RecruitingNCT06993415

Optimize Risk Prediction After Myocardial Infarction: The ORACLE Study

Optimize Risk Prediction After Myocardial Infarction Through Artificial Intelligence and Multidimensional Evaluation: The ORACLE Study

Sponsor

Fundación Pública Andaluza para la Investigación de Málaga en Biomedicina y Salud

Enrollment

750 participants

Start Date

Jun 1, 2025

Study Type

OBSERVATIONAL

Conditions

Myocardial Infarction (MI)

Summary

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.

Eligibility

Min Age: 18 Years

Inclusion Criteria2

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.

Exclusion Criteria5

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)
Subject belongs to a vulnerable population (per investigator's judgment), subject unable to read or write, or other conditions that unable the patient to fully comprehend and comply to the study procedures as per investigator's judgement

Interested in this trial?

Get notified about updates and connect with the research team.

Interventions

OTHERdata 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.