MATHIAS
Generation of an automatic learning model for more accurate stroke risk prediction in patients already at high risk of atrial fibrillation (AF), prior to diagnosis of AF due to an episode of stroke.
Are you interested?Need
Atrial Fibrillation (AF) is the most prevalent heart rhythm disorder linked to aging demographics and known and not so well known risk factors. It is clearly associated with serious health risks, especially the risk of stroke which is more severe and clinically complex, as well as being associated with an increased risk of residual disability. Furthermore, in up to 30% of cases, this rhythm disturbance was unknown and, therefore, untreated when the stroke or thromboembolic complication occurred. Both undiagnosed HACE and a high risk of HACE are associated with an increased thromboembolic risk that could be decreased by early and appropriate anti-cogulant treatment.
Solution
Through personalized assessment of risk of adverse cardiovascular event, can be improved by prevention of individual treatment strategies, considering factors such as anticoagulation strategies, rhythm control versus rate control, catheter ablation versus medical therapy, and risk factor modification, along with the incorporation of advanced machine learning techniques and comparison of predictive results with the most widely used scale (the CHA2DS2-VASc variables).
Objective
Improve patient outcomes and reduce healthcare costs by advancing the field of personalized medicine in the management of AF.