.001).

CONCLUSION

Our data showed that the age at RRMS onset has increased over the past decades.

Smoking and younger age at onset in anti-acetylcholine receptor antibody-positive myasthenia gravis

Smoking is a known risk factor for the development and progression of several autoimmune diseases. Previous studies have pointed out the association of smoking with the development and worsening of symptoms in myasthenia gravis (MG), but further investigation is necessary to confirm this association. Smoking history was investigated in a cross-sectional study of 139 patients with anti-acetylcholine receptor antibody-positive MG, and the association of smoking history with the age at the onset of MG was analyzed. Patients who had been smoking at the onset of MG were significantly younger compared with those who had never smoked or had quit before the onset of MG. A linear regression analysis adjusting for sex and the presence/absence of thymoma showed a significant association between smoking at onset and younger age at onset (regression coefficient -9.05; 95% confidence interval, -17.6, -0.51; p = 0.039). Among patients with smoking exposure within 10 years prior to or at the onset of MG, women were significantly younger at the onset of MG compared with men. Our results suggest that smoking is an independent risk factor for the earlier development of anti-acetylcholine receptor antibody-positive MG and further support the putative link between smoking and MG.

The association between hope and employment among individuals with multiple sclerosis: A hierarchical logistic regression model

BACKGROUND

Most people with multiple sclerosis (MS) are employed at the time of their diagnosis; however, due to the unpredictable nature of MS, most exit the workforce shortly thereafter. A plethora of research has examined factors that negatively affect employment outcomes for people with MS. However, little is known about how hope, a modifiable positive psychology factor, affects employment.

OBJECTIVE

This study examined the role of hope and its association with employment outcomes for people with MS.

METHODS

Two-hundred and fifty-five adults with MS (mean ± SD age, 45.45 years ± 10.28) completed surveys about their MS, employment, disability-related stress, and hope. A three-step hierarchical logistic regression was conducted to examine the extent to which hope explains the variance in employment, over and above demographic and disability related covariates.

RESULTS

The final model explained 28% of the variance in employment, suggesting that the model was able to distinguish people with MS who were employed versus those who were unemployed. Higher levels of hope were associated with an increased probability of being employed (OR = 4.65; 95% CI [1.98, 10.92]).

CONCLUSION

This study supports that hope is associated with favorable employment outcomes for people with MS. Persons with MS may benefit from working with rehabilitation professionals to enhance their hope, and this study provides a foundation for the development of hope-based interventions to improve employment outcomes among this population.

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

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.

Environmental risk factors in multiple sclerosis: bridging Mendelian randomization and observational studies

Multiple sclerosis (MS) is a complex disease with both genetic variants and environmental factors involved in disease susceptibility. The main environmental risk factors associated with MS in observational studies include obesity, vitamin D deficiency, Epstein-Barr virus infection and smoking. As modifying these environmental and lifestyle factors may enable prevention, it is important to pinpoint causal links between these factors and MS. Leveraging genetics through the Mendelian randomization (MR) paradigm is an elegant way to inform prevention strategies in MS. In this review, we summarize MR studies regarding the impact of environmental factors on MS susceptibility, thereby paying attention to quality criteria which will aid readers in interpreting any MR studies. We draw parallels and differences with observational studies and randomized controlled trials and look forward to the challenges that such work presents going forward.

Genetics and functional genomics of multiple sclerosis

Multiple sclerosis (MS) is an inflammatory neurodegenerative disease with genetic predisposition. Over the last decade, genome-wide association studies with increasing sample size led to the discovery of robustly associated genetic variants at an exponential rate. More than 200 genetic loci have been associated with MS susceptibility and almost half of its heritability can be accounted for. However, many challenges and unknowns remain. Definitive studies of disease progression and endophenotypes are yet to be performed, whereas the majority of the identified MS variants are not yet functionally characterized. Despite these shortcomings, the unraveling of MS genetics has opened up a new chapter on our understanding MS causal mechanisms.

A higher burden of multiple sclerosis genetic risk confers an earlier onset

BACKGROUND

Age at onset of multiple sclerosis (MS) is an objective, influential predictor of the evolution of MS independent of disease duration.

OBJECTIVES

Determine the influence of MS genetic predisposition on age of onset.

METHODS

We conducted a comprehensive investigation of MS risk variants and age at onset in 3495 non-Latinx white individuals, including for combinations of HLA-DRB1*15:01 alleles and quintiles of an unweighted genetic risk score (GRS) for 198 of 200 autosomal MS risk variants that reside outside the major histocompatibility complex.

