EUVIMEDEUVIMED entdecken
ValidierungsstudieMultizentrische StudieOpen Access · CC BY 4.0

Diagnosis of Cardiac Amyloidosis on Echocardiography Using Artificial Intelligence

Adam Ioannou iD, Michel G Khouri iD, Takeshi Kitai iD, Sreekanth Vemulapalli iD, Chung-Lieh Hung iD, Sze Chi Lim iD, Matthew Frost iD, Weile Wayne Tee iD, Josephine Mansell iD, Awais Sheikh iD, Lucia Venneri iD, Yousuf Razvi iD und 13 weitere

Circulation: Cardiovascular Imaging · 2026-04 · 19 (4)

DOI: 10.1161/circimaging.125.018991 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Circulation: Cardiovascular Imaging, 2026-04. Verfasst von Adam Ioannou und 24 weiteren Autor:innen. Beteiligte Einrichtung: National Amyloidosis Centre, University College London, Royal Free Campus, London, United Kingdom (A.I., J.M., A.S., L.V., Y.R., A.P., A.M.-N., M.U.R…. Hauptthemen laut MEDLINE: Amyloidosis, Deep Learning, Artificial Intelligence, Echocardiography. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Diagnosing cardiac amyloidosis (CA) on echocardiography can be challenging due to the imaging overlap between CA and more prevalent causes of a hypertrophic phenotype. This study sought to (1) evaluate the performance of artificial-intelligence (AI) derived measurements incorporated into the established multiparametric echocardiographic scoring system to detect CA; (2) develop and validate an AI-based deep-learning model for video-based detection of CA on echocardiography. METHODS: The study population comprised 5776 patients (CA, 2756; controls, 3020). The training data set included patients from the UK National Amyloidosis Center and Taiwan MacKay Memorial Hospital (CA, 2241; controls, 2130). External test data sets were obtained from the US Duke University Health System (CA, 334; left ventricular hypertrophy controls, 668) and Japan National Cerebral and Cardiovascular Center (CA, 181; left ventricular hypertrophy controls, 222). RESULTS: The multiparametric echocardiographic score computed using AI-derived measurements achieved an accuracy of 79.5% (sensitivity, 75.4%; specificity, 81.5%) in the United States cohort and 79.7% (sensitivity, 81.6%; specificity, 78.1%) in the Japan cohort. The deep-learning model demonstrated accuracies of 96.2% (sensitivity, 96.8%; specificity, 95.7%) and 95.8% (sensitivity, 97.3%; specificity, 94.3%) in the internal validation and internal test sets, respectively. External validation of the deep-learning model showed accuracies of 87.5% (sensitivity, 86.6%; specificity, 87.9%) in the United States and 88.4% (sensitivity, 92.3%; specificity, 85.3%) in the Japanese cohort. Subgroup analysis demonstrated that the deep-learning model showed robust discrimination of CA from other hypertrophic phenocopies: CA versus hypertension (area under the curve [AUC], 0.92 [95% CI, 0.91–0.94]), CA versus hypertrophic cardiomyopathy (AUC, 0.91 [95% CI, 0.87–0.94]), CA versus aortic stenosis (AUC, 0.93 [95% CI, 0.90–0.95]), CA versus chronic kidney disease (AUC, 0.93 [95% CI, 0.91–0.95]). The deep-learning model was able to classify a greater proportion of patients compared with the AI-derived multiparametric echocardiographic score and achieved superior diagnostic accuracy (AUC, 0.93 [95% CI, 0.91–0.95] versus AUC, 0.88 [95% CI, 0.85–0.90]; P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AmyloidosisDeep LearningArtificial IntelligenceEchocardiographyCardiomyopathiesImage Interpretation, Computer-AssistedHumansFemaleMaleReproducibility of ResultsPredictive Value of TestsAgedMiddle Aged

Stichwörter der Autor:innen

amyloidosisartificial intelligencedeep learningechocardiographyphenotype

Autor:innen und Institutionen

  • National Amyloidosis Centre, University College London, Royal Free Campus, London, United Kingdom (A.I., J.M., A.S., L.V., Y.R., A.P., A.M.-N., M.U.R., H.L., P.N.H., A.W., J.D.G., M. Fontana).
  • Duke University Health System, Durham, NC (M.G.K.).
  • Department of Heart Failure and Transplantation, National Cerebral and Cardiovascular Centre, Osaka, Japan (T.K.).
  • Duke Clinical Research Institute, Durham, NC (S.V.).
  • Institute of Biomedical Sciences, Mackay Medical College, Taipei, Taiwan (C.-L.H.).
  • Us2.ai, Singapore (S.C.L., M. Frost, W.W.T.).

ORCID-Profile: Adam Ioannou, Michel G Khouri, Takeshi Kitai, Sreekanth Vemulapalli, Chung-Lieh Hung, Sze Chi Lim, Matthew Frost, Weile Wayne Tee, Josephine Mansell, Awais Sheikh, Lucia Venneri, Yousuf Razvi, Aldostefano Porcari, Ana Martinez-Naharro, Muhammad U Rauf, Philip N Hawkins, William Moody, Justin A Ezekowitz, Carolyn S P Lam, Scott D Solomon, Julian D Gillmore, Marianna Fontana

Zitieren

APA

Ioannou, A., Khouri, M. G., Kitai, T., Vemulapalli, S., Hung, C. L., Lim, S. C., Frost, M., Tee, W. W., Mansell, J., Sheikh, A., Venneri, L., Razvi, Y., Porcari, A., Martinez-Naharro, A., Rauf, M. U., Lachmann, H., Hawkins, P. N., Wechelakar, A., Moody, W., …, & Fontana, M. (2026). Diagnosis of Cardiac Amyloidosis on Echocardiography Using Artificial Intelligence. Circulation: Cardiovascular Imaging, 19(4). https://doi.org/10.1161/circimaging.125.018991

Vancouver

Ioannou A, Khouri MG, Kitai T, Vemulapalli S, Hung CL, Lim SC, et al. Diagnosis of Cardiac Amyloidosis on Echocardiography Using Artificial Intelligence. Circulation: Cardiovascular Imaging. 2026;19(4). doi:10.1161/circimaging.125.018991

BibTeX
@article{Ioannou2026,
  author = {Ioannou, Adam and Khouri, Michel G and Kitai, Takeshi and Vemulapalli, Sreekanth and Hung, Chung-Lieh and Lim, Sze Chi and Frost, Matthew and Tee, Weile Wayne and Mansell, Josephine and Sheikh, Awais and Venneri, Lucia and Razvi, Yousuf and Porcari, Aldostefano and Martinez-Naharro, Ana and Rauf, Muhammad U and Lachmann, Helen and Hawkins, Philip N and Wechelakar, Ashutosh and Moody, William and Bandera, Francesco and Ezekowitz, Justin A and Lam, Carolyn S P and Solomon, Scott D and Gillmore, Julian D and Fontana, Marianna},
  title = {Diagnosis of Cardiac Amyloidosis on Echocardiography Using Artificial Intelligence},
  journal = {Circulation: Cardiovascular Imaging},
  year = {2026},
  volume = {19},
  number = {4},
  doi = {10.1161/circimaging.125.018991}
}
Kostenlos starten →