ORACLE

Optimize risk prediction after myocardial infarction through artificial intelligence and multidimensional evaluation

ABSTRACT

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, behavioural 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 enrol 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 behavioural 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.

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.

Project Information

Principal Investigator

Dr. Francesco Costa

📩app.oraclemi@gmail.com

Team

  • Prof. Andrés Ortiz – Computational Scientist
  • Dr. Arancha Diaz Exposito – Investigador Clinico
  • Dr. Jorge Rodriguez-Capitan – Investigador Clinico
  • Dr. Jose Manuel Garcia Pinilla – Investigador Clinico
  • Dr. Cristobal Urbano Carrillo – Investigador Clinico
  • Dr. Juan Jose Gomez Doblas – Investigador Clinico
  • Prof. Manuel Jimenez-Navarro – Investigador Clinico

Follow our social Networks

ORACLE MI

The ORACLE MI mobile app, developed within the context of the ORACLE study, automatically determines patients’ exposure to environmental pollutants, offering a unique opportunity to study how these factors may impact myocardial infarction patients in a personalized way, identify new risk factors, and improve prevention and treatment strategies. Additionally, the app sends quality-of-life and symptom surveys for precise follow-up, provides updates on secondary prevention of myocardial infarction and key research findings, and offers real-time air quality information to help patients make informed health decisions.

 NEWS ABOUT THE PROJECT

ORACLE en los medios

El Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina se enorgullece de anunciar que han sido seleccionado para albergar un proyecto financiado con una "ERC Starting Grant" de la Comisión Europea. Esta subvención, que asciende a un millón y...

Read more