Exacerbating effects of circadian rhythm disruption on the systemic lupus erythematosus.

OBJECTIVE: Circadian rhythm disruption (CRD) has been associated with inflammation and immune disorders, but its role in SLE progression is unclear. We aimed to investigate the impact of circadian rhythms on immune function and inflammation and their contribution to SLE progression to lupus nephritis (LN). METHODS: This study retrospectively analysed the clinical characteristics and transcriptional profiles of 373 samples using bioinformatics and machine-learning methods. A flare risk score (FRS) was established to predict overall disease progression for patients with lupus. Mendelian randomisation was used to analyse the causal relationship between CRD and SLE progression. RESULTS: Abnormalities in the circadian pathway were detected in patients with SLE, and lower enrichment levels suggested a disease state (normalised enrichment score=0.6714, p=0.0062). The disruption of circadian rhythms was found to be closely linked to lupus flares, with the FRS showing a strong ability to predict disease progression (area under the curve (AUC) of 5-year prediction: 0.76). The accuracy of disease prediction was improved by using a prognostic nomogram based on FRS (AUC=0.77). Additionally, Mendelian randomisation analysis revealed an inverse causal relationship between CRD and SLE (OR 0.6284 (95% CI 0.3630 to 1.0881), p=0.0485) and a positive causal relationship with glomerular disorders (OR 0.0337 (95% CI 1.634e-3 to 6.934e-1), p=0.0280). CONCLUSION: Our study reveals that genetic characteristics arising from CRD can serve as biomarkers for predicting the exacerbation of SLE. This highlights the crucial impact of CRD on the progression of lupus.

Deep Learning-Based Model Significantly Improves Diagnostic Performance for Assessing Renal Histopathology in Lupus Glomerulonephritis.

Background: Assessment of glomerular lesions and structures plays an essential role in understanding the pathological diagnosis of glomerulonephritis and prognostic evaluation of many kidney diseases. Renal pathophysiological assessment requires novel high-throughput tools to conduct quantitative, unbiased, and reproducible analyses representing a central readout. Deep learning may be an effective tool for glomerulonephritis pathological analysis. Methods: We developed a murine renal pathological system (MRPS) model to objectify the pathological evaluation via the deep learning method on whole-slide image (WSI) segmentation and feature extraction. A convolutional neural network model was used for accurate segmentation of glomeruli and glomerular cells of periodic acid-Schiff-stained kidney tissue from healthy and lupus nephritis mice. To achieve a quantitative evaluation, we subsequently filtered five independent predictors as image biomarkers from all features and developed a formula for the scoring model. Results: Perimeter, shape factor, minimum internal diameter, minimum caliper diameter, and number of objects were identified as independent predictors and were included in the establishment of the MRPS. The MRPS showed a positive correlation with renal score (r = 0.480, p < 0.001) and obtained great diagnostic performance in discriminating different score bands (Obuchowski index, 0.842 [95% confidence interval: 0.759, 0.925]), with an area under the curve of 0.78-0.98, sensitivity of 58-93%, specificity of 72-100%, and accuracy of 74-94%. Conclusion: Our MRPS for quantitative assessment of renal WSIs from MRL/lpr lupus nephritis mice enables accurate histopathological analyses with high reproducibility, which may serve as a useful tool for glomerulonephritis diagnosis and prognosis evaluation.