RESULTS

The mean age at onset was 32 years, 29% were male, and 46% were HLA-DRB1*15:01 carriers. For those with the greatest genetic risk burden (the highest GRS quintile with two HLA-DRB1*15:01 alleles) were on average 5 years younger at onset (p = 0.002) than those with the lowest genetic risk burden (the lowest GRS quintile with no HLA-DRB1*15:01 alleles). There was a strong inverse relationship between the MS genetic risk burden and age at onset of MS (p < 5 × 10^-8).

CONCLUSION

We demonstrate a significant gradient between elevated MS genetic risk burden and an earlier onset of MS, suggesting that a higher MS genetic risk burden accelerates onset of the disease.

Associations between smoking and walking, fatigue, depression, and health-related quality of life in persons with multiple sclerosis

Smoking is associated with increased multiple sclerosis (MS) risk. In addition, some studies have reported that smoking is associated with anxiety and depression. However, the associations between smoking, walking, and fatigue are needed to be investigated. The objective was to investigate the associations between cigarette smoking and walking, fatigue, depression symptom severity, and health-related quality of life in persons with MS. Two hundred seventy-nine persons with MS were evaluated in this cross-sectional study. Study outcomes were neurological disability level, walking speed, walking endurance, perceived walking impact of MS, fatigue, depression symptom severity, and health-related quality of life. There were 95 (34.1%) current smokers who had significantly higher fatigue (p = 0.003, pη² = 0.031) and depression (p = 0.044, pη² = 0.015), and lower health-related quality of life (p = 0.003, pη² = 0.031) after adjusting for age, gender, neurological disability level, and disease duration compared to non-smokers (n = 184). There was no significant difference between smokers and non-smokers in walking measures (p > 0.05). Smoking intensity was significantly correlated with age (r = 0.487), neurological disability level (r = 0.227), disease duration (r = 0.30), walking speed (r = 0.574), walking endurance (r =  - 0.461), perceived walking impact of MS (r = 0.684), fatigue (r = 0.370), health-related quality of life (r =  - 0.259), and depression (r = 0.269) in current smokers. Cigarette smokers with MS had significantly more fatigue and depression symptom severity and less health-related quality of life compared to non-smokers. Increased pack-years of cigarette smoking was associated with worse walking ability and health-related quality of life, and greater depression symptom severity and fatigue.

Onset Symptom Clusters in Multiple Sclerosis: Characteristics, Comorbidities, and Risk Factors

Background: Multiple sclerosis (MS) symptoms are expected to aggregate in specific patterns across different stages of the disease. Here, we studied the clustering of onset symptoms and examined their characteristics, comorbidity patterns and associations with potential risk factors.

Methods: Data stem from the Swiss Multiple Sclerosis Registry, a prospective study including 2,063 participants by November 2019. MS onset symptoms were clustered using latent class analysis (LCA). The latent classes were further examined using information on socio-demographic characteristics, MS-related features, potential risk factors, and comorbid diseases.

Results: The LCA model with six classes (frequencies ranging from 12 to 24%) was selected for further analyses. The latent classes comprised a multiple symptoms class with high probabilities across several symptoms, contrasting with two classes with solitary onset symptoms: vision problems and paresthesia. Two gait classes emerged between these extremes: the gait-balance class and the gait-paralysis class. The last class was the fatigue-weakness-class, also accompanied by depression symptoms, memory, and gastro-intestinal problems. There was a moderate variation by sex and by MS types. The multiple symptoms class yielded increased comorbidity with other autoimmune disorders. Similar to the fatigue-weakness class, the multiple symptoms class showed associations with angina, skin diseases, migraine, and lifetime prevalence of smoking. Mononucleosis was more frequently reported in the fatigue-weakness and the paresthesia class. Familial aggregation did not differ among the classes.

Conclusions: Clustering of MS onset symptoms provides new perspectives on the heterogeneity of MS. The clusters comprise different potential risk factors and comorbidities. They point toward different risk mechanisms.

The global prevalence of familial multiple sclerosis: an updated systematic review and meta-analysis

BACKGROUND

Considering that many recent studies have reported the prevalence of familial multiple sclerosis (FMS), we performed an updated meta-analysis of the worldwide prevalence of FMS by the addition of recent publications.

METHODS

A search in PubMed, Scopus, the ISI Web of Science, and Google Scholar was undertaken up to 20 December 2020. The inclusion criteria were based on the CoCoPop approach (condition, context, and population). Meta-analysis of the qualified studies was conducted by comprehensive meta-analysis ver. 2 software.

