Optimize Risk Prediction After Myocardial Infarction: The ORACLE Study
Optimize Risk Prediction After Myocardial Infarction Through Artificial Intelligence and Multidimensional Evaluation: The ORACLE Study
About This Trial
Background. Myocardial infarction (MI) is a leading cause of death worldwide. After MI, longterm antithrombotic therapy is crucial to prevent recurrent events, but increases bleeding, that also impacts morbidity and mortality. Giving these competing risks prediction tools to forecast ischemic and bleeding are of paramount importance to inform clinical decisions, but their current precision is limited. Improve events prediction, by discovering novel and innovative markers of risk would have a tremendous impact on therapeutic decisions and patients' outcome. Objectives. Discover novel "computational biomarkers" of risk and improve current standards of risk prediction by using innovative multidimensional information from wearable devices, biomarkers, behavioural patterns and non-invasive imaging, integrated through artificial intelligence computation. Outcomes. The primary outcomes of interest for this analysis are bleeding and ischemic events occurring in or outside the hospital at longest available follow-up. Bleeding will be categorised according to the Bleeding Academic Research Consortium (BARC) definition. The occurrence of major adverse cardiovascular events (MACE), a composite of cardiovascular death, MI, definite stent thrombosis and stroke will be collected according to the Academic Research Consortium-2 classification.
Who May Be Eligible (Plain English)
Original Eligibility Criteria
View original clinical language
Treatments Being Tested
data collection
The ORACLE program is a prospective, deep phenotyping, study based on multimodal information and artificial intelligence computation. We will prospectively collect in-hospital and out-of-hospital data of a large cohort of patients presenting with MI, including data from wearable devices recording continuous ECG, interstitial-fluids, non-invasive blood pressure and mobility, behavioural patterns from a dedicated mobile application, blood and urine biomarkers and non-invasive imaging. We will leverage on AI, using statistical learning methods and neural networks, to explore patterns and higher order interactions within the data to provide novel "computational biomarkers" of ischemic and bleeding risk.