RESUMO
BACKGROUND: Lupus erythematosus (LE) is a spectrum of autoimmune diseases. Due to the complexity of cutaneous LE (CLE), clinical skin image-based artificial intelligence is still experiencing difficulties in distinguishing subtypes of LE. OBJECTIVES: We aim to develop a multimodal deep learning system (MMDLS) for human-AI collaboration in diagnosis of LE subtypes. METHODS: This is a multi-centre study based on 25 institutions across China to assist in diagnosis of LE subtypes, other eight similar skin diseases and healthy subjects. In total, 446 cases with 800 clinical skin images, 3786 multicolor-immunohistochemistry (multi-IHC) images and clinical data were collected, and EfficientNet-B3 and ResNet-18 were utilized in this study. RESULTS: In the multi-classification task, the overall performance of MMDLS on 13 skin conditions is much higher than single or dual modals (Sen = 0.8288, Spe = 0.9852, Pre = 0.8518, AUC = 0.9844). Further, the MMDLS-based diagnostic-support help improves the accuracy of dermatologists from 66.88% ± 6.94% to 81.25% ± 4.23% (p = 0.0004). CONCLUSIONS: These results highlight the benefit of human-MMDLS collaborated framework in telemedicine by assisting dermatologists and rheumatologists in the differential diagnosis of LE subtypes and similar skin diseases.
RESUMO
In our previous study, we reported a series of N-(9,10-anthraquinone-2-carbonyl) amino acid derivatives as novel inhibitors of xanthine oxidase (XO). Recognizing the suboptimal drug-like properties associated with the anthraquinone moiety, we embarked on a nonanthraquinone medicinal chemistry exploration in the current investigation. Through systematic structure-activity relationship (SAR) studies, we identified a series of 4-(isopentyloxy)-3-nitrobenzamide derivatives exhibiting excellent in vitro potency against XO. The optimized compound, 4-isopentyloxy-N-(1H-pyrazol-3-yl)-3-nitrobenzamide (6k), demonstrated exceptional in vitro potency with an IC50 value of 0.13 µM. Compound 6k showed favorable drug-like characteristics with ligand efficiency (LE) and lipophilic ligand efficiency (LLE) values of 0.41 and 3.73, respectively. In comparison to the initial compound 1d, 6k exhibited a substantial 24-fold improvement in IC50, along with a 1.6-fold enhancement in LE and a 3.7-fold increase in LLE. Molecular modeling studies provided insights into the strong interactions of 6k with critical amino acid residues within the active site. Furthermore, in vivo hypouricemic investigations convincingly demonstrated that 6k significantly reduced serum uric acid levels in rats. The MTT results revealed that compound 6k is nontoxic to healthy cells. The gastric and intestinal stability assay demonstrated that compound 6k exhibits good stability in the gastric and intestinal environments. In conclusion, compound 6k emerges as a promising lead compound, showcasing both exceptional in vitro potency and favorable drug-like characteristics, thereby warranting further exploration.