| Title: | Prognostic value of deep learning-based retinal image analysis, metabolomics, genomics and environmental and behavioral exposures in patients with cardiac arrhythmias |
| Lead Institution: | Weill Cornell Medical College |
| Principal investigator: |
Application 137851
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
About
Abnormal heart rhythms are associated with various complications such as a reduced exercise tolerance, heart failure, stroke, and death. Abnormal heart rhythms more frequently occur in patients with heart disease or cardiac risk factors such as high blood pressure and in those with underlying genetic conditions. However, it is often very difficult to predict whether an abnormal heart rhythm will occur in the future even if risk factors are present. Even more importantly, it can be very challenging to determine which patients are most likely to have complications because of the abnormal heart rhythm. Imaging tests allow us to obtain a vast amount of information to assess the heart function and the general health of the cardiovascular system. This has already transformed the evaluation of patients with abnormal heart rhythms. However, it is likely that there is a lot more information we can obtain from those tests. One of the most promising ways to accurately evaluate medical images is to use artificial intelligence (AI). AI is already widely used to analyze various images and can perform tasks such as facial recognition better than any human. In addition, AI-based image analysis can be used to develop self-driving cars or even generate entirely new images based on certain prompts, but one of the most impactful applications may be in medicine. We are planning to apply AI-based techniques to images of the retina as those images are easy to obtain and because the retina contains a large number of small blood vessels that can provide information about the general health of the person's cardiovascular system. We are hoping to get a better understanding of subtle changes that can predispose patients to abnormal heart rhythms and possible complications. This could lead to earlier identification of high-risk patients and may allow appropriate interventions (for example medications or procedures such as the placement of a defibrillator) that can help prevent poor outcomes.1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 17703 | Utilization of Serum Metabolomics and Polygenic Risk Scores in a Novel Risk Stratification Tool for the Prediction of Incident Atrial Fibrillation | Subhanik Purkayastha (+9) | 2026 | Circulation Arrhythmia and Electrophysiology |
Enabling scientific discoveries that improve human health