RESULTS

The pooled prevalence of MS in relatives of 16,179 FMS cases was estimated to be 11.8% (95% CI: 10.7-13) based on a random-effects model. The pooled mean age of disease onset in adult probands was calculated to be 28.7 years (95% CI: 27.2 ± 30.2). Regarding 13 studies that reported the data of FMS in pediatrics (n = 877) and adults (n = 6636), the FMS prevalence in pediatrics and adults was 15.5% (95% CI: 13.8-17.4) and 10.8% (95% CI: 8.1-14.2), respectively. The prevalence of FMS in affected males (n = 5243) and females (n = 11,503) was calculated to be 13.7% (95% CI: 10.1-18.2) and 15.4% (95% CI: 10.3-22.4), respectively. The odds ratio of male/female in FMS cases was not statistically significant (OR = 0.9; 95% CI: 0.6-1.2, P = 0.55). Subgroup analysis demonstrated a significant difference in the prevalence of FMS between the geographical areas (P = 0.007). The meta-regression model indicated that the prevalence of FMS is lower with higher latitude and higher MS prevalence (P < 0.001). In contrast, meta-regression based on prevalence day was not statistically significant (P = 0.29).

CONCLUSIONS

The prevalence of FMS is higher in the pediatric group than that of adults, distinct between geographical areas, and diminishes with the increment of MS prevalence and latitude. Also, the symptoms initiate relatively at younger ages in the FMS cases. Interestingly, our analysis unveiled that FMS is not more prevalent in men than women and the risk of MS development in relatives is not higher when the affected proband is male.

Monomethyl Fumarate (MMF, Bafiertam) for the Treatment of Relapsing Forms of Multiple Sclerosis (MS)

Multiple sclerosis (MS) is a prevalent neurologic autoimmune disorder affecting two million people worldwide. Symptoms include gait abnormalities, perception and sensory losses, cranial nerve pathologies, pain, cognitive dysfunction, and emotional aberrancies. Traditional therapy includes corticosteroids for the suppression of relapses and injectable interferons. Recently, several modern therapies-including antibody therapy and oral agents-were approved as disease-modifying agents. Monomethyl fumarate (MMF, Bafiertam) is a recent addition to the arsenal available in the fight against MS and appears to be well-tolerated, safe, and effective. In this paper, we review the evidence available regarding the use of monomethyl fumarate (Bafiertam) in the treatment of relapsing-remitting MS.

Integrating patient-reported outcomes and quantitative timed tasks to identify relapsing remitting multiple sclerosis patient subgroups: a latent profile analysis

BACKGROUND

Multiple sclerosis (MS) patients experience wide-ranging symptoms with varied severity, and approaches that integrate patient-reported outcomes and objective quantitative measures will present opportunities for advancing clinical profiling. The primary objective of the current study was to conduct exploratory data analysis using latent variable modeling to empirically identify clusters of relapsing remitting (RR) MS patients with shared impairment patterns across three patient-reported outcomes and two timed task measures.

METHODS

Latent profile analyses and impairment data for 2,012 RRMS patients identified distinct patient clusters using timed task measures of upper and lower limb performance, and patient-reported outcomes measuring quality of life, depression symptom severity, and perceived global disability. Multinomial logistic regression models were used to characterize associations between socio-demographic attributes and assignment to the patient clusters.

RESULTS

There were 6 distinct clusters of RRMS patients that differed by symptom patterns, and by their socio-demographic attributes. Most notable were were no differences in age, sex, or disease duration between the least and most impaired classes, representing 14% and 4% of patients, respectively. Patients in the most impaired class were much more likely to be Black American, have a history of smoking, have a higher body mass index, and be of lower socioeconomic status than the least impaired class. There were positive relationships between age and classification to clusters of increasing moderately severe impairment but not the most severe clusters.

CONCLUSION

We present a framework for discerning phenotypic impairment clusters in RRMS. The results demonstrate opportunities for advancing clinical profiling, which is necessary for optimizing personalized MS care models and clinical research.

Neurocognitive impairment and social cognition in multiple sclerosis

PURPOSE/AIM OF THE STUDY

The impairment of neurocognitive functions occurs in all subtypes of multiple sclerosis, even from the earliest stages of the disease. Commonly reported manifestations of cognitive impairment include deficits in attention, conceptual reasoning, processing efficiency, information processing speed, memory (episodic and working), verbal fluency (language), and executive functions. Multiple sclerosis patients also suffer from social cognition impairment, which affects their social functioning. The objective of the current paper is to assess the effect of neurocognitive impairment and its potential correlation with social cognition performance and impairment in multiple sclerosis patients.

