Skip to main content English

AI-enabled cardiac amyloidosis screening

Cardiac Amyloidosis
Cardiac amyloidosis, a severe condition characterized by the build-up of misfolded proteins (amyloid) in the heart muscle, substantially affects heart performance, leading to heart failure and potentially death if not diagnosed early. Recognizing the urgency for early detection, an international team headed by scientists at the Medical University of Vienna (MedUni Vienna) has pioneered an artificial intelligence (AI) system capable of automatically identifying cardiac amyloidosis with high reliability. This breakthrough was reported in the internationally renowned journal "The Lancet Digital Health".

The AI system was developed and validated on data from more than 16,000 patients across nine centers in Europe and Asia, including the Vienna General Hospital. All patients received a nuclear medicine imaging scan referred to as scintigraphy. Scintigraphy, a nuclear medicine technique, is instrumental in diagnosing various conditions, including heart diseases. The AI tool, developed under the leadership of Christian Nitsche (Department of Medicine II, Meduni Vienna) and Marcus Hacker (Department of Biomedical Imaging and Image-guided Therapy, Meduni Vienna), promises to allow the underdiagnosis of cardiac amyloidosis by the introduction of an AI-enabled screening approach.

Tested against the diagnostic skills of nuclear medicine specialists, the AI was consistently able to perform at least as good as the medical specialists. Further, the study, first-authored by Clemens Spielvogel and David Haberl (both Department of Biomedical Imaging and Image-guided Therapy, Meduni Vienna), explored how diagnoses by the AI correlated with the future risk for heart failure and mortality. The study’s results revealed that patients for whom the AI suspected cardiac amyloidosis, had significantly higher risks compared to those without a suspicion for the disease.

Given the recent advent of therapies within the EU that can slow the disease's progression, accurate and early detection is crucial. The AI system may facilitate widespread screening among scintigraphy patients, assisting medical experts to detect cardiac amyloidosis earlier, thereby underscoring the study's significant impact on patient care.


Diagnosis and prognosis of abnormal cardiac scintigraphy uptake at risk for cardiac amyloidosis using artificial intelligence: An international, multi-center, multi-tracer development and validation study
Clemens P. Spielvogel, David Haberl, Katharina Mascherbauer, Jing Ning, Kilian Kluge, Tatjana Traub-Weidinger, Rhodri H. Davies, Iain Pierce, Kush Patel, Thomas Nakuz, Adelina Göllner, Dominik Amereller, Maria Starace, Alice Monaci, Michael Weber, Xiang Li, Alexander R. Haug, Raffaella Calabretta, Xiaowei Ma, Min Zhao, Julia Mascherbauer, Andreas Kammerlander, Christian Hengstenberg, Leon J. Menezes, Roberto Sciagra, Thomas A. Treibel, Marcus Hacker and Christian Nitsche

The Lancet Digital Health, Apr 2024