Diagnosis and prognosis of abnormal cardiac scintigraphy uptake suggestive of cardiac amyloidosis using artificial intelligence: a retrospective, international, multicentre, cross-tracer development and validation study.


Journal

The Lancet. Digital health
ISSN: 2589-7500
Titre abrégé: Lancet Digit Health
Pays: England
ID NLM: 101751302

Informations de publication

Date de publication:
Apr 2024
Historique:
received: 15 09 2023
revised: 21 11 2023
accepted: 11 12 2023
medline: 23 3 2024
pubmed: 23 3 2024
entrez: 22 3 2024
Statut: ppublish

Résumé

The diagnosis of cardiac amyloidosis can be established non-invasively by scintigraphy using bone-avid tracers, but visual assessment is subjective and can lead to misdiagnosis. We aimed to develop and validate an artificial intelligence (AI) system for standardised and reliable screening of cardiac amyloidosis-suggestive uptake and assess its prognostic value, using a multinational database of In this retrospective, international, multicentre, cross-tracer development and validation study, 16 241 patients with 19 401 scans were included from nine centres: one hospital in Austria (consecutive recruitment Jan 4, 2010, to Aug 19, 2020), five hospital sites in London, UK (consecutive recruitment Oct 1, 2014, to Sept 29, 2022), two centres in China (selected scans from Jan 1, 2021, to Oct 31, 2022), and one centre in Italy (selected scans from Jan 1, 2011, to May 23, 2023). The dataset included all patients referred to whole-body The prevalence of cases positive for cardiac amyloidosis-suggestive uptake was 142 (2%) of 9176 patients in the Austrian, 125 (2%) of 6763 patients in the UK, 63 (62%) of 102 patients in the Chinese, and 103 (52%) of 200 patients in the Italian cohorts. In the Austrian cohort, cross-validation performance showed an area under the curve (AUC) of 1·000 (95% CI 1·000-1·000). Independent validation yielded AUCs of 0·997 (0·993-0·999) for the UK, 0·925 (0·871-0·971) for the Chinese, and 1·000 (0·999-1·000) for the Italian cohorts. In the multicase multireader study, five physicians disagreed in 22 (11%) of 200 cases (Fleiss' kappa 0·89), with a mean AUC of 0·946 (95% CI 0·924-0·967), which was inferior to AI (AUC 0·997 [0·991-1·000], p=0·0040). The medical algorithmic audit demonstrated the system's robustness across demographic factors, tracers, scanners, and centres. The AI's predictions were independently prognostic for overall mortality (adjusted hazard ratio 1·44 [95% CI 1·19-1·74], p<0·0001). AI-based screening of cardiac amyloidosis-suggestive uptake in patients undergoing scintigraphy was reliable, eliminated inter-rater variability, and portended prognostic value, with potential implications for identification, referral, and management pathways. Pfizer.

Sections du résumé

BACKGROUND BACKGROUND
The diagnosis of cardiac amyloidosis can be established non-invasively by scintigraphy using bone-avid tracers, but visual assessment is subjective and can lead to misdiagnosis. We aimed to develop and validate an artificial intelligence (AI) system for standardised and reliable screening of cardiac amyloidosis-suggestive uptake and assess its prognostic value, using a multinational database of
METHODS METHODS
In this retrospective, international, multicentre, cross-tracer development and validation study, 16 241 patients with 19 401 scans were included from nine centres: one hospital in Austria (consecutive recruitment Jan 4, 2010, to Aug 19, 2020), five hospital sites in London, UK (consecutive recruitment Oct 1, 2014, to Sept 29, 2022), two centres in China (selected scans from Jan 1, 2021, to Oct 31, 2022), and one centre in Italy (selected scans from Jan 1, 2011, to May 23, 2023). The dataset included all patients referred to whole-body
FINDINGS RESULTS
The prevalence of cases positive for cardiac amyloidosis-suggestive uptake was 142 (2%) of 9176 patients in the Austrian, 125 (2%) of 6763 patients in the UK, 63 (62%) of 102 patients in the Chinese, and 103 (52%) of 200 patients in the Italian cohorts. In the Austrian cohort, cross-validation performance showed an area under the curve (AUC) of 1·000 (95% CI 1·000-1·000). Independent validation yielded AUCs of 0·997 (0·993-0·999) for the UK, 0·925 (0·871-0·971) for the Chinese, and 1·000 (0·999-1·000) for the Italian cohorts. In the multicase multireader study, five physicians disagreed in 22 (11%) of 200 cases (Fleiss' kappa 0·89), with a mean AUC of 0·946 (95% CI 0·924-0·967), which was inferior to AI (AUC 0·997 [0·991-1·000], p=0·0040). The medical algorithmic audit demonstrated the system's robustness across demographic factors, tracers, scanners, and centres. The AI's predictions were independently prognostic for overall mortality (adjusted hazard ratio 1·44 [95% CI 1·19-1·74], p<0·0001).
INTERPRETATION CONCLUSIONS
AI-based screening of cardiac amyloidosis-suggestive uptake in patients undergoing scintigraphy was reliable, eliminated inter-rater variability, and portended prognostic value, with potential implications for identification, referral, and management pathways.
FUNDING BACKGROUND
Pfizer.

