Short-term outcome prediction for myasthenia gravis: an explainable machine learning model.

Background: Myasthenia gravis (MG) is an autoimmune disease characterized by muscle weakness and fatigability. The fluctuating nature of the disease course impedes the clinical management. Objective: The purpose of the study was to establish and validate a machine learning (ML)-based model for predicting the short-term clinical outcome in MG patients with different antibody types. Methods: We studied 890 MG patients who had regular follow-ups at 11 tertiary centers in China from 1 January 2015 to 31 July 2021 (653 patients for derivation and 237 for validation). The short-term outcome was the modified post-intervention status (PIS) at a 6-month visit. A two-step variable screening was used to determine the factors for model construction and 14 ML algorithms were used for model optimisation. Results: The derivation cohort included 653 patients from Huashan hospital [age 44.24 (17.22) years, female 57.6%, generalized MG 73.5%], and the validation cohort included 237 patients from 10 independent centers [age 44.24 (17.22) years, female 55.0%, generalized MG 81.2%]. The ML model identified patients who were improved with an area under the receiver operating characteristic curve (AUC) of 0.91 [0.89-0.93], 'Unchanged' 0.89 [0.87-0.91], and 'Worse' 0.89 [0.85-0.92] in the derivation cohort, whereas identified patients who were improved with an AUC of 0.84 [0.79-0.89], 'Unchanged' 0.74 [0.67-0.82], and 'Worse' 0.79 [0.70-0.88] in the validation cohort. Both datasets presented a good calibration ability by fitting the expectation slopes. The model is finally explained by 25 simple predictors and transferred to a feasible web tool for an initial assessment. Conclusion: The explainable, ML-based predictive model can aid in forecasting the short-term outcome for MG with good accuracy in clinical practice.

Causal relationships between mood instability and autoimmune diseases: A mendelian randomization analysis.

OBJECTIVES: The interrelationship between mental health and autoimmunity gains more and more attention in recent years. However, the causality between personality traits and autoimmune diseases remained largely unknown. METHODS: We first conducted two-sample mendelian randomization (MR) analysis on the relationships between mood instability, which is a common personality trait in the general population, and 10 autoimmune diseases. The results were further validated in secondary analyses of sensitivity where different MR methods, ethnicities, genders, and ascertainment methods were compared. RESULTS: In the primary analyses, three autoimmune diseases showed genetical predisposition to mood instability: asthma (OR [95%CI] = 3.45 [2.48, 4.78], P = 1.33E- 13), hypothyroidism (OR [95%CI] = 1.02 [1.00, 1.03], P = 1.71E-02), and systemic lupus erythematosus (OR [95%CI] = 5.25 [1.21, 22.76], P = 2.67E-02). The results were consistent in subsequent secondary analyses. Three diseases remained significantly correlated with mood instability by different MR methods with asthma remaining significant in Finnish and mixed populations, and in females from the UK biobank, while hypothyroidism remained significant in both genders from the UK biobank. CONCLUSION: Mood instability is a modifiable risk factor for three autoimmune diseases including asthma, hypothyroidism and systemic lupus erythematosus.

Herpesvirus entry mediator on T cells as a protective factor for myasthenia gravis: A Mendelian randomization study.

