A Bayesian Model to Analyze the Association of Rheumatoid Arthritis With Risk Factors and Their Interactions

Abstract

Rheumatoid arthritis (RA) is a chronic autoimmune disorder that commonly manifests as destructive joint inflammation but also affects multiple other organ systems. The pathogenesis of RA is complex where a variety of factors including comorbidities, demographic, and socioeconomic variables are known to associate with RA and influence the progress of the disease. In this work, we used a Bayesian logistic regression model to quantitatively assess how these factors influence the risk of RA, individually and through their interactions. Using cross-sectional data from the National Health and Nutrition Examination Survey (NHANES), a set of 11 well-known RA risk factors such as age, gender, ethnicity, body mass index (BMI), and depression were selected to predict RA. We considered up to third-order interactions between the risk factors and implemented factor analysis of mixed data (FAMD) to account for both the continuous and categorical natures of these variables. The model was further optimized over the area under the receiver operating characteristic curve (AUC) using a genetic algorithm (GA) with the optimal predictive model having a smoothed AUC of 0.826 (95% CI: 0.801–0.850) on a validation dataset and 0.805 (95% CI: 0.781–0.829) on a holdout test dataset. Apart from corroborating the influence of individual risk factors on RA, our model identified a strong association of RA with multiple second- and third-order interactions, many of which involve age or BMI as one of the factors. This observation suggests a potential role of risk-factor interactions in RA disease mechanism. Furthermore, our findings on the contribution of RA risk factors and their interactions to disease prediction could be useful in developing strategies for early diagnosis of RA.

Anti-Ma2 Antibody-Associated Paraneoplastic Neurological Syndromes: A Pilot Study

“…In detail, white blood cells, protein, and IgG index (as determined by isoelectric focusing) in CSF corresponded to the immune-inflammatory response of the central nervous system, whereas tumor markers, coexisting antibodies, erythrocyte sedimentation rate (ESR), neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and lymphocyte to monocyte ratio (LMR) reflected peripheral or general conditions. Electroencephalogram (EEG), electromyography (EMG), magnetic resonance imaging (MRI), 18 F-fluorodeoxyglucose positron emission tomography (FDG-PET), and computed tomography were performed to assess the individual pathological state and investigate the underlying cancers. The anti-Ma2 antibodies in serum and/or CSF were evaluated by commercial line blots (Euroimmun, Lübeck, Germany) and confirmed using indirect immunofluorescence tests on monkey cerebellum slides.…”

“…farther distance between the point of the variable and the origin on the factor map. Abbreviations: ab, antibody; CSF, cerebrospinal fluid; Dim, dimension; EEG, electroencephalograms; EMG, electromyography; ESR, erythrocyte sedimentation rate; FAMD, factor analysis of mixed data; FDG-PET, 18 F-fluorodeoxyglucose positron emission tomography; IVMP, intravenous methylprednisolone; IVIG, intravenous immunoglobulin; LE, Limbic encephalitis; LMR, lymphocyte to monocyte ratio; MND, motor neuron diseases; MRI, magnetic resonance imaging; mRS, modified Rankin Scale; NLR, neutrophil-to-lymphocyte ratio; PLR, platelet-to-lymphocyte ratio; SMN, sensorimotor neuropathies. to-lymphocyte ratio.…”

“…Moreover, we could divide and color each individual by other variables and explore their relationships using the ellipses of the confidence intervals (Figure 5). 18 F-fluorodeoxyglucose positron emission tomography; IVMP, intravenous methylprednisolone; IVIG, intravenous immunoglobulin; LE, Limbic encephalitis; LMR, lymphocyteto-monocyte ratio; MND, motor neuron diseases; MRI, magnetic resonance imaging; mRS, modified Rankin Scale; NLR, neutrophil-to-lymphocyte ratio; PLR, platelet-to-lymphocyte ratio; SMN, sensorimotor neuropathies.…”

“…Furthermore, it could help analyze similarities and their relationships after deconstructing the original complex data into fewer relevant factors [ 12 , 13 ]. It has been improved and applied in various fields, including describing the epidemiological characteristics of infectious diseases, such as COVID-19 and dengue vector mosquitoes; exploring and predicting the risk factors for health status, or diseases like rheumatoid arthritis and acute encephalitis; and monitoring environmental pollution [ 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. As a result, we conducted FAMD to better visualize the correlations between each variable and individual and further explored the possible risk factors of outcomes.…”

“…Abbreviations: AFP, alpha fetoprotein; ATG, anti-thyroglobulin abs; BMTL, bilateral mesial temporal lobe lesions; β2GPI, beta-2 glycoprotein 1; CA, carbohydrate antigen; CAMP, compound motor action potential; CEA, carcinoembryonic antigen; CSF, cerebrospinal fluid; EEG, electroencephalograms; EMG, electromyography; ESR, erythrocyte sedimentation rate; FDG-PET,18 F-fluorodeoxyglucose positron emission tomography; hCG, human chorionic gonadotrophin; LMR, lymphocyte-to-monocyte ratio; MRI, magnetic resonance imaging; NLR, neutrophil-to-lymphocyte ratio; PLR, platelet-to-lymphocyte ratio; PSA, prostate-specific antigen; RNS, repetitive nerve stimulation; SCC, squamous cell carcinoma antigen; TG, thyroglobulin; TPO, thyroperoxidase; -, not done or no date available, * positive anti-Ma2 abs in CSF, while others were serum positive; ˆincreased ESR after adjusting for age and sex.…”