This is confirmed by a study published in The Lancet that has had the participation of researchers from the Bellvitge University Hospital and IDIBELL.
The algorithm, based on data from about 20,000 patients, will allow in the future to decide the best therapeutic option for each person to avoid new episodes of heart failure The article establishes the bases for future studies in which patients can be treated according to the strategies recommended for these tools.
New tools based on artificial intelligence are better than current tools to predict the chances that a person who has been discharged from an acute coronary syndrome (myocardial infarction or angina pectoris) will die or suffer a new serious episode of bleeding or myocardial ischemia during the year after discharge, according to the conclusions of an international multicenter study just published in The Lancet.
Researchers from the Bellvitge University Hospital and IDIBELL also participated in the study, led by specialists from the University of Turin (Italy).
Patients who have recovered from an acute coronary syndrome are at increased risk of having another heart attack, bleeding, or other complications. To prevent it, they often receive dual antiplatelet therapy, but this therapy, while reducing the risk of myocardial ischemia, increases the risk of bleeding. This makes it very important for doctors to know what specific risk each patient has, in order to individualize treatments and take a further step in the application of personalized medicine in heart disease.
Although statistical methods have been in existence for years that make this prediction from various clinical parameters, until now these tools have had limited precision. The study authors initially created and tested four new risk stratification models that process data with machine learning systems. A total of 25 clinical, therapeutic, angiographic, and procedural variables were introduced into these models, retrospectively extracted from two registries of 19,826 patients admitted between 2003 and 2016 in various centers around the world, including the Bellvitge University Hospital, along with the data. of the subsequent evolution of the patients.
To confirm the performance of the new models, the most effective of them, called PRAISE, was then applied to another set of 3,444 patients and compared with the risk assessment tools used so far. The final results have shown that the new tool based on artificial intelligence predicts mortality, the risk of bleeding and the risk of suffering a new heart attack much better.
Dr. Albert Ariza, one of the authors of the study, highlights that "the advantage of machine learning methods is that they apply algorithms to large and varied sets of data, capturing relationships between these data that simpler systems cannot capture." Ariza, who is coordinator of the Cardiological Intensive Care Unit of the Cardiology Service of the Hospital de Bellvitge and a researcher at IDIBELL, stresses that these are tools “that are beginning to be used progressively and have already shown their usefulness in some other clinical setting; We hope that they will soon be available to all cardiologists to help us make decisions based on personalized risk assessment ”.
Now, the algorithm must be validated in future studies where patients receive the treatment recommended by PRAISE, especially regarding the duration of dual antiplatelet therapy.