Machine learning for myocarditis diagnosis using cardiovascular magnetic resonance: a systematic review, diagnostic test accuracy meta-analysis, and comparison with human physicians

Łajczak P, Sahin OK, Matyja J, Puglla Sanchez LR, Sayudo IF, Ayesha A, Lopes V, Majeed MW, Krishna MM, Joseph M, Pereira M, Obi O, Silva R, Lecchi C, Schincariol M (2025)

Publication Type: Journal article, Review article

Publication year: 2025

Journal

International Journal of Cardiovascular Imaging Springer Verlag (Germany)

DOI: 10.1007/s10554-025-03497-5

Abstract

Myocarditis is an inflammation of heart tissue. Cardiovascular magnetic resonance imaging (CMR) has emerged as an important non-invasive imaging tool for diagnosing myocarditis, however, interpretation remains a challenge for novice physicians. Advancements in machine learning (ML) models have further improved diagnostic accuracy, demonstrating good performance. Our study aims to assess the diagnostic accuracy of ML in identifying myocarditis using CMR. A systematic search was performed using PubMed, Embase, Web of Science, Cochrane, and Scopus to identify studies reporting the diagnostic accuracy of ML in the detection of myocarditis using CMR. The included studies evaluated both image-based and report-based assessments using various ML models. Diagnostic accuracy was estimated using a Random-Effects model (R software). We found a total of 141 ML model results from a total of 12 studies, which were included in the systematic review. The best models achieved 0.93 (95% Confidence Interval (CI) 0.88–0.96) sensitivity and 0.95 (95% CI 0.89–0.97) specificity. Pooled area under the curve was 0.97 (95% CI 0.93–0.98). Comparisons with human physicians showed comparable results for diagnostic accuracy of myocarditis. Quality assessment concerns and heterogeneity were present. CMR augmented using ML models with advanced algorithms can provide high diagnostic accuracy for myocarditis, even surpassing novice CMR radiologists. However, high heterogeneity, quality assessment concerns, and lack of information on cost-effectiveness may limit the clinical implementation of ML. Future investigations should explore cost-effectiveness and minimize biases in their methodologies.

Authors with CRIS profile

Michele Schincariol Department of Medicine 2 – Cardiology and Angiology

Involved external institutions

Medical University of Silesia in Katowice / Śląski Uniwersytet Medyczny w Katowicach (SUM) PL Poland (PL) Edremit State Hospital / Edremit Devlet Hastanesi TR Turkey (TR) Delft University of Technology (TU Delft) NL Netherlands (NL) Hospital Clínico Universitario Lozano Blesa ES Spain (ES) Syiah Kuala University / Universitas Syiah Kuala (Unsyiah) ID Indonesia (ID) Shifa Tameer-e-Millat University PK Pakistan (PK) Federal University of Amazonas / Universidade Federal do Amazonas (UFAM) BR Brazil (BR) Government Medical College (GMC) IN India (IN) Government Medical College / ഗവൺമെന്റ് മെഡിക്കൽ കോളേജ്, തിരുവനന്തപുരം IN India (IN) Lincoln American University GY Guyana (GY) New York Institute of Technology US United States (USA) (US) Universidade Federal do Ceará (UCF) BR Brazil (BR) Università della Svizzera italiana (USI) CH Switzerland (CH)

How to cite

APA:

Łajczak, P., Sahin, O.K., Matyja, J., Puglla Sanchez, L.R., Sayudo, I.F., Ayesha, A.,... Schincariol, M. (2025). Machine learning for myocarditis diagnosis using cardiovascular magnetic resonance: a systematic review, diagnostic test accuracy meta-analysis, and comparison with human physicians. International Journal of Cardiovascular Imaging. https://doi.org/10.1007/s10554-025-03497-5

MLA:

Łajczak, Paweł, et al. "Machine learning for myocarditis diagnosis using cardiovascular magnetic resonance: a systematic review, diagnostic test accuracy meta-analysis, and comparison with human physicians." International Journal of Cardiovascular Imaging (2025).

BibTeX: Download