AimTo assess the relationship of sodium‐glucose cotransporter‐2 inhibitors (SGLT2i), glucagon‐like peptide‐1 receptor analogues (GLP‐1RA) and their combination (SGLT2i + GLP‐1RA) with 5‐year risk of all‐cause mortality, hospitalization and cardiovascular/macrovascular disease in people with type 2 diabetes.Materials and MethodsRetrospective cohort analysis of 2.2 million people with type 2 diabetes receiving insulin across 85 health care organizations using a global federated health research network. Three intervention cohorts (SGLT2i, GLP‐1RA and SGLT2i + GLP‐1RA) were compared against a control cohort (no SGLT2i/GLP‐1RA). Propensity score matching for age, ischaemic heart disease, sex, hypertension, chronic kidney disease, heart failure and glycated haemoglobin was used to balance cohorts 1:1 (SGLT2i, n = 143 600; GLP‐1RA, n = 186 841; SGLT‐2i + GLP‐1RA, n = 108 504). A sub‐analysis comparing combination and monotherapy cohorts was also performed.ResultsThe intervention cohorts showed a reduced hazard ratio (HR, 95% confidence interval) over 5 years compared with the control cohort for all‐cause mortality (SGLT2i 0.49, 0.48‐0.50; GLP‐1RA 0.47, 0.46‐0.48; combination 0.25, 0.24‐0.26), hospitalization (0.73, 0.72‐0.74; 0.69, 0.68‐0.69; 0.60, 0.59‐0.61) and acute myocardial infarct (0.75, 0.72‐0.78; 0.70, 0.68‐0.73; 0.63, 0.60‐0.66), respectively. All other outcomes showed a significant risk reduction in favour of the intervention cohorts. The sub‐analysis showed a significant risk reduction in all‐cause mortality for combination therapy versus SGLT2i (0.53, 0.50‐0.55) and GLP‐1RA (0.56, 0.54‐0.59).ConclusionsSGLT2i, GLP‐1RAs or combination therapy confers mortality and cardiovascular protection in people with type 2 diabetes over 5 years. Combination therapy was associated with the greatest risk reduction in all‐cause mortality versus a propensity matched control cohort. In addition, combination therapy offers a reduction in 5‐year all‐cause mortality when compared directly against either monotherapy.