ERA-NET: Systems medicine for diagnosis and stratification of atrial fibrillation

The goal for the SysAFib project is to predict recurrence of atrial fibrillation (AF) in patients that have been treated with atrial ablation. AF is the most common rhythm disorder in the heart, and gives rise to substantial health problems for millions of people world-wide. Ablation is a form of treatment where one enters the atria with a catheter, and supplies energy to warm up the tissue in certain areas within the atria. The purpose is to create lines of scar tissue that block electrical signals and thereby eliminate abnormal electrical activity. Ablation is the most effective known treatment of AF, but AF still reoccurs in many patients, and they need to go through multiple treatments. The purpose of the SysAFib project is to develop advanced analysis tools and models that can make it easier to identify patients at high risk of recurrence. The project has developed and tested methods for predicting AF recurrence based on individual data sources such as genetics, medical images, and ECG signals. We have found that all the methods are able to predict AF recurrence, and they are in some cases better than existing methods, but the difference is not very large. In the last phase of the project we have worked on combining all the sources into a single predictor, which we believe will give improved prediction over existing methods. The first tests have been promising, and the method is currently being tested on an existing patient database at Maastricht University, and on new patients being enrolled at Oslo University Hospital in the fall of 2019 and early 2020. The necessary data from each patient is collected and shared with the other partners, who perform their analysis and arrive at a prediction of whether the patient will have recurrent AF or not. The predictions are then combined into a single score that indicates the patient's risk of AF recurrence. Finally, the quality of this score is evaluated through comparison with the actual patient outcome.

The project has led to a substantial knowledge increase for the individual project partners, and also for the atrial fibrillation research community, through a number of published research results. Clinicians have been closely involved in the project, and the knowledge gained will potentially lead to improved clinical decisions and treatment of patients. However, the most significant impact of the research project is linked with the results of the prospective study of the combined risk score, which is ongoing but not yet completed. Improved prediction of AF recurrence could have important consequences both for the individual patient and for society as a whole. A decision support tool to improve risk stratification and patient follow-up may lead to a change in clinical practice and improve the long-term outcome for AF patients.

Atrial fibrillation (AF) is the most common cardiac arrhythmia, characterized by chaotic electrical activation of the atria, preventing synchronized contraction. More than 6 million Europeans suffer from this arrhythmia and age is the most powerful predictor of risk. Life-threatening complications and fast progression to persistent or permanent forms call for as early as possible diagnosis and effective treatment of AF. AF is often treated with anti-arrhythmic drugs, with limited efficacy and safety. Atrial ablation, an invasive procedure, is more effective. This procedure is by no means optimized, however, and AF may reoccur. The efficacy of first time ablation may range from 30%-75% depending on the individual patient and disease, such that multiple ablation procedures may be recommended. Thus it is critical to understand whether an ablation procedure is likely to benefit a particular patient with AF, and whether the arrhythmia is likely to reoccur in this patient, in order to maximize positive patient outcomes and ensure judicious resource allocation in our healthcare systems. Currently, however, there are no decision support tools at the European level enabling clinicians to access integrated AF patient data together with predictive models to facilitate prognosis and subsequent treatment planning. The aim of SysAFib is to integrate the existing sources of knowledge using systems medicine approach into a focused decision support system to determine which patients are good candidates for atrial ablation and which patients are at risk for arrhythmia recurrence following the procedure. This would be impossible to develop to the stage of a demonstrator project without a strong European partnership of individually world-leading scientific, clinical, and experimental competencies. Another key aspect of the project concerns the development and pursuit of a comprehensive dissemination and exploitation strategy.