Disability in multiple sclerosis is associated with age and inflammatory, metabolic and oxidative/nitrosative stress biomarkers: results of multivariate and machine learning procedures

Association of multiple sclerosis with stroke: A comprehensive review

Background

Multiple sclerosis (MS) is a chronic immune-mediated disorder characterized by the degradation of the myelin sheath in the central nervous system. Research indicates that individuals with MS exhibit a higher susceptibility to stroke compared to the general population. This association is rooted in shared underlying mechanisms, specifically involving neuroinflammatory processes.

Methodology

We performed an extensive search on PubMed, MEDLINE, Embase, Scopus, and Google Scholar using specific terms. The search terms included variations of "multiple sclerosis," "stroke," "cerebrovascular disease," "vascular risk factors," "disease-modifying therapies," and "neuroinflammation." The search was limited to articles published from January 1, 2000, up to 31 May, 2023.

Results and Discussion

Stroke, a global health burden characterized by significant mortality and adult disability, underscores the critical importance of understanding the link between MS and stroke. Despite a growing body of research establishing an elevated risk of stroke in MS patients, notable information gaps persist. Limited prospective multicenter studies on stroke incidence in MS patients contribute to an incomplete understanding of the precise relationship between these two conditions.

Conclusion

In conclusion, this review underscores the critical need for a thorough understanding of the complex relationship between MS and stroke. The identified risk factors and the influence of MS DMTs on stroke risk necessitate further investigation to inform evidence-based preventive and therapeutic strategies. Bridging the existing information gaps through prospective multicenter studies is imperative for a comprehensive understanding of this association. The development of targeted diagnostic and therapeutic approaches for acute stroke risk in MS patients is paramount to mitigate the impact of these debilitating conditions. Ultimately, this review serves as a foundation for future efforts to enhance preventative measures and therapeutic interventions, thereby improving the overall quality of life for individuals with MS susceptible to strokes.

Stroke risk in multiple sclerosis: a critical appraisal of the literature

Observational studies suggest that the occurrence of stroke on multiple sclerosis (MS) patients is higher compared to the general population. MS is a heterogeneous disease that involves an interplay of genetic, environmental and immune factors. The occurrence of stroke is subject to a wide range of both modifiable and non-modifiable, short- and long-term risk factors. Both MS and stroke share common risk factors. The immune mechanisms that underlie stroke are similar to neurodegenerative diseases and are attributed to neuroinflammation. The inflammation in autoimmune diseases may, therefore, predispose to an increased risk for stroke or potentiate the effect of conventional stroke risk factors. There are, however, additional determinants that contribute to a higher risk and incidence of stroke in MS. Due to the challenges that are associated with their differential diagnosis, the objective is to present an overview of the factors that may contribute to increased susceptibility or occurrence of stroke in MSpatients by performing a review of the available to date literature. As both MS and stroke can individually detrimentally affect the quality of life of afflicted patients, the identification of factors that contribute to an increased risk for stroke in MS is crucial for the prompt implementation of preventative therapeutic measures to limit the additive burden that stroke imposes.

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 Prevalence of Diabetes Mellitus Type II (DMII) in the Multiple Sclerosis Population: A Systematic Review and Meta-Analysis

