Background: Antinuclear antibody pattern recognition is vital for autoimmune disease diagnosis but labor-intensive for manual interpretation. To develop an automated pattern recognition system, we established machine learning models based on the International Consensus on Antinuclear Antibody Patterns (ICAP) at a competent level, mixed patterns recognition, and evaluated their consistency with human reading. Methods: 51,694 human epithelial cells (HEp-2) cell images with patterns assigned by experienced medical technologists collected in a medical center were used to train six machine learning algorithms and were compared by their performance. Next, we choose the best performing model to test the consistency with five experienced readers and two beginners. Results: The mean F1 score in each classification of the best performing model was 0.86 evaluated by Testing Data 1. For the inter-observer agreement test on Testing Data 2, the average agreement was 0.849 (?) among five experienced readers, 0.844 between the best performing model and experienced readers, 0.528 between experienced readers and beginners. The results indicate that the proposed model outperformed beginners and achieved an excellent agreement with experienced readers. Conclusions: This study demonstrated that the developed model could reach an excellent agreement with experienced human readers using machine learning methods.
remains the major concern of anti-CD19 CAR-T cell therapy. One mechanism for relapse is the development of humoral and/or cellular immune responses against some specific epitopes of scFv in the CAR structure, which are derived from a murine antibody. In this investigator-initiated trial, we developed a humanized anti-CD19 scFv CAR-T (hCAR-T) cells and infused these cells to patients with r/r ALL. Sustained B cell aplasia and long-term persistence of hCAR-T cells were observed in these patients. Moreover, four patients with high tumor burden and rapidly progressive disease experienced grade 3-4 of cytokine release syndrome (CRS). These severe CRSs were successfully controlled by tocilizumab, glucocorticoid and plasma exchange (PE). Our data provide a potential method to reduce the relapse rate for patients accepting CAR-T cell therapy.Research.
BackgroundBreast cancer is one of the most common malignancies among women. However, there remains no consensus in current literature on the incidence of autoimmune diseases among breast cancer patients. The purpose of this study was to evaluate the risks of major autoimmune diseases (MAD) including systemic lupus erythematosus (SLE), rheumatoid arthritis (RA), Sjögren's syndrome (SS) and dermatomyositis (DMtis)/polymyositis (PM) in female breast cancer patients.MethodsUsing the Taiwanese National Health Insurance Research Database (NHIRD) records from 2003 to 2013, we identified newly-diagnosed female breast cancer patients and randomly selected females without breast cancer in the period 2007 to 2013 into a control group. We matched the two cohorts using a 1:4 ratio based on age, and the year of index date for comparison of the risk of major autoimmune diseases. We estimated and compared the relative risks of autoimmune diseases in female breast cancer patients and females without breast cancer.ResultsA total of 54,311 females with breast cancer and 217,244 matched females without breast cancer were included in this study. For SLE, the incidence rates were 2.3 (breast cancer group) vs. 10.0 (control group) per 100,000 women years; for RA rates were 19.3 (breast cancer group) vs. 42.7 (control group) per 100,000 women years; and for SS rates were 20.5 (breast cancer group) vs. 38.2 (control group) per 100,000 women years. After adjusting for potential confounders, the hazard ratios (95% confidence intervals) for female breast cancer patients vs. control group were 0.04 (0.01–0.24) for SLE; 0.03 (0.02–0.04) for RA; and 0.21 (0.09–0.48) for SS.ConclusionFemale breast cancer patients had lower risks of SLE, RA and SS when compared to female individuals without breast cancer. However, there was no significant difference in the risk of developing DMtis/PM between both groups.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.