Performance of a deep neural network in teledermatology: a single-centre prospective diagnostic study.

BACKGROUND: The use of artificial intelligence (AI) algorithms for the diagnosis of skin diseases has shown promise in experimental settings but has not been yet tested in real-life conditions. OBJECTIVE: To assess the diagnostic performance and potential clinical utility of a 174-multiclass AI algorithm in a real-life telemedicine setting. METHODS: Prospective, diagnostic accuracy study including consecutive patients who submitted images for teledermatology evaluation. The treating dermatologist chose a single image to upload to a web application during teleconsultation. A follow-up reader study including nine healthcare providers (3 dermatologists, 3 dermatology residents and 3 general practitioners) was performed. RESULTS: A total of 340 cases from 281 patients met study inclusion criteria. The mean (SD) age of patients was 33.7 (17.5) years; 63% (n = 177) were female. Exposure to the AI algorithm results was considered useful in 11.8% of visits (n = 40) and the teledermatologist correctly modified the real-time diagnosis in 0.6% (n = 2) of cases. The overall top-1 accuracy of the algorithm (41.2%) was lower than that of the dermatologists (60.1%), residents (57.8%) and general practitioners (49.3%) (all comparisons P < 0.05, in the reader study). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained, the balanced top-1 accuracy of the algorithm (47.6%) was comparable to the dermatologists (49.7%) and residents (47.7%) but superior to the general practitioners (39.7%; P = 0.049). Algorithm performance was associated with patient skin type and image quality. CONCLUSIONS: A 174-disease class AI algorithm appears to be a promising tool in the triage and evaluation of lesions with patient-taken photographs via telemedicine.

Single-chain recombinant HLA-DQ2.5/peptide molecules block α2-gliadin-specific pathogenic CD4+ T-cell proliferation and attenuate production of inflammatory cytokines: a potential therapy for celiac disease.

Celiac disease (CD) is a disorder of the small intestine caused by intolerance to wheat gluten and related proteins in barley and rye. CD4(+) T cells have a central role in CD, recognizing and binding complexes of HLA-DQ2.5 bearing gluten peptides that have survived digestion and that are deamidated by tissue transglutaminase (TG2), propagating a cascade of inflammatory processes that damage and eventually destroy the villous tissue structures of the small intestine. In this study, we present data showing that recombinant DQ2.5-derived molecules bearing covalently tethered α2-gliadin-61-71 peptide have a remarkable ability to block antigen-specific T-cell proliferation and inhibited proinflammatory cytokine secretion in human DQ2.5-restricted α2-gliadin-specific T-cell clones obtained from patients with CD. The results from our in vitro studies suggest that HLA-DQ2.5-derived molecules could significantly inhibit and perhaps reverse the intestinal pathology caused by T-cell-mediated inflammation and the associated production of proinflammatory cytokines.

Programmed cell death in cereal aleurone.

Progress in understanding programmed cell death (PCD) in the cereal aleurone is described. Cereal aleurone cells are specialized endosperm cells that function to synthesize and secrete hydrolytic enzymes that break down reserves in the starchy endosperm. Unlike the cells of the starchy endosperm, aleurone cells are viable in mature grain but undergo PCD when germination is triggered or when isolated aleurone layers or protoplasts are incubated in gibberellic acid (GA). Abscisic acid (ABA) slows down the process of aleurone cell death and isolated aleurone protoplasts can be kept alive in media containing ABA for up to 6 months. Cell death in barley aleurone occurs only after cells become highly vacuolated and is manifested in an abrupt loss of plasma membrane integrity. Aleurone cell death does not follow the apoptotic pathway found in many animal cells. The hallmarks of apoptosis, including internucleosomal DNA cleavage, plasma membrane and nuclear blebbing and formation of apoptotic bodies, are not observed in dying aleurone cells. PCD in barley aleurone cells is accompanied by the accumulation of a spectrum of nuclease and protease activities and the loss of organelles as a result of cellular autolysis.