Innovative approaches to atrial fibrillation prediction: should polygenic scores and machine learning be implemented in clinical practice?

Atrial fibrillation (AF) prediction and screening are of important clinical interest because of the potential to prevent serious adverse events. Devices capable of detecting short episodes of arrhythmia are now widely available. Although it has recently been suggested that some high-risk patients with AF detected on implantable devices may benefit from anticoagulation, long-term management remains challenging in lower-risk patients and in those with AF detected on monitors or wearable devices as the development of clinically meaningful arrhythmia burden in this group remains unknown. Identification and prediction of clinically relevant AF is therefore of unprecedented importance to the cardiologic community. Family history and underlying genetic markers are important risk factors for AF. Recent studies suggest a good predictive ability of polygenic risk scores, with a possible additive value to clinical AF prediction scores. Artificial intelligence, enabled by the exponentially increasing computing power and digital data sets, has gained traction in the past decade and is of increasing interest in AF prediction using a single or multiple lead sinus rhythm electrocardiogram. Integrating these novel approaches could help predict AF substrate severity, thereby potentially improving the effectiveness of AF screening and personalizing the management of patients presenting with conditions such as embolic stroke of undetermined source or subclinical AF. This review presents current evidence surrounding deep learning and polygenic risk scores in the prediction of incident AF and provides a futuristic outlook on possible ways of implementing these modalities into clinical practice, while considering current limitations and required areas of improvement.

Impact of calcification modeling to improve image fusion accuracy for endovascular aortic aneurysm repair.

Since the 1990s, endovascular aortic aneurysm repair (EVAR) has become a common alternative to open surgery for the treatment of abdominal aortic aneurysms (AAAs). To aid the deployment of stent-grafts, fluoroscopic image guidance can be enhanced using preoperative simulation and intraoperative image fusion techniques. However, the impact of calcification (Ca) presence on the guidance accuracy of such techniques is yet to be considered. In the present work, we introduce a guidance tool that accounts for patient-specific Ca presence. Numerical simulations of EVAR were developed for 12 elective AAA patients, both with (With-Ca) and without (No-Ca) Ca consideration. To assess the accuracy of the simulations, the image results were overlaid on corresponding intraoperative images and the overlay error was measured at selected anatomical landmarks. With this approach we gained insight into the impact of Ca presence on image fusion accuracy. Inclusion of Ca improved mean image fusion accuracy by 8.68 ± 4.59%. In addition, a positive correlation between the relative Ca presence and the image fusion accuracy was found (R = .753, p < .005). Our results suggest that considering Ca presence in patient-specific EVAR simulations increases the reliability of EVAR image guidance techniques that utilize numerical simulation, especially for patients with severe aortic Ca presence.