How Artificial Intelligence Can Enhance the Diagnosis of Cardiac Amyloidosis: A Review of Recent Advances and Challenges

Abstract

Cardiac amyloidosis (CA) is an underdiagnosed form of infiltrative cardiomyopathy caused by abnormal amyloid fibrils deposited extracellularly in the myocardium and cardiac structures. There can be high variability in its clinical manifestations, and diagnosing CA requires expertise and often thorough evaluation; as such, the diagnosis of CA can be challenging and is often delayed. The application of artificial intelligence (AI) to different diagnostic modalities is rapidly expanding and transforming cardiovascular medicine. Advanced AI methods such as deep-learning convolutional neural networks (CNNs) may enhance the diagnostic process for CA by identifying patients at higher risk and potentially expediting the diagnosis of CA. In this review, we summarize the current state of AI applications to different diagnostic modalities used for the evaluation of CA, including their diagnostic and prognostic potential, and current challenges and limitations.

Artificial Intelligence Assists in the Early Identification of Cardiac Amyloidosis

“…The diagnosis of AL cardiac amyloidosis can be challenging, and delay in diagnosis is often a barrier to accessing appropriate care [ 2 ]. Additionally, AL CA can be rapidly progressive with fatal outcomes if not detected in a timely fashion and targeted treatment such as chemotherapy not initiated promptly [ 3 ].…”

“…TTE in this case had suboptimal endocardial definition and did not permit strain evaluation, in which an apical sparing pattern would be pathognomonic for CA and, if present, potentially prompts further evaluation. In addition to its rarity, patients with CA frequently present with nonspecific signs and symptoms, and given the variety of the diagnostic tests involved with variable sensitivity and specificity, the overall diagnosis of CA is often challenging [ 1 , 2 ].…”

“…Amyloid deposits can involve multiple organs, including, but not limited to, kidney, heart, gastrointestinal tract, nerves, and skin. The diagnosis of AL cardiac amyloidosis can be challenging and requires clinical expertise, and there is often a large testing burden [ 1 , 2 ]. A delay in its diagnosis is often a barrier to accessing appropriate care, and in the case of AL cardiac amyloidosis, which can be rapidly progressive and fatal, early diagnosis is critical [ 3 , 4 ].…”

Chemotherapy Related Cardiotoxicity Evaluation—A Contemporary Review with a Focus on Cardiac Imaging

“…Nuclear imaging with technetium-99 m pyrophosphate scintigraphy (PYP) imaging also plays a role in the evaluation of cardiac transthyretin amyloidosis (ATTR), which falls under the umbrella of cardio-oncology [104,105]. In addition to serum biomarkers, a non-invasive diagnosis of cardiac ATTR can be supported when there are typical TTE/CMR findings (unexplained left ventricular wall thickening ≥ 12 mm, diastolic dysfunction, abnormal GLS on TTE with an apical sparing pattern or diffuse LGE with elevated extracellular volume on CMR).…”

“…The ever-evolving field of AI offers promise for increased efficiency, accuracy, and accessibility in the evaluation of CTRCD [110]. In the general population, many AI and machine learning (ML) models have been developed and validated to predict the risk of cardiovascular outcomes, including systolic and diastolic dysfunction, cardiac amyloidosis, significant valvular heart disease, and arrhythmias [105,[111][112][113].…”