Introduction: The interactions between Diabetes Mellitus type II (DMII) and Multiple Sclerosis (MS) lead to higher levels of fatigue, higher risk of physical disability, faster cognitive decline, and in general a lower quality of life and a higher frequency of depression compared to the general population. All of the above accelerate the disability progression of patients with MS, reduce the patients' functional capacity, and further increase their psychological and economic burden. Methods: This systematic review and meta-analysis aims to calculate the prevalence of DMII in the MS population. Following PRISMA guidelines, a thorough search of the Medline Pubmed, Cochrane Library, and Scopus databases was performed, focusing on the frequency of DMII in the MS population. Results: A total of 19 studies were included in the synthesis. The results of the main meta-analysis of random effects using R studio 3.3.0 for Windows and the Meta r package showed that the prevalence of DMII in the MS population is 5% (95% CI [0.03, 0.07], 19 studies, I2 = 95%, pQ < 0.001). Additional subgroup analysis based on region showed a difference of 4.4% (I2 = 95.2%, pQ < 0.001), psubgroupdifference = 0.003) between European and non-European participants, while demographic- and MS-specific characteristic (EDSS, Disease Duration) did not seem to affect the prevalence of DMII in the MS population (p = 0.30, p = 0.539, p = 0.19, p = 0.838). No publication bias was discovered (Egger's p test value: 0.896). Conclusions: Even though the prevalence of DMII in the MS population is lower than 10% (the reported prevalence of DMII in the general population) the interactions between the two conditions create significant challenges for MS patients, their caregivers, and physicians. DΜΙΙ should be systematically recorded in the case of MS patients to clearly delineate any potential relationship between the two conditions. Additionally, more structured studies investigating the interactions of MS and DMΙΙ as well as the direction of the causation between those two conditions are necessary in order to gain a deeper insight into the nature of the interaction between MS and DMII.

A pathway phenotype linking metabolic, immune, oxidative, and opioid pathways with comorbid depression, atherosclerosis, and unstable angina

BACKGROUND

There is strong comorbidity between atherosclerosis (ATS) and depression which is attributed to increased atherogenicity, insulin resistance (IR), and immune and oxidative stress.

AIM OF THE STUDY

To examine the role of the above pathways and mu-opioid receptor (MOR), β-endorphin levels, zinc, copper, vitamin D3, calcium, and magnesium in depression due to ATS/unstable angina (UA).

METHODS

Biomarkers were assayed in 58 controls and 120 ATS patients divided into those with moderate and severe depression according to the Beck Depression Inventory-II (BDI-II) scores >19 and >29, respectively.

RESULTS

Neural network and logistic regression models showed that severe depression due to ATS/UA was best predicted by interleukin-6 (IL-6), UA, MOR, zinc, β-endorphin, calcium and magnesium, and that moderate depression was associated with IL-6, zinc, MOR, β-endorphin, UA, atherogenicity, IR, and calcium. Neural networks yielded a significant discrimination of severe and moderate depression with an area under the receiver operating curves of 0.831 and 0.931, respectively. Using Partial Least Squares path analysis, we found that 66.2% of the variance in a latent vector extracted from ATS/UA clinical features, and the BDI-II scores, atherogenicity, and IR could be explained by the regression on IL-6, IL-10, zinc, copper, calcium, MOR, and age. The BDI-II scores increased from controls to ATS to UA class III to UA class IV.

CONCLUSIONS

Immune activation, the endogenous opioid system, antioxidants, trace elements, and macrominerals modulate a common core shared by increased depressive symptoms, ATS, UA, atherogenicity, and IR.

High mobility group box 1 and Dickkopf-related protein 1 as biomarkers of glucose toxicity, atherogenicity, and lower β cell function in patients with type 2 diabetes mellitus

Type 2 diabetes mellitus (T2DM) is associated with increased atherogenicity and inflammatory responses, which may be related to high mobility group box 1 (HMGB1) and Dickkopf-related protein 1 (DKK1). The role of HMGB1 and DKK1 in T2DM is examined in association with lipid and insulin profiles. Serum HMGB1 and DKK1 were measured in T2DM with and without hypertension and compared with controls. The results showed that HMGB1 and DKK1 are higher in T2DM irrespective of hypertension. A large part of the variance in the β-cell index and glucose toxicity was explained by the combined effects of HMGB1 and DKK1. In conclusion, both HMGB1 and DKK1 may contribute to increased atherogenicity in T2DM. Moreover, both biomarkers may cause more deficits in β-cell function and increase glucose toxicity leading to the development of more inflammation and diabetic complications. HMGB1 and the Wnt pathways are other drug targets in treating T2DM.

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.

Influence of eight weeks of combined training on adipsin and lipoprotein profile and possible relations with depression, anxiety and stress in women with multiple sclerosis

OBJECTIVES

Immobility and its physiological and psychological consequences are common problems in patients with multiple sclerosis. The aim of this study was to investigate the effect of 8 weeks of combined training on Adipsin and lipid profile and the possible relationship between these indicators and psychological function in women with multiple sclerosis.