MATERIALS AND METHODS

An overview of the available-to-date literature on neurocognitive impairment and social cognition performance in multiple sclerosis patients by disease subtype was performed.

RESULTS

It is not clear if social cognition impairment occurs independently or secondarily to neurocognitive impairment. There are associations of variable strengths between neurocognitive and social cognition deficits and their neural basis is increasingly investigated.

CONCLUSIONS

The prompt detection of neurocognitive predictors of social cognition impairment that may be applicable to all multiple sclerosis subtypes and intervention are crucial to prevent further neural and social cognition decline in multiple sclerosis patients.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

A new clustering method identifies multiple sclerosis-specific T-cell receptors

OBJECTIVE

To characterize T-cell receptors (TCRs) and identify target epitopes in multiple sclerosis (MS).

METHODS

Peripheral blood mononuclear cells were obtained from 39 MS patients and 19 healthy controls (HCs). TCR repertoires for α/β/δ/γ chains, TCR diversity, and V/J usage were determined by next-generation sequencing. TCR β chain repertoires were compared with affectation status using a novel clustering method, Grouping of Lymphocyte Interactions by Paratope Hotspots (GLIPH). Cytomegalovirus (CMV)-IgG was measured in an additional 113 MS patients and 93 HCs. Regulatory T cells (Tregs) were measured by flow cytometry.

RESULTS

TCR diversity for all four chains decreased with age. TCRα and TCRβ diversity was higher in MS patients (P = 0.0015 and 0.024, respectively), even after age correction. TRAJ56 and TRBV4-3 were more prevalent in MS patients than in HCs (p^corr  = 0.027 and 0.040, respectively). GLIPH consolidated 208,674 TCR clones from MS patients into 1,294 clusters, among which two candidate clusters were identified. The TRBV4-3 cluster was shared by HLA-DRB1*04:05-positive patients (87.5%) and predicted to recognize CMV peptides (CMV-TCR). MS Severity Score (MSSS) was lower in patients with CMV-TCR than in those without (P = 0.037). CMV-IgG-positivity was associated with lower MSSS in HLA-DRB1*04:05 carriers (P = 0.0053). HLA-DRB1*04:05-positive individuals demonstrated higher CMV-IgG titers than HLA-DRB1*04:05-negative individuals (P = 0.017). CMV-IgG-positive patients had more Tregs than CMV-IgG-negative patients (P = 0.054).

INTERPRETATION

High TCRα/TCRβ diversity, regardless of age, is characteristic of MS. Association of a CMV-recognizing TCR with mild disability indicates CMV's protective role in HLA-DRB1*04:05-positive MS.

Role of Smoking in the Pathogenesis of Multiple Sclerosis: A Review Article

Multiple sclerosis (MS) is a complex and unpredictable neurological condition. It is the most commonly seen autoimmune disorder. The incidence of disease and its prevalence are growing worldwide. Early identification of the disease and accurate diagnosis is important to prevent further complications and disability. The etiology remains unclear, and it is believed that complex gene-environment interactions play an essential role. Genetic predisposition only describes a portion of the disease risk, whereas lifestyle and environmental factors are significant contributors. Smoking was identified as an important risk factor for MS. The main objectives of this review were to examine the underlying mechanisms of immune dysregulation in the development of MS, explore the association between smoking and MS, and identify other genetic and environmental factors that alter the risk of developing the disease. We searched PubMed for articles relevant to the study topic published between 2000 and 2020 using the search terms "multiple sclerosis," "cigarette smoking," "risk factors," and, "epigenetics." Studies reveal a marked association between smoking and the risk of MS. Unlike genetic risk factors, many lifestyles and environmental factors can be adjusted, with potential for prevention, particularly for people at the highest risk, such as families of individuals with MS.

Two susceptible HLA-DRB1 alleles for multiple sclerosis differentially regulate anti-JC virus antibody serostatus along with fingolimod

Background

Progressive multifocal leukoencephalopathy (PML) caused by JC virus (JCV) is a rare but serious complication of some disease-modifying drugs used to treat multiple sclerosis (MS). Japanese MS patients treated with fingolimod were reported to be 10 times more likely to develop PML than equivalent patients in other countries. The strongest susceptibility human leukocyte antigen (HLA) class II alleles for MS are distinct between races (DRB1*15:01 for Caucasians and DRB1*04:05 and DRB1*15:01 for Japanese); therefore, we investigated whether HLA class II alleles modulate anti-JCV antibody serostatus in Japanese MS patients with and without fingolimod.