Identifiants

pubmed: 38519153
pii: S2589-7500(23)00265-0
doi: 10.1016/S2589-7500(23)00265-0
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

e251-e260

Informations de copyright

Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.

Déclaration de conflit d'intérêts

Declaration of interests CN reports speaker fees or institutional research grants from Pfizer and advisory board honoraria from Prothena. TAT is co-founder and shareholder of Myocardium AI. RHD has received payment for consultancy work and owns shares in Myocardium AI. All other authors declare no competing interests.

Auteurs

Clemens P Spielvogel (CP)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

David Haberl (D)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Katharina Mascherbauer (K)

Department of Medicine II, Division of Cardiology, Medical University of Vienna, Vienna, Austria.

Jing Ning (J)

Christian Doppler Laboratory for Applied Metabolomics, Medical University of Vienna, Vienna, Austria.

Kilian Kluge (K)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Tatjana Traub-Weidinger (T)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Rhodri H Davies (RH)

Institute of Cardiovascular Science, University College London, London, UK; Bart's Heart Centre, St Bartholomew's Hospital, West Smithfield, London, London, UK.

Iain Pierce (I)

Institute of Cardiovascular Science, University College London, London, UK; Bart's Heart Centre, St Bartholomew's Hospital, West Smithfield, London, London, UK.

Kush Patel (K)

Bart's Heart Centre, St Bartholomew's Hospital, West Smithfield, London, London, UK.

Thomas Nakuz (T)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Adelina Göllner (A)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Dominik Amereller (D)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Maria Starace (M)

Department of Experimental and Clinical Biomedical Sciences, Nuclear Medicine Unit, University of Florence, Florence, Italy.

Alice Monaci (A)

Department of Experimental and Clinical Biomedical Sciences, Nuclear Medicine Unit, University of Florence, Florence, Italy.

Michael Weber (M)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Xiang Li (X)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Alexander R Haug (AR)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria; Christian Doppler Laboratory for Applied Metabolomics, Medical University of Vienna, Vienna, Austria.

Raffaella Calabretta (R)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Xiaowei Ma (X)

Department of Nuclear Medicine, Second Xiangya Hospital, Central South University, Changsha, China.

Min Zhao (M)

Department of Nuclear Medicine, Third Xiangya Hospital, Central South University, Changsha, China.

Julia Mascherbauer (J)

Department of Medicine II, Division of Cardiology, Medical University of Vienna, Vienna, Austria; Karl Landsteiner University of Health Sciences, Department of Internal Medicine 3, University Hospital St Pölten, Krems, Austria.

Andreas Kammerlander (A)

Department of Medicine II, Division of Cardiology, Medical University of Vienna, Vienna, Austria.

Christian Hengstenberg (C)

Department of Medicine II, Division of Cardiology, Medical University of Vienna, Vienna, Austria.

Leon J Menezes (LJ)

Bart's Heart Centre, St Bartholomew's Hospital, West Smithfield, London, London, UK.

Roberto Sciagra (R)

Department of Experimental and Clinical Biomedical Sciences, Nuclear Medicine Unit, University of Florence, Florence, Italy.

Thomas A Treibel (TA)

Institute of Cardiovascular Science, University College London, London, UK; Bart's Heart Centre, St Bartholomew's Hospital, West Smithfield, London, London, UK.

Marcus Hacker (M)

Department of Biomedical Imaging and Image-Guided Therapy, Division of Nuclear Medicine, Medical University of Vienna, Vienna, Austria.

Christian Nitsche (C)

Institute of Cardiovascular Science, University College London, London, UK; Department of Medicine II, Division of Cardiology, Medical University of Vienna, Vienna, Austria; Bart's Heart Centre, St Bartholomew's Hospital, West Smithfield, London, London, UK. Electronic address: christian.nitsche@meduniwien.ac.at.

Classifications MeSH