METHODS

In this quasi-experimental study, 40 women with multiple sclerosis were selected by purposeful sampling method and randomly divided into two equal control and exercise groups (n=20). Exercise was performed for 8 weeks (two resistance sessions and one endurance session per week). Before and after the intervention, blood samples were taken and the DASS-21 questionnaire was completed to assess anxiety, depression and stress. Data were analyzed using analysis of covariance, t-test, Bonferroni post hoc test and Pearson correlation test at a significance level of p≤0.05.

RESULTS

In the exercise group, levels of Adipsin, total cholesterol, LDL, TG, weight, fat percentage, WHR, BMI, depression, anxiety and stress were significantly reduced and HDL levels were significantly increased after 8 weeks of combined exercise (p≤0.05). Also, BMI (p=0.01), fat percentage (p=0.01) and WHR (p=0.01) levels had significant positive correlation with Adipsin. There was a significant positive relationship between Total cholesterol level with depression index (p=0.04).

CONCLUSIONS

Performing combination exercises through improving body composition can increase the risk of obesity and cardiovascular risk factors and improve the psychological function of patients with multiple sclerosis. Specialists can use these exercises as an adjunct to drug therapy for MS patients.

Multiple sclerosis diagnosis and phenotype identification by multivariate classification of in vivo frontal cortex metabolite profiles

Multiple sclerosis (MS) is a heterogeneous autoimmune disease for which diagnosis continues to rely on subjective clinical judgment over a battery of tests. Proton magnetic resonance spectroscopy (¹H MRS) enables the noninvasive in vivo detection of multiple small-molecule metabolites and is therefore in principle a promising means of gathering information sufficient for multiple sclerosis diagnosis and subtype classification. Here we show that supervised classification using ¹H-MRS-visible normal-appearing frontal cortex small-molecule metabolites alone can indeed differentiate individuals with progressive MS from control (held-out validation sensitivity 79% and specificity 68%), as well as between relapsing and progressive MS phenotypes (held-out validation sensitivity 84% and specificity 74%). Post hoc assessment demonstrated the disproportionate contributions of glutamate and glutamine to identifying MS status and phenotype, respectively. Our finding establishes ¹H MRS as a viable means of characterizing progressive multiple sclerosis disease status and paves the way for continued refinement of this method as an auxiliary or mainstay of multiple sclerosis diagnostics.

Intersections between Copper, β-Arrestin-1, Calcium, FBXW7, CD17, Insulin Resistance and Atherogenicity Mediate Depression and Anxiety Due to Type 2 Diabetes Mellitus: A Nomothetic Network Approach

Type 2 diabetes mellitus (T2DM) is frequently accompanied by affective disorders with a prevalence of comorbid depression of around 25%. Nevertheless, the biomarkers of affective symptoms including depression and anxiety due to T2DM are not well established. The present study delineated the effects of serum levels of copper, zinc, β-arrestin-1, FBXW7, lactosylceramide (LacCer), serotonin, calcium, magnesium on severity of depression and anxiety in 58 men with T2DM and 30 healthy male controls beyond the effects of insulin resistance (IR) and atherogenicity. Severity of affective symptoms was assessed using the Hamilton Depression and Anxiety rating scales. We found that 61.7% of the variance in affective symptoms was explained by the multivariate regression on copper, β-arrestin-1, calcium, and IR coupled with atherogenicity. Copper and LacCer (positive) and calcium and BXW7 (inverse) had significant specific indirect effects on affective symptoms, which were mediated by IR and atherogenicity. Copper, β-arrestin-1, and calcium were associated with affective symptoms above and beyond the effects of IR and atherogenicity. T2DM and affective symptoms share common pathways, namely increased atherogenicity, IR, copper, and β-arrestin-1, and lowered calcium, whereas copper, β-arrestin-1, calcium, LacCer, and FBXW7 may modulate depression and anxiety symptoms by affecting T2DM.

