Non-invasive prediction of non-alcoholic steatohepatitis in Japanese patients with morbid obesity by artificial intelligence using rule extraction technology

AIM To construct a non-invasive prediction algorithm for predicting non-alcoholic steatohepatitis(NASH), we investigated Japanese morbidly obese patients using artificial intelligence with rule extraction technology.METHODS Consecutive patients who required bariatric surgery underwent a liver biopsy during the operation. Standard clinical, anthropometric, biochemical measurements were used as parameters to predict NASH and were analyzed using rule extraction technology. One hundred and two patients, including 79 NASH and 23 non-NASH patients were analyzed in order to create the predictionmodel, another cohort with 77 patients including 65 NASH and 12 non-NASH patients were analyzed to validate the algorithm.RESULTS Alanine aminotransferase, C-reactive protein, homeostasis model assessment insulin resistance, albumin were extracted as predictors of NASH using a recursive-rule extraction algorithm. When we adopted the extracted rules for the validation cohort using a highly accurate rule extraction algorithm, the predictive accuracy was 79.2%. The positive predictive value, negative predictive value,sensitivity and specificity were 88.9%, 35.7%, 86.2% and 41.7%, respectively.CONCLUSION We successfully generated a useful model for predicting NASH in Japanese morbidly obese patients based on their biochemical profile using a rule extraction algorithm.

Ipragliflozin-induced improvement of liver steatosis in obese mice may involve sirtuin signaling

BACKGROUND Sodium glucose cotransporter 2(SGLT2)inhibitors are newly developed oral antidiabetic drugs.SGLT2 is primarily expressed in the kidneys and reabsorbs approximately 90%of the glucose filtered by the renal glomeruli.SGLT2 inhibitors lower glucose levels independently of insulin action by facilitating urinary glucose excretion.The SGLT2 inhibitor ipragliflozin has reportedly improved liver steatosis in animal models and clinical studies.However,the mechanisms by which SGLT2 inhibitors improve liver steatosis are not fully understood.AIM To investigate the ameliorative effects of ipragliflozin on liver steatosis and the mechanisms of these effects in obese mice.METHODS We analyzed 8-wk-old male obese(ob/ob)mice that were randomly divided into a group receiving a normal chow diet and a group receiving a normal chow diet supplemented with ipragliflozin(3 mg/kg or 10 mg/kg)for 4 wk.We also analyzed their lean sex-matched littermates receiving a normal chow diet as another control group. Body weight and liver weight were evaluated, and liverhistology, immunoblotting, and reverse transcription-polymerase chain reactionanalyses were performed.RESULTSHepatic lipid accumulation was significantly ameliorated in ob/ob mice treatedwith 10 mg/kg ipragliflozin compared to untreated ob/ob mice irrespective ofbody weight changes. Ipragliflozin had no appreciable effects on hepatic oxidativestress-related gene expression levels or macrophage infiltration, but significantlyreduced hepatic interleukin-1β (IL-1β) mRNA expression levels. Ipragliflozinincreased both the mRNA and protein expression levels of sirtuin 1 (SIRT1) in theliver. The hepatic mRNA levels of peroxisome proliferator-activated receptor γcoactivator 1α (PGC-1α), peroxisome proliferator-activated receptor α (PPARα),and fibroblast growth factor-21 (FGF21) were also significantly higher inipragliflozin-treated ob/ob mice than in untreated ob/ob mice.CONCLUSIONOur study suggests that the liver steatosis-ameliorating effects of ipragliflozin inob/ob mice may be mediated partly by hepatic SIRT1 signaling, possibly throughthe PGC-1α/PPARα-FGF21 pathway.