Antifibrotic effect and long-term outcome of SGLT2 inhibitors in patients with NAFLD complicated by diabetes mellitus.

The aim of this retrospective multicenter study was to clarify the antifibrotic effect and long-term outcome of sodium glucose cotransporter 2 inhibitors (SGLT2-Is) in patients with nonalcoholic fatty liver disease (NAFLD) complicated by type 2 diabetes mellitus (T2DM). Of the 1262 consecutive patients with T2DM who recently received SGLT2-Is, 202 patients with NAFLD had been receiving SGLT2-Is for more than 48 weeks and were subjected to this analysis. Furthermore, 109 patients who had been on SGLT2-I therapy for more than 3 years at the time of analysis were assessed for the long-term effects of SGLT2-Is. Significant decreases in body weight, liver transaminases, plasma glucose, hemoglobin A1c, and Fibrosis-4 (FIB-4) index were found at week 48. Overall, the median value of FIB-4 index decreased from 1.42 at baseline to 1.25 at week 48 (p < 0.001). In the low-risk group (FIB-4 index < 1.3), there was no significant change in the FIB-4 index. In the intermediate-risk (≥1.3 and <2.67) and high-risk (≥2.67) groups, the median levels significantly decreased from 1.77 and 3.33 at baseline to 1.58 and 2.75 at week 48, respectively (p < 0.001 for both). Improvements in body weight, glucose control, liver transaminases, and FIB-4 index were found at 3 years of SGLT2-I treatment. In the intermediate-risk and high-risk groups (≥1.3 FIB-4 index), the FIB-4 index maintained a significant reduction from baseline throughout the 3 years of treatment. Conclusion: This study showed that SGLT2-Is offered a favorable effect on improvement in FIB-4 index as a surrogate marker of liver fibrosis in patient with NAFLD complicated by T2DM, especially those with intermediate and high risks of advanced fibrosis, and this antifibrotic effect is sustained for the long term.

Convolutional neural network-based system for endocytoscopic diagnosis of early gastric cancer.

BACKGROUND: Endocytoscopy (ECS) aids early gastric cancer (EGC) diagnosis by visualization of cells. However, it is difficult for non-experts to accurately diagnose EGC using ECS. In this study, we developed and evaluated a convolutional neural network (CNN)-based system for ECS-aided EGC diagnosis. METHODS: We constructed a CNN based on a residual neural network with a training dataset comprising 906 images from 61 EGC cases and 717 images from 65 noncancerous gastric mucosa (NGM) cases. To evaluate diagnostic ability, we used an independent test dataset comprising 313 images from 39 EGC cases and 235 images from 33 NGM cases. The test dataset was further evaluated by three endoscopists, and their findings were compared with CNN-based results. RESULTS: The trained CNN required 7.0 s to analyze the test dataset. The area under the curve of the total ECS images was 0.93. The CNN produced 18 false positives from 7 NGM lesions and 74 false negatives from 28 EGC lesions. In the per-image analysis, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 83.2%, 76.4%, 92.3%, 93.0%, and 74.6%, respectively, with the CNN and 76.8%, 73.4%, 81.3%, 83.9%, and 69.6%, respectively, for the endoscopist-derived values. The CNN-based findings had significantly higher specificity than the findings determined by all endoscopists. In the per-lesion analysis, the accuracy, sensitivity, specificity, PPV, and NPV of the CNN-based findings were 86.1%, 82.1%, 90.9%, 91.4%, and 81.1%, respectively, and those of the results calculated by the endoscopists were 82.4%, 79.5%, 85.9%, 86.9%, and 78.0%, respectively. CONCLUSIONS: Compared with three endoscopists, our CNN for ECS demonstrated higher specificity for EGC diagnosis. Using the CNN in ECS-based EGC diagnosis may improve the diagnostic performance of endoscopists.