Circulatory antioxidant and oxidative stress markers are in correlation with demographics but not cognitive functions in multiple sclerosis patients

BACKGROUND

Multiple sclerosis (MS) is the most common non-traumatic cause of disability in younger adults. MS can be presented with a wide range of symptoms such as cognitive impairment (CI). Oxidative stress (OXS) is a major basis of the pathogenesis of MS. There is a positive correlation between OXS factors and the progression of the disease in MS patients. There are limited studies regarding the role of OXS in MS-related CI. In this study, as an exploratory analysis, we assess the role of endogenous antioxidants and OXS factors in cognitive function, the severity of disability due to MS, and demographic findings in a sample of MS patients.

METHODS

Adult (>18 years old) patients with a definite diagnosis of MS based on 2017 revised MacDonald criteria were included in this study. The neurophysiological assessment was conducted, using the validated Persian version of minimal assessment of cognitive function in multiple sclerosis (MACFIMS) battery, which is composed of seven different tests. Based on the structure of the battery, CI was defined as a failure in at least two different components of the MACFIMS battery. The patients were separated into two groups of CI and non-CI. Examined antioxidant factors included catalase Activity (CAT), Glutathione Peroxidase 1 (GPX1), Glutathione Peroxidase 2 (GPX2), Reduced Glutathione (GSH), Superoxide Dismutase (SOD), and serum total antioxidant capacity (TAC). Malondialdehyde (MDA) was also measured as an OXS marker.

RESULTS

71 patients were involved in this study. The type of MS was relapsing-remitting MS (RRMS) in 80.28% of the participants. Disease duration (P<0.01), type of MS (p<0.01), and EDSS score (p<0.01) were different between CI and non-CI groups, but there were not any significant differences in CAT (p = 0.80), GPX1 (p = 0.71), GPX2 (p = 0.41), GSH (p = 0.96), TAC (p = 0.13), SOD (p = 0.37), and MDA (p = 0.82). A significant difference between RRMS and progressive MS (PMS) patients in the levels of GPX1 (p = 0.01), GPX2 (p = 0.01), and SOD (p = 0.01) was observed. Also, we found higher circulatory levels of CAT (p = 0.02) and TAC (p<0.01) in male MS patients. We found significant correlations between aging and CAT (R = 0.28; p = 0.01), GPX1 (R = 0.36; p<0.01), GPX2 (R = 0.34; p<0.01), and SOD (R = 0.40; p<0.01). EDSS, the duration of the disease, relapse rate, and the number of impaired cognitive tasks were not correlated with any of investigated OXS or antioxidant factors (p>0.05). In terms of a detailed investigation of associations between MACFIMS battery components and levels of OXS and antioxidant factors, there were no significant relations in this regard (p>0.05). Based on the logistic regression multivariate analysis, only disease duration (p = 0.03) and GPX1 (p = 0.01) were independently associated with CI in MS patients in our sample.

CONCLUSION

The circulatory levels of GPX1, GPX2, and SOD are significantly different between RRMS and PMS patients. Neither endogenous antioxidants nor MDA, as an OXS biomarker, are associated with the cognitive function or level of physical disability in MS patients. Limitations of this study suggest a need for future studies in a larger sample of MS patients.

Understanding the role of S-nitrosylation/nitrosative stress in inflammation and the role of cellular denitrosylases in inflammation modulation: Implications in health and diseases

S-nitrosylation is a very fundamental post-translational modification of protein and non-protein thiols due the involvement of it in a variety of cellular processes including activation/inhibition of several ion channels such as ryanodine receptor in the cardiovascular system; blood vessel dilation; cGMP signaling and neurotransmission. S-nitrosothiol homeostasis in the cell is tightly regulated and perturbations in homeostasis result in an altered redox state leading to a plethora of disease conditions. However, the exact role of S-nitrosylated proteins and nitrosative stress metabolites in inflammation and in inflammation modulation is not well-reviewed. The cell utilizes its intricate defense mechanisms i.e. cellular denitrosylases such as Thioredoxin (Trx) and S-nitrosoglutathione reductase (GSNOR) systems to combat nitric oxide (NO) pathology which has also gained current attraction as novel anti-inflammatory molecules. This review attempts to provide state-of-the-art knowledge from past and present research on the mechanistic role of nitrosative stress intermediates (RNS, OONO^-, PSNO) in pulmonary and autoimmune diseases and how cellular denitrosylases particularly GSNOR and Trx via imparting opposing effects can modulate and reduce inflammation in several health and disease conditions. This review would also bring into notice the existing gaps in current research where denitrosylases can be utilized for ameliorating inflammation that would leave avenues for future therapeutic interventions.