Methods

We enrolled 128 Japanese patients with MS, in whom 64 (50%) were under fingolimod treatment at sampling, and examined the relationship between HLA class II alleles and anti-JCV antibody serostatus. Serum anti-JCV antibody positivity and index were measured using a second-generation two-step assay and HLA-DRB1 and -DPB1 alleles were genotyped.

Results

HLA-DRB1*15 carriers had a lower frequency of anti-JCV antibody positivity (57% vs 78%, p = 0.015), and lower antibody index (median 0.42 vs 1.97, p = 0.037) than non-carriers. Among patients without HLA-DRB1*15, DRB1*04 carriers had a higher seropositivity rate than non-carriers (84% vs 54%, p = 0.030), and DPB1*04:02 carriers had a higher anti-JCV antibody index than non-carriers (3.20 vs 1.34, p = 0.008) although anti-JCV antibody-positivity rates did not differ. Patients treated with fingolimod had a higher antibody index than other patients (1.46 vs 0.64, p = 0.039) and treatment period had a positive correlation with antibody index (p = 0.018). Multivariate logistic regression analysis revealed that age was positively associated, and HLA-DRB1*15 was negatively associated with anti-JCV antibody positivity (odds ratio [OR] = 1.06, p = 0.006, and OR = 0.37, p = 0.028, respectively). Excluding HLA-DRB1*15-carriers, DRB1*04 was an independent risk factor for the presence of anti-JCV antibody (OR = 5.50, p = 0.023).

Conclusions

HLA-DRB1*15 is associated with low anti-JCV antibody positive rate and low JCV antibody index, and in the absence of DRB1*15, DRB1*04 carriers are associated with a high antibody positive rate in Japanese, suggesting the effects of two susceptible HLA-DRB1 alleles on anti-JCV antibody serostatus differ.

Specialized Pro-Resolving Lipid Mediators: Emerging Therapeutic Candidates for Multiple Sclerosis

Multiple sclerosis (MS) is a neuroinflammatory disease in which unresolved and uncontrolled inflammation disrupts normal cellular homeostasis and leads to a pathological disease state. It has long been recognized that endogenously derived metabolic by-products of omega fatty acids, known as specialized pro-resolving lipid mediators (SPMs), are instrumental in resolving the pathologic inflammation. However, there is minimal data available on the functional status of SPMs in MS, despite the fact that MS presents a classical model of chronic inflammation. Studies to date indicate that dysfunction of the SPM biosynthetic pathway is responsible for their altered levels in patient-derived biofluids, which contributes to heightened inflammation and disease severity. Collectively, current findings suggest the contentious role of SPMs in MS due to variable outcomes in biological matrices across studies conducted so far, which could, in part, also be attributed to differences in population characteristics. It seems that SPMs have neuroprotective action on MS by exerting proresolving effects on brain microglia in its preclinical model; however, there are no reports demonstrating the direct effect of SPMs on oligodendrocytes or neurons. This reveals that "one size does not fit all" notion holds significance for MS in terms of the status of SPMs in other inflammatory conditions. The lack of clarity served as the impetus for this review, which is the first of its kind to summarize the relevant data regarding the role of SPMs in MS and the potential to target them for biomarker development and future alternative therapies for this disease. Understanding the mechanisms behind biological actions of SPMs as resolution mediators may prevent or even cure MS and other neurodegenerative pathologies.

Predicting self-reported depression after the onset of multiple sclerosis using genetic and non-genetic factors

BACKGROUND

Persons with multiple sclerosis (PwMS) are disproportionately burdened by depression compared to the general population. While several factors associated with depression and depression severity in PwMS have been identified, a prediction model for depression risk has not been developed. In addition, it is unknown if depression-related genetic variants, including Apolipoprotein E (APOE), would be informative for predicting depression in PwMS.

OBJECTIVE

To develop a depression prediction model for PwMS who did not have a history of depression prior MS onset.

METHODS

The study population included 917 non-Hispanic white PwMS. An optimized multivariable Cox proportional hazards model for time to depression was generated using non-genetic variables, to which APOE and a depression-related genetic risk score were included.

