Using Artificial Intelligence for the Early Detection of Cardiac Amyloidosis
Description: Cardiac amyloidosis is a particularly morbid cause of heart failure, a common and costly condition affecting over 6 million US adults. Until recently, cardiac amyloidosis was thought to be a rare disease but appears to be a much more common HF cause. Prior studies have revealed early clinical clues of both types of cardiac amyloidosis, such as constellations of symptoms, changes in liver, kidney, blood, and cholesterol tests, and specific changes in echocardiograms and electrocardiograms. Unfortunately, damage caused to the heart and other organs prior to treatment tends to be irreversible. The advent of novel, disease-modifying therapies has increased the importance of early detection and treatment of cardiac amyloidosis to improve survival. Over the past ten years, the rapid adoption of electronic health records, coupled with advances in artificial intelligence, has created the opportunity to integrate diverse data sources to understand the early pathogenesis of cardiac amyloidosis and to detect the disease earlier. The goals of this study are to describe the early manifestations of cardiac amyloidosis on cardiac imaging and to develop and pilot test high-performing, artificial intelligence algorithms, and clinical decision support tools for the early detection of cardiac amyloidosis using diverse data sources.
Funder: American Heart Association
Amount: $230,900
Funding type: fellowship
Funder scheme: Career Development Award
Start date: 2021-07-01
End date: 2024-06-30
Investigators: Faraz Ahmad, Faraz Ahmad
Institution: Northwestern University - Chicago Campus
Funded outputs count: 13
Funder award ID: 856917
OpenAlex ID: G144208136