Background We aimed to investigate the efficacy of canagliflozin (based on its effect on liver function and blood glucose levels) and its safety in high alanine aminotransferase (ALT) patients (ALT >30 U/L). Methods This post hoc analysis of canagliflozin in type 2 diabetes mellitus (T2DM) patients was divided into Study 1 (pooled analysis of 12- and 24-week placebo-controlled, monotherapy studies) and Study 2 (52-week monotherapy/combination therapy study). The canagliflozin 100 mg group data were compared with placebo or baseline ALT subgroup (baseline ALT >30 or ≤30 U/L) data. The primary endpoint was change in ALT level from baseline. Secondary endpoints were changes in efficacy-related parameters. Adverse events (AEs) were evaluated. Results The mean ALT change at 12 weeks was −10.3 ± 11.7 and −3.2 ± 17.6 U/L in the canagliflozin vs. placebo group in the high ALT subgroup (P = 0.0206); no significant difference was shown in the low ALT subgroup (Study 1). In both ALT subgroups, glycosylated hemoglobin (HbA1c) and body weight were significantly reduced in the canagliflozin vs. placebo group (all P < 0.0001). The mean change in ALT at 52 weeks was −16.0 ± 18.8 U/L in the high ALT subgroup (P < 0.0001, Study 2). The incidence of AEs or serious AEs in the high ALT subgroup in the canagliflozin group was similar to that in the placebo group (Study 1) or low ALT subgroup (Studies 1 and 2). Conclusions In T2DM patients with impaired liver function, canagliflozin may improve liver function, reduce HbA1c and body weight, and be well tolerated.

Background and Aims: Identifying patients with steatotic liver disease who are at a high risk of developing HCC remains challenging. We present a deep learning (DL) model to predict HCC development using hematoxylin and eosin-stained whole-slide images of biopsy-proven steatotic liver disease. Approach and Results: We included 639 patients who did not develop HCC for ≥7 years after biopsy (non-HCC class) and 46 patients who developed HCC <7 years after biopsy (HCC class). Paired cases of the HCC and non-HCC classes matched by biopsy date and institution were used for training, and the remaining nonpaired cases were used for validation. The DL model was trained using deep convolutional neural networks with 28,000 image tiles cropped from whole-slide images of the paired cases, with an accuracy of 81.0% and an AUC of 0.80 for predicting HCC development. Validation using the nonpaired cases also demonstrated a good accuracy of 82.3% and an AUC of 0.84. These results were comparable to the predictive ability of logistic regression model using fibrosis stage. Notably, the DL model also detected the cases of HCC development in patients with mild fibrosis. The saliency maps generated by the DL model highlighted various pathological features associated with HCC development, including nuclear atypia, hepatocytes with a high nuclear-cytoplasmic ratio, immune cell infiltration, fibrosis, and a lack of large fat droplets. Conclusions: The ability of the DL model to capture subtle pathological features beyond fibrosis suggests its potential for identifying early signs of hepatocarcinogenesis in patients with steatotic liver disease. Export