RESULTS

Having a mother who had a history of depression, having obstructive pulmonary disease, obesity and other physical disorders at MS onset, and affect-related symptoms at MS onset predicted depression risk (hazards ratios (HRs): 1.6-2.3). Genetic variables improved the prediction model's performance. APOE ε4/ε4 and ε2/x conferred increased (HR = 2.5, p = 0.026) and decreased (HR = 0.65, p = 0.046) depression risk, respectively.

CONCLUSION

We present a prediction model aligned with The Precision Medicine Initiative, which integrates genetic and non-genetic predictors to inform depression risk stratification after MS onset.

Predicting onset of secondary-progressive multiple sclerosis using genetic and non-genetic factors

BACKGROUND

Predicting the transition from relapsing-remitting (RR) to secondary-progressive (SP) multiple sclerosis (MS) from early in the disease course is challenging.

OBJECTIVE

To construct prediction models for SPMS using sociodemographic and self-reported clinical measures that would be available at/near MS onset, with specific considerations for MS genetic risk factors.

METHODS

We conducted a retrospective cross-sectional study based on 1295 white, non-Hispanic individuals. Cox proportional hazard prediction models were generated for three censored SPMS outcomes (ever transitioning, transitioning within 10 years, and transitioning within 20 years) using sociodemographic, comorbid health information, symptomatology, and other measures of early disease activity. HLADRB1*15:01 and HLA-A*02:01, as well as a genetic risk score, were iteratively considered in each model. We also explored the relationships for all 200 MS risk variants located outside the major histocompatibility complex. Nomograms were generated for the final prediction models.

RESULTS

An older age of MS onset and being male predicted a short latency to SPMS, while a longer interval between the first two relapses predicted a much longer latency. Comorbid conditions and onset symptomatology variably predicted the risk for transitioning to SPMS for each censored outcome. The most notable observation was that HLA-A*02:01, which confers decreased risk for MS, also contributed to decreased hazards for SPMS.

CONCLUSIONS

These results have the potential to advance prognostication for a person with MS using information available at or near onset, potentially improving care and quality of life for those who live with MS.

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

HLA-DRB1 allele impact on pediatric multiple sclerosis in a Hellenic cohort

Background

Pediatric-onset multiple sclerosis (POMS) is considered a complex disease entity with many genetic and environmental factors implicated in its pathogenesis. Linkage studies in Caucasian adult populations consistently demonstrate the major histocompatibility complex and its HLA (human leukocyte antigen) polymorphisms as the genetic locus most strongly linked to MS.

Objective

To investigate the frequencies and possible clinical and imaging correlations of HLA-DRB1 alleles in a Hellenic POMS sample.

Methods

Fifty POMS patients fulfilling the IPMSSG (International Pediatric Multiple Sclerosis Study Group) criteria were enrolled using 144 adult-onset MS (AOMS) patients and 246 healthy controls for comparisons. HLA genotyping was performed with standard low-resolution sequence-specific oligonucleotide (SSO) techniques. Clinical and imaging correlations with specific HLA-DRB1 alleles were also examined.

Results

The HLA-DRB1*03 genotype was significantly higher in POMS patients compared to both the AOMS population (26% vs. 12.5%, p = 0.042) and the general population (26% vs. 12.6%, p = 0.004). HLA-DRB1*03-positive POMS patients had significantly more relapses (6.9 ± 4.9 vs. 4.2 ± 4.4, p = 0.005) and more thoracic spinal cord lesions than HLA-DRB1*03-negative patients (61.5% vs. 27%, p = 0.043).

Conclusion

In our Hellenic population, HLA-DRB1*03 allele confers increased risk for POMS and it is also correlated with possibly increased disease activity, expanding the existing knowledge on HLA associations and POMS.

The Interaction between Viral and Environmental Risk Factors in the Pathogenesis of Multiple Sclerosis

Multiple sclerosis (MS) is a chronic debilitating inflammatory disease of unknown ethology targeting the central nervous system (CNS). MS has a polysymptomatic onset and is usually first diagnosed between the ages of 20–40 years. The pathology of the disease is characterized by immune mediated demyelination in the CNS. Although there is no clinical finding unique to MS, characteristic symptoms include sensory symptoms visual and motor impairment. No definitive trigger for the development of MS has been identified but large-scale population studies have described several epidemiological risk factors for the disease. This list is a confusing one including latitude, vitamin D (vitD) levels, genetics, infection with Epstein Barr Virus (EBV) and endogenous retrovirus (ERV) reactivation. This review will look at the evidence for each of these and the potential links between these disparate risk factors and the known molecular disease pathogenesis to describe potential hypotheses for the triggering of MS pathology.