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.
Patients with Myocardial Infarction (i.e. hospitalization for ST- segment elevated, non-ST-segment elevated myocardial infarction or unstable angina) undergoing invasive management and at high risk of clinical events (i.e. presence of at least two of these high risk criteria: age >65 years, diabetes mellitus, multivessel disease, peripheral artery disease, chronic kidney disease, prior stroke anytime or prior TIA in the last 6 months, prior MI, complex PCI, Prior PCI/CABG, heart failure, BMI>27, anticipated long term use of an oral anticoagulant, haemoglobin less than 11g/dl, spontaneous bleeding requiring hospitalization or transfusion in the past 12 months, bleeding diathesis* active malignancy other than skin, previous spontaneous intracranial hemorrhage).
Systemic conditions associated with an increased bleeding risk (e.g. haematological disorders, including a history of or current thrombocytopaenia defined as a platelet count <100,000/mm3 (<100 x 10^9/L), or any known coagulation disorder associated with increased bleeding risk.
Age < 18 years
Low life expectancy (<1 year)
Pregnant or breastfeeding women
Evidence at coronary angiography of non-significant coronary artery disease (<30% in the left main stem or <50% in the other coronary segments)
Patients with Myocardial Infarction (i.e. hospitalization for ST- segment elevated, non-ST-segment elevated myocardial infarction or unstable angina) undergoing invasive management and at high risk of clinical events (i.e. presence of at least two of these high risk criteria: age \>65 years, diabetes mellitus, multivessel disease, peripheral artery disease, chronic kidney disease, prior stroke anytime or prior TIA in the last 6 months, prior MI, complex PCI, Prior PCI/CABG, heart failure, BMI\>27, anticipated long term use of an oral anticoagulant, haemoglobin less than 11g/dl, spontaneous bleeding requiring hospitalization or transfusion in the past 12 months, bleeding diathesis\* active malignancy other than skin, previous spontaneous intracranial hemorrhage).
Cohort
Prospective
data collection
Other interventionThe 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.
Frequency and severity of bleeding and ischemic events
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.
Number of death, stroke, recurrent MI, stent thrombosis, heart failure, hospitalization
Death will be defined as death from cardiovascular causes or cerebrovascular causes and any death without another known cause. Stroke will be defined as an acute new neurological deficit ending in death or lasting \>24 hours not due to another readily identifiable cause such as trauma. Recurrent MI is defined according to the fourth universal definition of MI. Stent thrombosis will be classified as definite, probable or possible according to the Academic Research Consortium (ARC) definition. New-onset heart failure requiring re-hospitalisation or unplanned medical contact for heart failure symptoms will be evaluated. Recurrent hospitalization for acute coronary syndrome, unstable angina or clinically-indicated urgent revascularization will also be evaluated.
Quality life and adherence to treatment
Patients' quality of life and adherence to treatment will be evaluated with: * Health mobility and mental scales (i.e. EQ-5D-5L and SF-12v2) * Anginal status according to the Seattle Angina questionnaire (SAQ) * Functional status according to the Kansas City Cardiomiopathy questionnaire (KCCQ) * Modified Borg Dyspnoea Scale
Click on the lead sponsor to view all of their trials.
Fundación Pública Andaluza para la Investigación de Málaga en Biomedicina y Salud
Lead sponsor
European Research Council
Collaborator
