Myocardial infarction in type 2 diabetes using sodium–glucose co-transporter-2 inhibitors, dipeptidyl peptidase-4 inhibitors or glucagon-like peptide-1 receptor agonists: proportional hazards analysis by deep neural network based machine learning

Analysis of 199,116 patients showed a 37% lower risk of myocardial infarction for those using GLP-1 receptor agonists compared to dipeptidyl peptidase-4 inhibitors.

• Sodium-glucose co-transporter-2 inhibitors and glucagon-like peptide-1 receptor agonists are associated with a significantly lower risk of myocardial infarction compared to dipeptidyl peptidase-4 inhibitors.
• The hazard ratio for myocardial infarction with SGLT-2 inhibitors was 0.81 and for GLP-1 receptor agonists was 0.63, indicating a reduced risk.
• GLP-1 receptor agonists also demonstrated a significantly lower risk of myocardial infarction compared to SGLT-2 inhibitors, with a hazard ratio of 0.77.
• Receiver operating characteristics analysis indicated that machine learning provided higher precision in predicting myocardial infarction than logistic regression.
• The study's population primarily consisted of patients with commercial health plans, which may limit the generalizability of the findings.

AI simplified