Metformin Hydrochloride/Rosiglitazone Maleate

Hepatotoxicity is a major cause of drug withdrawal from the market. To reduce the drug attrition induced by hepatotoxicity, an accurate and efficient hepatotoxicity prediction system must be constructed. In the present study, we constructed a three-level hepatotoxicity prediction system based on different levels of adverse hepatic effects (AHEs) combined with machine learning, using (1) an end point, hepatotoxicity; (2) four hepatotoxicity severity degrees; and (3) specific AHEs. After collecting and curing 15 873 compound-AHE pairs associated with 2017 compounds and 403 AHEs, we constructed 27 models with three end point levels with the random forest algorithm, and obtained accuracies ranging from 67.0 to 78.2% and the area under receiver operating characteristic curves (AUCs) of 0.715-0.875. The 27 models were fully integrated into a tiered hepatotoxicity prediction system. The existence of hepatotoxicity existence, severity degree, and potential AHEs for a given compound could be inferred simultaneously and systematically. Thus, the tiered hepatotoxicity prediction system allows researchers to have significant confidence in confirming compound hepatotoxicity, analyzing hepatotoxicity from multiple perspectives, obtaining warnings for the potential hepatotoxicity severity, and even rapidly selecting the proper in vitro experiments for hepatotoxicity verification. We also applied three external sets (11 drugs or candidates that failed in clinical trials or were withdrawn from the market, the PharmGKB (offsides) database, and an herbal hepatotoxicity data set) to test and validate the prediction ability of our system. Furthermore, the hepatotoxicity prediction system was adapted into a flow framework based on the Konstanz Information Miner, which was made available for researchers.

At present, China has listed the compound tablet containing a fixed dose of rosiglitazone and metformin, Avandamet, which may improve patient compliance. The aim of this study was to evaluate the efficacy and safety of Avandamet or uptitrated metformin treatment in patients with type 2 diabetes inadequately controlled with metformin alone.

This study was a 48-week, multicenter, randomized, open-labeled, active-controlled trial. Patients with inadequate glycaemic control (glycated hemoglobin [HbA1c] 7.5-9.5%) receiving a stable dose of metformin (≥1500 mg) were recruited from 21 centers in China (from 19 November, 2009 to 15 March, 2011). The primary objective was to compare the proportion of patients who reached the target of HbA1c ≤7% between Avandamet and metformin treatment.

At week 48, 83.33% of patients reached the target of HbA1c ≤7% in Avandamet treatment and 70.00% in uptitrated metformin treatment, with significantly difference between groups. The target of HbA1c ≤6.5% was reached in 66.03% of patients in Avandamet treatment and 46.88% in uptitrated metformin treatment. The target of fasting plasma glucose (FPG) ≤6.1 mmol/L was reached in 26.97% of patients in Avandamet treatment and 19.33% in uptitrated metformin treatment. The target of FPG ≤7.0 mmol/L was reached in 63.16% of patients in Avandamet treatment and 43.33% in uptitrated metformin treatment. Fasting insulin decreased 3.24 ± 0.98 μU/ml from baseline in Avandamet treatment and 0.72 ± 1.10 μU/ml in uptitrated metformin treatment. Overall adverse event (AE) rates and serious AE rates were similar between groups. Hypoglycaemia occurred rarely in both groups.

Compared with uptitrated metformin, Avandamet treatment provided significant improvements in key parameters of glycemic control and was generally well tolerated.

ChiCTR-TRC-13003776.