AI System Automatically and Reliably Detects Cardiac Amyloidosis Using Scintigraphy Imaging

Cardiac amyloidosis, a condition characterized by the buildup of abnormal protein deposits (amyloids) in the heart muscle, severely affects heart function and can lead to heart failure or death without prompt treatment. Considering the importance of early detection, researchers have now developed an artificial intelligence (AI) system that automatically and reliably detects cardiac amyloidosis during scintigraphy imaging.

The new AI system was developed and validated by an international research team led by Medical University Vienna (Vienna, Austria), utilizing data sets from 16,000 patients who underwent a scintigraphy imaging examination across Europe and Asia between 2010 and 2020. Scintigraphy, a nuclear medicine procedure, is instrumental in identifying various diseases, such as cancer, thyroid, kidney, and heart disease. The AI tool significantly enhances the speed of diagnosing cardiac amyloidosis by automatically detecting the condition during the scintigraphy imaging process.

The AI system’s accuracy was also rigorously tested by comparing it with the diagnostic capabilities of medical professionals. The results showed that the AI tool could identify cardiac amyloidosis with a reliability that matches or even surpasses that of medical experts. Further analysis by the research team delved into the relationship between AI-detected diagnoses of cardiac amyloidosis and subsequent health outcomes. The findings revealed that patients diagnosed with the condition by the AI tool faced double the risk of mortality and a more than seventeen-fold increase in the risk of developing heart failure compared to those not diagnosed with amyloidosis by the AI system.

"In the future, our findings and the technology we have developed could enable screening for cardiac amyloidosis among all scintigraphy patients, with the AI system evaluating the image data in parallel with doctors," said Clemens Spielvogel from MedUni Vienna's Department of Biomedical Imaging and Image-guided Therapy.

Related Links:
Medical University Vienna