Cardiovascular disease is the leading cause of death and causes tremendous suffering, socioeconomic loss, and burden to health systems. Atherosclerosis, a condition that is clinically silent, i.e. it often remains undetected until it is too late, underlies major cardiovascular events such as heart attacks and strokes.

Early identification of people at high risk for such clinical events enables preventive actions. However, conventional risk prediction scores are often not widely adopted in otherwise healthy and symptom-free people. At the same time, medical information is increasingly digitalised. This leads to huge amounts of electronic health data amenable to risk prediction. Yet, conventional approaches fail to handle this data in its entirety and harness it for medical decision-making.

Here, we use artificial intelligence (AI) methods to develop modern risk prediction tools for early identification of people at high risk for major cardiovascular events. This endeavor builds on our previous experience in using machine-learning algorithms for risk prediction. In our multidisciplinary consortium, we aim to validate and improve our models across different hospital networks and populations. Second, we will integrate our models in hospital information systems and assess their impact on daily hospital routine. Lastly, we will address effective risk communication strategies in order to effect behavioral changes in patients.

Our ultimate aim is to develop easy-to-use, accessible, and reliable risk prediction tools that allow early identification of people at high risk in order to set actions to prevent major cardiovascular events and thereby reduce the global impact of cardiovascular disease.

Platzhalterbild für Einbettung
The video is disabled for privacy reasons to prevent unwanted data transfer to YouTube. Please see our privacy policy for more information about what data is transferred to YouTube. Click to activate and watch the video.