Background and objectives: Myasthenia gravis (MG) is a T cell-driven, autoantibody-mediated disorder affecting transmission in neuromuscular junctions. The associations between the peripheral T cells and MG have been extensively studied. However, they are mainly of observational nature, thus limiting our understanding of the effect of inflammatory biomarkers on MG risk. With large data sets now available, we used Mendelian randomization (MR) analysis to investigate whether the biomarkers on T cells are causally associated with MG and further validate the relationships. Methods: We performed a two-sample MR analysis using genetic data from one genome-wide association study (GWAS) for 210 extensive T-cell traits in 3,757 general population individuals and the largest GWAS for MG currently available (1,873 patients versus 36,370 age/gender-matched controls) from US and Italy. Then the biomarkers of interest were validated separately in two GWASs for MG in FIN biobank (232 patients versus 217,056 controls) and UK biobank (152 patients versus 386,631 controls). Results: In the first analysis, three T-cell traits were identified to be causally protective for MG risk: 1) CD8 on terminally differentiated CD8+ T cells (OR [95% CI] = 0.71 [0.59, 0.86], P = 5.62e-04, adjusted P =2.81e-02); 2) CD4+ regulatory T proportion in T cells (OR [95% CI] = 0.44 [0.26, 0.72], P = 1.30e-03, adjusted P =2.81e-02); 3) HVEM expression on total T cells (OR [95% CI] = 0.67 [0.52, 0.86], P = 1.61e-03, adjusted P =2.81e-02) and other eight T-cell subtypes (e.g., naïve CD4+ T cells). In particular, HVEM is a novel immune checkpoint on T cells that has never been linked to MG before. The SNPs on the TNFRSF14 per se further support a more direct link between the HVEM and MG. The validation analysis replicated these results in both FIN and UK biobanks. Both datasets showed a concordant protective trend supporting the findings, albeit not significant. Conclusion: This study highlighted the role of HVEM on T cells as a novel molecular-modified factor for MG risk and validated the causality between T cells and MG. These findings may advance our understanding of MG's immunopathology and facilitate the future development of predictive disease-relevant biomarkers.

Plasma exchange versus intravenous immunoglobulin in AChR subtype myasthenic crisis: A prospective cohort study.

Myasthenic crisis (MC) is a life-threatening state with respiratory failure in patients with myasthenia gravis (MG). The fast-acting immunomodulatory therapies for treating MC included plasma exchange (PE) and intravenous immunoglobulin (IVIG). However, the efficacy and the impact on antibody changes remained unknown. We prospectively followed 40 anti-acetylcholine receptors (AChR) antibody-positive MC patients who received either PE (n = 12) or IVIG (n = 28) at crisis. PE was associated with a reduced ICU stay length (p = 0.018) and an early response by the average changes in MGFA-QMG (p = 0.003), MMT (p = 0.020), and ADL (p = 0.011) at one-week off-ventilation. However, the clinical efficacy was equally comparable in both groups after 1 month. Post-treatment hemoglobin drop was significant in both groups, while IVIG was associated with a significant reduction in anti-AChR antibody titers (p < 0.001). This analysis provides real-world evidence in supporting the use of PE as a fast-acting therapy for shortening the ICU stay in AChR-associated MC.

Gambling Risk Amongst Adolescents: Evidence from a School-Based Survey in the Malaysian Setting.

There has been emerging evidence regarding gambling experiences of young people in Asia recently, but to date, none in Malaysia. This study aimed to estimate the prevalence of gambling, and to identify individual, familial and high-risk behaviours factors among Malaysian adolescents. A cross-sectional study was conducted over 4 months at randomly selected secondary schools in Seremban in Negeri Sembilan state. A total of 2265 self-administered, anonymous questionnaires were distributed to the students. The students completed the questionnaire consisting of sociodemographic and family background, gambling behaviours, high risk behaviours and mental health questions. Approximately 29.6 % (95 % CI 27.7-31.5) of respondents reported participating in some forms of gambling activities in the previous 12 months. Among these, 3.6 % (95 % CI 2.8-4.3) of them were problem gamblers. Parental gambling was the strongest correlate with adolescent gambling behaviour. Signification association was found between gambling behaviour and gender (being males), but interestingly, not with ethnicity. Adolescents who reported engaging in high risk behaviours (such as smoking, alcohol consumption, involvement in physical fights, illegal vehicular racing) were also more likely to gamble. Gambling is not an uncommon phenomenon amongst Malaysian adolescents. Public awareness campaign, health education to targeted groups, revision of existing laws, and screening at primary care level should be implemented to address the issue of gambling among adolescents. This study also highlights the need to examine the national scope of the problem in Malaysia.