Predicting anti-TNF treatment response in rheumatoid arthritis: An artificial intelligence-driven model using cytokine profile and routine clinical practice parameters

Introduction

Rheumatoid arthritis (RA) is a heterogeneous disease in which therapeutic strategies used have evolved dramatically. Despite significant progress in treatment strategies such as the development of anti-TNF drugs, it is still not possible to differentiate those patients who will respond from who will not. This can lead to effective-treatment delays and unnecessary costs. The aim of this study was to utilize a profile of the patient's characteristics, clinical parameters, immune status (cytokine profile) and artificial intelligence to assess the feasibility of developing a tool that could allow us to predict which patients will respond to treatment with anti-TNF drugs.

Methods

This study included 38 patients with RA from the RA-Paz cohort. Clinical activity was measured at baseline and after 6 months of treatment. The cytokines measured before the start of anti-TNF treatment were IL-1, IL-12, IL-10, IL-2, IL-4, IFNg, TNFa, and IL-6. Statistical analyses were performed using the Wilcoxon-Rank-Sum Test and the Benjamini-Hochberg method. The predictive model viability was explored using the 5-fold cross-validation scheme in order to train the logistic regression models.

Results

Statistically significant differences were found in parameters such as IL-6, IL-2, CRP and DAS-ESR. The predictive model performed to an acceptable level in correctly classifying patients (ROC-AUC 0.804167 to 0.891667), suggesting that it would be possible to develop a clinical classification tool.

Conclusions

Using a combination of parameters such as IL-6, IL-2, CRP and DAS-ESR, it was possible to develop a predictive model that can acceptably discriminate between remitters and non-remitters. However, this model needs to be replicated in a larger cohort to confirm these findings.

Hematologically important mutations: The autosomal forms of chronic granulomatous disease (third update)

Chronic granulomatous disease (CGD) is an immunodeficiency disorder affecting about 1 in 250,000 individuals. CGD patients suffer from severe, recurrent bacterial and fungal infections. The disease is caused by mutations in the genes encoding the components of the leukocyte NADPH oxidase. This enzyme produces superoxide, which is subsequently metabolized to hydrogen peroxide and other reactive oxygen species (ROS). These products are essential for intracellular killing of pathogens by phagocytic leukocytes (neutrophils, eosinophils, monocytes and macrophages). The leukocyte NADPH oxidase is composed of five subunits, four of which are encoded by autosomal genes. These are CYBA, encoding p22^phox, NCF1, encoding p47^phox, NCF2, encoding p67^phox and NCF4, encoding p40^phox. This article lists all mutations identified in these genes in CGD patients. In addition, cytochrome b₅₅₈ chaperone-1 (CYBC1), recently recognized as an essential chaperone protein for the expression of the X-linked NADPH oxidase component gp91^phox (also called Nox2), is encoded by the autosomal gene CYBC1. Mutations in this gene also lead to CGD. Finally, RAC2, a small GTPase of the Rho family, is needed for activation of the NADPH oxidase, and mutations in the RAC2 gene therefore also induce CGD-like symptoms. Mutations in these last two genes are also listed in this article.

Variants in CASP10, a diagnostic challenge: Single center experience and review of the literature

Autoimmune lymphoproliferative syndrome is a primary immunodeficiency caused by variants in FAS-mediated apoptosis related genes and is characterized by lymphadenopathy, splenomegaly and autoimmunity. A total of six different variants in CASP10 have been described as potential causative of disease, although two of them have recently been considered polymorphisms. The high allele frequency of these variants in healthy population in addition to the broad clinical spectrum of the disease difficult the interpretation of their pathogenicity. Here, we describe the clinical and analytical findings of three new patients carrying variants in CASP10 and summarize 12 more cases from the literature. Autoimmune cytopenias, adenopathies and increment of TCRαβ+CD4-CD8- cells have been the most common findings, being possibly the FAS-mediated apoptosis pathway the pathogenic mechanism of this disease. The clinical impact and the consequences of CASP10 variants are not fully elucidated, therefore the description of new cases will contribute to solve this issue.