EUVIMEDEUVIMED entdecken
Multizentrische Studie

Machine Learning to Automatically Differentiate Hypertrophic Cardiomyopathy, Cardiac Light Chain, and Cardiac Transthyretin Amyloidosis: A Multicenter CMR Study

Lukas Damian Weberling iD, Andreas Ochs iD, Mitchel Benovoy, Fabian Aus dem Siepen iD, Janek Salatzki iD, Evangelos Giannitsis iD, Chong Duan, Kevin Maresca iD, Yao Zhang, Jan Möller, Silke Friedrich, Stefan Schönland und 4 weitere

Circulation: Cardiovascular Imaging · 2025-07 · 18 (7)

DOI: 10.1161/circimaging.124.017761 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Circulation: Cardiovascular Imaging, 2025-07. Verfasst von Lukas Damian Weberling und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Angiology and Pneumology (L.D.W., A.O., F.a.d.S., J.S., E.G., B.M., M.G.F., N.F., F.A.), Heidelberg University Hospital, Ge…. Hauptthemen laut MEDLINE: Cardiomyopathy, Hypertrophic, Machine Learning, Amyloid Neuropathies, Familial, Magnetic Resonance Imaging, Cine. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Cardiac amyloidosis is associated with poor outcomes and is caused by the interstitial deposition of misfolded proteins, typically ATTR (transthyretin) or AL (light chains). Although specific therapies during early disease stages exist, the diagnosis is often only established at an advanced stage. Cardiovascular magnetic resonance (CMR) is the gold standard for imaging suspected myocardial disease. However, differentiating cardiac amyloidosis from hypertrophic cardiomyopathy may be challenging, and a reliable method for an image-based classification of amyloidosis subtypes is lacking. This study sought to investigate a CMR machine learning (ML) algorithm to identify and distinguish cardiac amyloidosis. METHODS: This retrospective, multicenter, multivendor feasibility study included consecutive patients diagnosed with hypertrophic cardiomyopathy or AL/ATTR amyloidosis and healthy volunteers. Standard clinical information, semiautomated CMR imaging data, and qualitative CMR features were integrated into a trained ML algorithm. RESULTS: Four hundred participants (95 healthy, 94 hypertrophic cardiomyopathy, 95 AL, and 116 ATTR) from 56 institutions were included (269 men aged 58.5 [48.4–69.4] years). A 3-stage ML screening cascade sequentially differentiated healthy volunteers from patients, then hypertrophic cardiomyopathy from amyloidosis, and then AL from ATTR. The ML algorithm resulted in an accurate differentiation at each step (area under the curve, 1.0, 0.99, and 0.92, respectively). After reducing included data to demographics and imaging data alone, the performance remained excellent (area under the curve, 0.99, 0.98, and 0.88, respectively), even after removing late gadolinium enhancement imaging data from the model (area under the curve, 1.0, 0.95, 0.86, respectively). CONCLUSIONS: A trained ML model using semiautomated CMR imaging data and patient demographics can accurately identify cardiac amyloidosis and differentiate subtypes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiomyopathy, HypertrophicMachine LearningAmyloid Neuropathies, FamilialMagnetic Resonance Imaging, CineImmunoglobulin Light-chain AmyloidosisImage Interpretation, Computer-AssistedCardiomyopathiesHumansMaleFemaleMiddle AgedRetrospective StudiesAgedDiagnosis, DifferentialFeasibility StudiesPredictive Value of Tests

Stichwörter der Autor:innen

amyloidosisartificial intelligencecardiomyopathy, hypertrophiccontrast mediaheart diseasesheart failuremagnetic resonance imaging

Autor:innen und Institutionen

  • Department of Cardiology, Angiology and Pneumology (L.D.W., A.O., F.a.d.S., J.S., E.G., B.M., M.G.F., N.F., F.A.), Heidelberg University Hospital, Germany.
  • German Centre for Cardiovascular Research (Deutsches Zentrum für Herz-Kreislauf-Forschung, DZHK), Partner Site Heidelberg/Mannheim (L.D.W., A.O., F.a.d.S., J.S., E.G., B.M., N.F., F.A.).
  • Area 19 Medical, Inc, Montreal, Quebec, Canada (M.B., S.F.).
  • Department of Haematology, Oncology and Rheumatology, Amyloidosis Center (F.a.d.S., S.S.), Heidelberg University Hospital, Germany.
  • Pfizer, Inc, Cambridge, MA (C.D., K.M., Y.Z.).
  • Pfizer Pharma GmbH, Berlin, Germany (J.M.).

ORCID-Profile: Lukas Damian Weberling, Andreas Ochs, Fabian Aus dem Siepen, Janek Salatzki, Evangelos Giannitsis, Kevin Maresca, Benjamin Meder, Matthias G Friedrich, Norbert Frey, Florian André

Zitieren

APA

Weberling, L. D., Ochs, A., Benovoy, M., Aus dem Siepen, F., Salatzki, J., Giannitsis, E., Duan, C., Maresca, K., Zhang, Y., Möller, J., Friedrich, S., Schönland, S., Meder, B., Friedrich, M. G., Frey, N., & André, F. (2025). Machine Learning to Automatically Differentiate Hypertrophic Cardiomyopathy, Cardiac Light Chain, and Cardiac Transthyretin Amyloidosis: A Multicenter CMR Study. Circulation: Cardiovascular Imaging, 18(7). https://doi.org/10.1161/circimaging.124.017761

Vancouver

Weberling LD, Ochs A, Benovoy M, Aus dem Siepen F, Salatzki J, Giannitsis E, et al. Machine Learning to Automatically Differentiate Hypertrophic Cardiomyopathy, Cardiac Light Chain, and Cardiac Transthyretin Amyloidosis: A Multicenter CMR Study. Circulation: Cardiovascular Imaging. 2025;18(7). doi:10.1161/circimaging.124.017761

BibTeX
@article{Weberling2025,
  author = {Weberling, Lukas Damian and Ochs, Andreas and Benovoy, Mitchel and Aus dem Siepen, Fabian and Salatzki, Janek and Giannitsis, Evangelos and Duan, Chong and Maresca, Kevin and Zhang, Yao and Möller, Jan and Friedrich, Silke and Schönland, Stefan and Meder, Benjamin and Friedrich, Matthias G and Frey, Norbert and André, Florian},
  title = {Machine Learning to Automatically Differentiate Hypertrophic Cardiomyopathy, Cardiac Light Chain, and Cardiac Transthyretin Amyloidosis: A Multicenter CMR Study},
  journal = {Circulation: Cardiovascular Imaging},
  year = {2025},
  volume = {18},
  number = {7},
  doi = {10.1161/circimaging.124.017761}
}
Kostenlos starten →