Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria - a proof of concept study

Aug 5, 2026

Upload by Violet

Prosthetic valve endocarditis (PVE) is a serious complication with limited diagnostic accuracy using existing Duke criteria and their modifications, especially for PVE. The study evaluates whether machine learning can improve the predictive value of the modified Duke/ESC 2015 (MDE2015) criteria. In a retrospective multicentre cohort of 160 suspected PVE patients, multiple machine-learning models were compared against an MDE2015-based diagnosis using a composite gold standard. Results show improved performance and measurable certainty levels that may support clinical interpretability and future refinement of advanced imaging criteria.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Methods

Results

Discussion

EUR Research Information Portal Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis-a proof of concept study Published in: European Journal of Nuclear Medicine and Molecular Imaging Publication status and date: Published: 01/11/2024 DOI (link to publisher): 10.1007/s00259-024-06774-y Document Version Publisher's PDF, also known as Version of record Document License/Available under: CC BY Citation for the published version (APA): ten Hove, D. , Slart, R. H. J. A. , Glaudemans, A. W. J. M. , Postma, D. F. , Gomes, A. , Swart, L. E. , Tanis, W. , Geel, P. P. V. , Mecozzi, G. , Budde, R. P. J. , Mouridsen, K. , & Sinha, B. (2024) . Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis-a proof of concept study. European Journal of Nuclear Medicine and Molecular Imaging, 51(13), 3924-3933 . [https://doi.org/10.1007/s00259-024-](https://doi.org/10.1007/s00259-024-)[ ](https://doi.org/10.1007/s00259-024-)[06774-y](06774-y) Link to publication on the EUR Research Information Portal Terms and Conditions of Use Except as permitted by the applicable copyright law, you may not reproduce or make this material available to any third party without the prior written permission from the copyright holder(s) . Copyright law allows the following uses of this material without prior permission: • you may download, save and print a copy of this material for your personal use only; • you may share the EUR portal link to this material. In case the material is published with an open access license (e.g. a Creative Commons (CC) license), other uses may be allowed. Please check the terms and conditions of the specific license. Take-down policy If you believe that this material infringes your copyright and/or any other intellectual property rights, you may request its removal by contacting us at the following email address: [openaccess.library@eur.nl. Please](openaccess.library@eur.nl. Please) provide us with all the relevant information, including the reasons why you believe any of your rights have been infringed. In case of a legitimate complaint, we will make the material inaccessible and/or remove it from the website. European Journal of Nuclear Medicine and Molecular Imaging [https://doi.org/10.1007/s00259-024-06774-y](https://doi.org/10.1007/s00259-024-06774-y) ORIGINAL ARTICLE Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis – a proof of concept study D. ten Hove1,2 · R. H. J. A. Slart1,3 · A. W. J. M. Glaudemans1 · D. F. Postma4 · A. Gomes2 · L. E. Swart5 · W. Tanis6 · P. P. van Geel7 · G. Mecozzi8 · R. P. J. Budde9 · K. Mouridsen1,10 · B. Sinha2 Received: 14 November 2023 / Accepted: 17 May 2024 © The Author(s) 2024 Abstract Introduction Prosthetic valve endocarditis (PVE) is a serious complication of prosthetic valve implantation, with an estimated yearly incidence of at least 0.4-1.0% . The Duke criteria and subsequent modifications have been developed as a diagnostic framework for infective endocarditis (IE) in clinical studies. However, their sensitivity and specificity are limited, especially for PVE. Furthermore, their most recent versions (ESC2015 and ESC2023) include advanced imaging modalities, e.g., cardiac CTA and [ 18F]FDG PET/CT as major criteria. However, despite these significant changes, the weighing system using major and minor criteria has remained unchanged. This may have introduced bias to the diagnostic set of criteria. Here, we aimed to evaluate and improve the predictive value of the modified Duke/ESC 2015 (MDE2015) criteria by using machine learning algorithms. Methods In this proof-of-concept study, we used data of a well-defined retrospective multicentre cohort

FAQs

What clinical problem does the study address?

The study targets the diagnostic challenge of prosthetic valve endocarditis (PVE) and the limited sensitivity/specificity of the modified Duke/ESC 2015 criteria, especially when advanced imaging is involved.

How was the machine learning evaluation designed?

A retrospective multicentre cohort of 160 suspected PVE patients was used, comparing four machine-learning algorithms with the MDE2015-based prediction using the same features as the criteria.

What were the main diagnostic performance findings?

Treating “possible” cases as positive yielded sensitivity 0.96 and specificity 0.60, while treating them as negative yielded sensitivity 0.74 and specificity 0.98. Machine-learning models achieved AUCs around 0.93–0.94, with logistic regression showing sensitivity 0.92 and specificity 0.85.

Aug 5, 2026

Upload by Violet