Use of Rituximab as an Off-Label Medication in Glomerular Diseases: Clinical Perspective

ObjectivesThe aim of this study was to review the use rituximab (RTX) and outcomes in immune-mediated glomerular diseases (glomerulonephritis [GN]) and to compare it to the established literature.MethodsAdult GN patients who received RTX between January 2014 and January 2018 in three public hospitals were reviewed. Membranous nephropathy (MN) and minimal change disease (MCD) were considered diseases with the literature supporting RTX use. Lupus nephritis (LN), primary focal segmental glomerulosclerosis (1^o FSGS), IgA nephropathy, IgG4-related disease (IgG4-RD), and C3GN had insufficient literature support for RTX use. Clinical remission was assessed 6 months after receiving RTX.ResultsA total of 61 cases were analyzed. RTX was an add-on therapy in 87%. The remission rate was 95% in the MCD and MN versus 56% in the off-label group (p = 0.002). LN patients had a mean initial estimated glomerular filtration rate (eGFR) of 69 mL/min. All class III LN achieved remission, and 11 of 21 class IV achieved remission. The mean initial eGFR for 1^o FSGS was 33 mL/min, and it did not improve, and only 2 of 5 had partial resolution of proteinuria. Proteinuria improved in 3 of 5 IgG4-RD cases with eGFR stabilization but failed to improve in C3GN cases with eGFR deterioration. Vasculitis cases (6 ANCA-associated vasculitis and 2 IgA vasculitis) were analyzed separately. Remission was achieved in only 2 ANCA-associated vasculitis cases, and none in IgA vasculitis cases.ConclusionsOur data support the use of RTX in resistant MCD and MN. RTX showed success in LN and IgG4-RD but not FSGS or C3GN. The small number of cases of vasculitis does not allow drawing a conclusion on RTX effectiveness.     

Sodium-glucose co-transporter-2 inhibitors and atrial fibrillation in the cardiovascular and renal outcome trials

Dapagliflozin is a sodium-glucose co-transporter-2 (SGLT2) inhibitor that has recently been shown to reduce the incidence of reported episodes of atrial fibrillation (AF)/atrial flutter in the DECLARE-TIMI 58 trial. This raises the question regarding whether SGLT2 inhibitors can reduce the incidence of AF in a high-risk population. We searched for trials comparing SGLT2 inhibitors to placebo in high-risk individuals with or without diabetes (ie, cardiovascular and renal outcome trials) and that reported the incidence of AF as a serious adverse event. The EMPA-REG OUTCOME trial, CANVAS, CANVAS-R, the DECLARE-TIMI 58 trial, CREDENCE, DAPA-HF, VERTIS-CV and DAPA-CKD were included. The incidence of AF, reported as a serious adverse event, was 0.9% in individuals who received an SGLT2 inhibitor compared to 1.1% in those who received placebo. Pooled results showed a significantly lower incidence of AF in individuals with and without diabetes (relative risk 0.79, 95% confidence interval 0.67,0.93). This review suggests that there is a significantly lower risk of incident AF for individuals on SGLT2 inhibitors versus placebo. While there was a statistically significant lower incidence of AF, reported as a serious adverse event, more research is needed to evaluate its clinical significance.     

Convolution Neural Network for Breast Cancer Detection and Classification Using Deep Learning

Objective: Early detection and precise diagnosis of breast cancer (BC) plays an essential part in enhancing the diagnosis and improving the breast cancer survival rate of patients from 30 to 50%. Through the advances of technology in healthcare, deep learning takes a significant role in handling and inspecting a great number of X-ray, MRI, CTR images.  The aim of this study is to propose a deep learning model (BCCNN) to detect and classify breast cancers into eight classes: benign adenosis (BA), benign fibroadenoma (BF), benign phyllodes tumor (BPT), benign tubular adenoma (BTA), malignant ductal carcinoma (MDC), malignant lobular carcinoma (MLC), malignant mucinous carcinoma (MMC), and malignant papillary carcinoma (MPC). Methods: Breast cancer MRI images were classified into BA, BF, BPT, BTA, MDC, MLC, MMC, and MPC using a proposed Deep Learning model with additional 5 fine-tuned Deep learning models consisting of Xception, InceptionV3, VGG16, MobileNet and ResNet50 trained on ImageNet database. The dataset was collected from Kaggle depository for breast cancer detection and classification. That Dataset was boosted using GAN technique. The images in the dataset have 4 magnifications (40X, 100X, 200X, 400X, and Complete Dataset). Thus we evaluated the proposed Deep Learning model and 5 pre-trained models using each dataset individually. That means we carried out a total of 30 experiments. The measurement that was used in the evaluation of all models includes: F1-score, recall, precision, accuracy. Results: The classification F1-score accuracies of Xception, InceptionV3, ResNet50, VGG16, MobileNet, and Proposed Model (BCCNN) were 97.54%, 95.33%, 98.14%, 97.67%, 93.98%, and 98.28%, respectively. Conclusion: Dataset Boosting, preprocessing and balancing played a good role in enhancing the detection and classification of breast cancer of the proposed model (BCCNN) and the fine-tuned pre-trained models’ accuracies greatly. The best accuracies were attained when the 400X magnification of the MRI images due to their high images resolution.