An introduction to machine learning and analysis of its use in rheumatic diseases.

Machine learning (ML) is a computerized analytical technique that is being increasingly employed in biomedicine. ML often provides an advantage over explicitly programmed strategies in the analysis of multidimensional information by recognizing relationships in the data that were not previously appreciated. As such, the use of ML in rheumatology is increasing, and numerous studies have employed ML to classify patients with rheumatic autoimmune inflammatory diseases (RAIDs) from medical records and imaging, biometric or gene expression data. However, these studies are limited by sample size, the accuracy of sample labelling, and absence of datasets for external validation. In addition, there is potential for ML models to overfit or underfit the data and, thereby, these models might produce results that cannot be replicated in an unrelated dataset. In this Review, we introduce the basic principles of ML and discuss its current strengths and weaknesses in the classification of patients with RAIDs. Moreover, we highlight the successful analysis of the same type of input data (for example, medical records) with different algorithms, illustrating the potential plasticity of this analytical approach. Altogether, a better understanding of ML and the future application of advanced analytical techniques based on this approach, coupled with the increasing availability of biomedical data, may facilitate the development of meaningful precision medicine for patients with RAIDs.

Gut Microbiota and Bacterial DNA Suppress Autoimmunity by Stimulating Regulatory B Cells in a Murine Model of Lupus.

Autoimmune diseases, such as systemic lupus erythematosus, are characterized by excessive inflammation in response to self-antigens. Loss of appropriate immunoregulatory mechanisms contribute to disease exacerbation. We previously showed the suppressive effect of vancomycin treatment during the "active-disease" stage of lupus. In this study, we sought to understand the effect of the same treatment given before disease onset. To develop a model in which to test the regulatory role of the gut microbiota in modifying autoimmunity, we treated lupus-prone mice with vancomycin in the period before disease development (3-8 weeks of age). We found that administration of vancomycin to female MRL/lpr mice early, only during the pre-disease period but not from 3 to 15 weeks of age, led to disease exacerbation. Early vancomycin administration also reduced splenic regulatory B (Breg) cell numbers, as well as reduced circulating IL-10 and IL-35 in 8-week old mice. Further, we found that during the pre-disease period, administration of activated IL-10 producing Breg cells to mice treated with vancomycin suppressed lupus initiation, and that bacterial DNA from the gut microbiota was an inducer of Breg function. Oral gavage of bacterial DNA to mice treated with vancomycin increased Breg cells in the spleen and mesenteric lymph node at 8 weeks of age and reduced autoimmune disease severity at 15 weeks. This work suggests that a form of oral tolerance induced by bacterial DNA-mediated expansion of Breg cells suppress disease onset in the autoimmune-prone MRL/lpr mouse model. Future studies are warranted to further define the mechanism behind bacterial DNA promoting Breg cells.