Project description
Computational biomarkers for myocardial infarction risk
Myocardial infarction (MI) is a major global cause of death but current prediction tools for ischaemic and bleeding risks after therapy suffer from limited precision. Funded by the European Research Council, the ORACLE project aims to improve risk prediction by utilising multidimensional data from wearable devices, biomarkers, and non-invasive imaging. The idea is to identify novel computational biomarkers for risk using AI to analyse data from a large cohort of MI patients. The project is expected to generate clinically guided AI algorithms and integrate them into practice for informed treatment decisions.
Objective
Myocardial infarction (MI) is a leading cause of death worldwide. After MI, long-term 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. I hypothesize that using innovative multidimensional information from wearable devices, biomarkers, behavioral patterns and non-invasive imaging, integrated through artificial intelligence computation, we may discover novel “computational biomarkers” of risk and improve current standards of risk prediction. In this project, I will enroll a large cohort of MI patients, whereby prospective collection of consolidated and innovative potential risk predictors will take place, in order to generate a comprehensive and multidimensional dataset. I will collect data from state-of-the-art non-invasive imaging, blood biomarkers, wearable medical devices of continuous heart electrical activity, sweat, mobility and behavioral patterns to create a large physiological time series allowing patients’ deep phenotyping. We will therefore analyze data leveraging artificial intelligence computation to find relevant associations with clinical outcomes, and compare new algorithms with current risk prediction tools. This research will increase our knowledge on bleeding and ischemic risk factors, enabling enhanced capability predictions models. In the near future, we hypothesize that our clinically-guided Artificial Intelligence algorithm might be integrated in clinical practice, helping clinicians to inform treatment decisions, patients to better understand their risk profile, finally setting a common ground for shared patient/physician decisions.
Fields of science
Keywords
Programme(s)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Topic(s)
Funding Scheme
HORIZON-ERC - HORIZON ERC GrantsHost institution
29590 MALAGA
Spain