Retinal Nerve Fiber Layer Thickness Correlates with Serum and Cerebrospinal Fluid Neurofilament Levels and is Associated with Current Disability in Multiple Sclerosis

Introduction

The main purpose of the present study is to confirm Peripapillary Retinal Nerve Fiber Layer (pRNFL) thickness is a biomarker of axonal degeneration in patients with Multiple Sclerosis (MS) and to evaluate its relationship with Neurofilament heavy chain (NfH) and Nitrotyrosine (NT).

Method

We quantified serum (s) and/or cerebrospinal fluid (CSF) NfH and NT levels in 30 relapsing-remitting MS patients (RRMS), 16 secondary progressive MS (SPMS) patients and in 29 control subjects matched for age and gender. Optical coherence tomography (OCT) measurements of pRNFL were performed in all subjects. Clinical outcomes were tested by Multiple Sclerosis Functional Composite (MSFC) and Expanded Disability Status Scale (EDSS).

Results

RRMS patients exhibited significantly higher NfH/NT levels (99 pg/mL, 107.52 nM respectively) than controls (74 pg/mL, 48.72 nM) in CSF (p<0.0001), but not in sera. SPMS patients had significantly higher s NfH/NT values (111.25 pg/mL, 1251.77 nM respectively) and lower mean pRNFL thickness (79 µm) than patients with RRMS (98.50 µm) and controls (108 µm) (p<0.0001). pRNFL thickness was significantly correlated with all clinical disability measurements (EDSS, Trail Making test, 9-Hole Peg Test, and PASAT) in both RRMS and SPMS (p<0.001, p=0.02, p=0.03, p=0.02 respectively). A positive correlation was also found between serum and/or CSF NfH levels and EDSS scores in RRMS and SPMS (p<0.001, p=0.02 respectively). The pRNFL thickness was also correlated significantly with serum and/or CSF NfH levels but not with s/CSF NT levels in both clinical forms of MS (p<0.01, p<0.001 respectively).

Conclusion

The current study demonstrated that both pRNFL and s/CSF NfH are reliable and quantitative biomarkers that correlate with current disease course and cross-sectional measure of disability in patients with MS.

Current review and next steps for artificial intelligence in multiple sclerosis risk research

In the last few decades, the prevalence of multiple sclerosis (MS), a chronic inflammatory disease of the nervous system, has increased, particularly in Northern European countries, the United States, and United Kingdom. The promise of artificial intelligence (AI) and machine learning (ML) as tools to address problems in MS research has attracted increasing interest in these methods. Bayesian networks offer a clear advantage since they can integrate data and causal knowledge allowing for visualizing interactions between dependent variables and potential confounding factors. A review of AI/ML research methods applied to MS found 216 papers using terms "Multiple Sclerosis", "machine learning", "artificial intelligence", "Bayes", and "Bayesian", of which 90 were relevant and recently published. More than half of these involve the detection and segmentation of MS lesions for quantitative analysis; however clinical and lifestyle risk factor assessment and prediction have largely been ignored. Of those that address risk factors, most provide only association studies for some factors and often fail to include the potential impact of confounding factors and bias (especially where these have causal explanations) that could affect data interpretation, such as reporting quality and medical care access in various countries. To address these gaps in the literature, we propose a causal Bayesian network approach to assessing risk factors for MS, which can address deficiencies in current epidemiological methods of producing risk measurements and makes better use of observational data.

Trace element, immune and opioid biomarkers of unstable angina, increased atherogenicity and insulin resistance: Results of machine learning

BACKGROUND

Aberrations in endothelial cells, immune and oxidative pathways are associated with atherosclerosis (ATS) and unstable angina (UA). The role of trace elements, minerals, and the endogenous opioid system (EOS) in UA are less well established.

