Descrizione del progetto
Biomarcatori computazionali per il rischio di infarto miocardico
Sebbene l’infarto miocardico sia una delle principali cause di morte a livello globale, gli attuali strumenti di previsione dei rischi ischemici ed emorragici in seguito alla terapia volta a trattarlo sono caratterizzati da una precisione limitata. Finanziato dal Consiglio europeo della ricerca, il progetto ORACLE si prefigge di migliorare le previsioni di questi rischi utilizzando dati multidimensionali provenienti da dispositivi indossabili, biomarcatori e tecniche immaginografiche non invasive. L’idea del progetto è quella di identificare nuovi biomarcatori computazionali del rischio mediante l’impiego dell’intelligenza artificiale (IA) al fine di analizzare i dati di un’ampia coorte di pazienti colpiti da infarto miocardico. In base alle aspettative, ORACLE dovrebbe generare algoritmi di IA basati su dati clinici e integrarli nella pratica con l’obiettivo di consentire di prendere decisioni terapeutiche informate.
Obiettivo
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.
Campo scientifico
Parole chiave
Programma(i)
- HORIZON.1.1 - European Research Council (ERC) Main Programme
Argomento(i)
Meccanismo di finanziamento
HORIZON-ERC - HORIZON ERC GrantsIstituzione ospitante
29590 MALAGA
Spagna