Dose-response, efficacy, and safety of oral semaglutide monotherapy in Japanese patients with type 2 diabetes (PIONEER 9): a 52-week, phase 2/3a, randomised, controlled trial

Abstract

Background: Given the unique phenotype of type 2 diabetes in Japanese patients, novel therapies such as oral semaglutide require evaluation in this population. PIONEER 9 aimed to assess the dose-response of oral semaglutide and to compare the efficacy and safety of oral semaglutide with placebo and a subcutaneous GLP-1 receptor agonist in a Japanese population.

Methods: PIONEER 9 was a 52-week, phase 2/3a, randomised, controlled trial done at 16 sites (clinics and university hospitals) in Japan. Japanese patients aged 20 years or older with uncontrolled type 2 diabetes managed by diet or exercise or with oral glucose-lowering drug monotherapy (washed out) were randomly assigned (1:1:1:1:1) to receive double-blind once-daily oral semaglutide (3 mg, 7 mg, or 14 mg) or placebo, or open-label subcutaneous once-daily liraglutide 0·9 mg. The primary endpoint was change in HbA_1c from baseline to week 26 with the trial product (primary) estimand (which assumes all patients remained on trial product without rescue medication use) in all randomly assigned patients. This trial is registered with ClinicalTrials.gov, NCT03018028.

Findings: Between Jan 10, and July 11, 2017, 243 patients were randomly assigned to oral semaglutide 3 mg (n=49), 7 mg (n=49), or 14 mg (n=48), or placebo (n=49), or to liraglutide 0·9 mg (n=48). Changes in HbA_1c from baseline (mean 8·2%) to week 26 were dose-dependent with oral semaglutide (mean change -1·1% [SE 0·1] for oral semaglutide 3 mg, -1·5% [0·1] for 7 mg, and -1·7% [0·1] for 14 mg), -0·1% (0·1) with placebo, and -1·4% (0·1) with liraglutide 0·9 mg. Estimated treatment differences for change in HbA_1c compared with placebo were -1·1 percentage points (95% CI -1·4 to -0·8; p<0·0001) for oral semaglutide 3 mg, -1·5 percentage points (-1·7 to -1·2; p<0·0001) for oral semaglutide 7 mg, and -1·7 percentage points (-2·0 to -1·4; p<0·0001) for oral semaglutide 14 mg. Estimated treatment differences for change in HbA_1c compared with liraglutide 0·9 mg were 0·3 percentage points (95% CI -0·0 to 0·6; p=0·0799) for oral semaglutide 3 mg, -0·1 percentage points (-0·4 to 0·2; p=0·3942) for oral semaglutide 7 mg, and -0·3 percentage points (-0·6 to -0·0; p=0·0272) for oral semaglutide 14 mg. Gastrointestinal events, predominantly of mild or moderate severity, were the most frequently reported class of adverse event with oral semaglutide: constipation was most common, occurring in five to six (10-13%) patients with oral semaglutide, three (6%) with placebo, and nine (19%) with liraglutide 0·9 mg.

Interpretation: This study showed that oral semaglutide provides significant reductions in HbA_1c compared with placebo in a dose-dependent manner in Japanese patients with type 2 diabetes, and has a safety profile consistent with that of GLP-1 receptor agonists.

Funding: Novo Nordisk.