Machine Learning in Critical Care: The Role of Diabetes and Age in Acute Coronary Syndromes

Background: To investigate the impact of early, within 24 hours, percutaneous coronary intervention (PCI) compared with only routine medical treatment on clinical outcomes in a large international cohort of patients with non-ST elevation acute coronary syndrome (NSTE-ACS) and diabetes.   Methods: Cohort study using a population- based registry (International Survey of Acute Coronary Syndromes in Transitional Countries [ISACS-TC]) enrolled in 41 hospitals participating in the ISACS-TC in 12 European countries between October 2010 and April 2016. We identified 1,250 patients with diabetes and NSTE-ACS. The primary endpoint was 30-day all-cause mortality. The secondary endpoint was the composite outcome of 30-day all-cause mortality and left ventricular dysfunction (ejection fraction < 40%). We undertook analyses to explore the heterogeneity of treatment effects using meta-classification (MC) algorithms followed by propensity score matching and inverse probability-of-treatment weighting (IPTW) from a landmark of 24 hours from hospitalization. Findings: Of 1,250 NSTE-ACS first-day survivors with diabetes (median age 67 year; 59%, men), 470 (38%) received early PCI and 780 routine medical treatment. The overall 30-day all-cause mortality rates were higher in the routine medical treatment than the early PCI group (6·3% vs. 2·5%). The prediction results of the MC algorithms accounted for only one interaction term that was statistically significant: age ≥ 65 years. After propensity-matched analysis as well as IPTW, early PCI was associated with reduced 30-day all-cause mortality in the older age (OR: 0·35; 95%CI: 0·14 to 0·92 and 0·43; 95%CI: 0·21 to 0·86, respectively), whereas younger age had no association with the primary endpoint. Similar results were also obtained for the secondary endpoint. Interpretation: Among patients with diabetes hospitalized for NSTE-ACS, an early, within 24 hours, PCI strategy is associated with reduced odds of 30-day mortality only for patients aged 65 years or over. MC algorithms provide accurate identification of treatment effect modifiers.   Funding Statement: None   Declaration of Interests: No competing interest exist. Ethics Approval Statement: The study was approved by the local research ethics committee from each hospital.