Abstract
Introduction: Sodium-glucose cotransporter-2 (SGLT2) inhibitors have well-documented cardioprotective effects in broad groups of patients with type 2 diabetes mellitus (T2DM) but are underused, in part due to high cost. Individualized prediction of the magnitude of cardiovascular risk reduction may allow more targeted use. Hypothesis: A machine learning decision support tool can predict ASCVD effect of canagliflozin therapy in T2DM based on each patient’s unique phenotypic profile. Methods: We constructed a topological representation of the Canagliflozin Cardiovascular Assessment Study (CANVAS) using 75 baseline variables collected from 4327 patients with T2DM randomly assigned to canagliflozin (n=2886) or placebo (n=1441). Within each patient’s 5% topological neighborhood, we calculated age- and sex-adjusted risk estimates for major adverse cardiovascular events (MACE: cardiovascular death, myocardial infarction, stroke). An extreme gradient boosting algorithm was trained to predict the personalized MACE effect of canagliflozin using features consistently associated with benefit in topological analyses and was validated in the independent CANVAS-R trial (n=5808, randomized 1:1 to canagliflozin or placebo). Results: In CANVAS (mean age 60.9±8.1 years, 33.9% women) 1605 (37.1%) patients had a neighborhood hazard ratio lower (more protective) than the overall effect estimate of 0.86 for the primary composite outcome of time to MACE ( A ). A 15-variable tool, INSIGHT, was developed in CANVAS ( B ), and subsequently tested in CANVAS-R (mean age 62.4±8.4 years, 2164 (37.3%) women) where it identified patient phenotypes with higher MACE benefit of canagliflozin (adj. HR 0.60 [95% CI: 0.41-0.89] ( C ) versus 0.99 [95% CI: 0.76-1.29] ( D ); P-value for interaction=0.04). Conclusions: We present an evidence-based, machine learning-guided algorithm to personalize the prescription of SGLT2 inhibitors for cardiovascular benefit in patients with T2DM.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