METHODS

We measured lipid, insulin resistance (IR), and immune, trace element (copper and zinc), mineral (magnesium, calcium), EOS (β-endorphin and mu-opioid receptor (MOR)) and antioxidant (vitamin D3) biomarkers in patients with ATS (n = 60) and UA (n = 60) and healthy controls (n = 58).

RESULTS

ATS patients showed increased atherogenic and IR indices, IL-6, IL-10, β-endorphin, copper and magnesium, and lower zinc than healthy controls. Logistic regression showed that UA was significantly discriminated from ATS without UA with an accuracy of 85.5 % using calcium, IL-10, β-endorphin, MOR, triglycerides, IR (all positively), and copper and vitamin D3 (inversely). Neural networks showed that UA was discriminated from ATS without UA with an area under the ROC curve of 0.942 using MOR, β-endorphin, calcium, insulin resistance, vitamin D3 and copper as input variables. We found that 50.0 % of the variance in IR was explained by the regression on copper, IL-10, IL-6 (all positively), and zinc (inversely), while 32.9 % of the variance in the atherogenic index of plasma was explained by copper, IL-10 (both positively), and magnesium (inversely).

CONCLUSION

UA is not only mediated by insulin resistance, atherogenicity, and immune disorders, but also by aberrations in the endogenous opioid system and trace elements as well as lowered antioxidant levels. Copper appears to play a key role in IR and atherogenicity.

The cholesterol autoxidation products, 7-ketocholesterol and 7β-hydroxycholesterol are associated with serum neurofilaments in multiple sclerosis

BACKGROUND

Serum neurofilament light chain (sNfL) is an established marker of neuroaxonal injury in multiple sclerosis (MS).

OBJECTIVES

To investigate if oxysterols produced from non-enzymatic and enzymatic cholesterol oxidation are differentially associated with sNfL measurements in MS.

METHODS

This longitudinal study included 62 relapsing-remitting (RR-MS) and 36 progressive MS (PMS) patients with baseline and 5-year follow-up measures of serum levels of 6 oxysterols, sNfL and lipids. The oxysterols, 24-hydroxycholesterol (24HC), 25HC, 27HC, 7αHC, 7βHC and 7-ketocholesterol (7KC), were measured using liquid chromatography-mass spectrometry. sNfL was measured using single molecular array assay. Serum high-density lipoprotein cholesterol (HDL-C) and low-density lipoprotein cholesterol (LDL-C) levels were obtained from a lipid profile.

RESULTS

The enzymatically produced oxysterols 24HC, 25HC, 27HC and 7αHC were not associated with sNfL. However, baseline levels of reactive oxygen species (ROS) produced oxysterols, 7KC (p = 0.032) and 7βHC (p = 0.0025), were positively associated with sNfL levels at follow-up. Follow-up 7KC (p = 0.038) levels were also associated with follow-up sNfL levels. The associations of 7KC or 7βHC with sNfL remained significant after adjusting for LDL-C or HDL-C.

CONCLUSIONS

7KC and 7βHC, produced by ROS-mediated cholesterol oxidation are associated with neuroaxonal injury as assessed by sNfL in MS.

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.

Hyperhomocysteinemia and Endothelial Dysfunction in Multiple Sclerosis

Endothelial dysfunction is recognized as one of the leading factors in the pathogenesis of diseases of the central nervous system of various etiologies. Numerous studies have shown the role of hyperhomocysteinemia in the development of endothelial dysfunction and the prothrombogenic state. The most important condition in the development of multiple sclerosis (MS) is a dysregulation of the blood-brain barrier (BBB) and transendothelial leukocyte migration. It has been proven that homocysteine also contributes to the damage of neurons by the mechanism of excitotoxicity and the induction of the apoptosis of neurons. These processes can be one of the factors of neurodegenerative brain damage, which plays a leading role in the progression of MS. This review describes the pleiotropic effect of homocysteine on these processes and its role in MS pathogenesis.