Artificial intelligence-enhanced detection of subclinical coronary artery disease in athletes: diagnostic performance and limitations.
Artificial intelligence
Coronary artery disease
Coronary computed tomography angiography
Diagnostic accuracy
Fractional flow reserve
Marathon runners
Journal
The international journal of cardiovascular imaging
ISSN: 1875-8312
Titre abrégé: Int J Cardiovasc Imaging
Pays: United States
ID NLM: 100969716
Informations de publication
Date de publication:
07 Oct 2024
07 Oct 2024
Historique:
received:
19
06
2024
accepted:
25
09
2024
medline:
7
10
2024
pubmed:
7
10
2024
entrez:
7
10
2024
Statut:
aheadofprint
Résumé
This study evaluates the diagnostic performance of artificial intelligence (AI)-based coronary computed tomography angiography (CCTA) for detecting coronary artery disease (CAD) and assessing fractional flow reserve (FFR) in asymptomatic male marathon runners. We prospectively recruited 100 asymptomatic male marathon runners over the age of 45 for CAD screening. CCTA was analyzed using AI models (CorEx and Spimed-AI) on a local server. The models focused on detecting significant CAD (≥ 50% diameter stenosis, CAD-RADS 3, 4, or 5) and distinguishing hemodynamically significant stenosis (FFR ≤ 0.8) from non-significant stenosis (FFR > 0.8). Statistical analysis included sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. The AI model demonstrated high sensitivity, with 91.2% for any CAD and 100% for significant CAD, and high NPV, with 92.7% for any CAD and 100% for significant CAD. The diagnostic accuracy was 73.4% for any CAD and 90.4% for significant CAD. However, the PPV was lower, particularly for significant CAD (25.0%), indicating a higher incidence of false positives. AI-enhanced CCTA is a valuable non-invasive tool for detecting CAD in asymptomatic, low-risk populations. The AI model exhibited high sensitivity and NPV, particularly for identifying significant stenosis, reinforcing its potential role in screening. However, limitations such as a lower PPV and overestimation of disease indicate that further refinement of AI algorithms is needed to improve specificity. Despite these challenges, AI-based CCTA offers significant promise when integrated with clinical expertise, enhancing diagnostic accuracy and guiding patient management in low-risk groups.
Identifiants
pubmed: 39373817
doi: 10.1007/s10554-024-03256-y
pii: 10.1007/s10554-024-03256-y
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Agatston AS et al (1990) Quantification of coronary artery calcium using ultrafast computed tomography. J Am Coll Cardiol 15(4):827–832
Chang AM et al (2011) Does coronary artery calcium scoring add to the predictive value of coronary computed tomography angiography for adverse cardiovascular events in low-risk chest pain patients? Acad Emerg Med 18(10):1065–1071
Doris M, Newby DE (2016) Coronary CT angiography as a diagnostic and prognostic tool: perspectives from the SCOT-HEART trial. Curr Cardiol Rep 18(2):18
Balanescu S (2016) Fractional flow reserve assessment of coronary artery stenosis. Eur Cardiol 11(2):77–82
Liao J et al (2022) Artificial intelligence in coronary CT angiography: current status and future prospects. Front Cardiovasc Med 9:896366
Grabitz C et al (2023) Cardiovascular health and potential cardiovascular risk factors in young athletes. Front Cardiovasc Med 10:1081675
D’Agostino RB Sr et al (2008) General cardiovascular risk profile for use in primary care: the Framingham heart study. Circulation 117(6):743–753
Burgstahler C et al (2018) Coronary and carotid atherosclerosis in asymptomatic male marathon runners. Scand J Med Sci Sports 28(4):1397–1403
Tsiflikas I et al (2015) Prevalence of subclinical coronary artery disease in middle-aged, male marathon runners detected by cardiac CT. Rofo 187(7):561–568
Gassenmaier S et al (2021) Prevalence of pathological FFR(CT) values without coronary artery stenosis in an asymptomatic marathon runner cohort. Eur Radiol 31(12):8975–8982
Leipsic J et al (2014) SCCT guidelines for the interpretation and reporting of coronary CT angiography: a report of the society of cardiovascular computed tomography guidelines committee. J Cardiovasc Comput Tomogr 8(5):342–358
Paul JF et al (2022) Evaluation of a deep learning model on coronary CT angiography for automatic stenosis detection. Diagn Interv Imaging 103(6):316–323
Brendel, J.M., et al. (2024) Coronary artery disease evaluation during transcatheter aortic valve replacement work-up using photon-counting CT and artificial intelligence. Diagn Interv Imaging
Mehier B et al (2024) Diagnostic performance of deep learning to exclude coronary stenosis on CT angiography in TAVI patients. Int J Cardiovasc Imaging 40(5):981–990
Zreik M et al (2019) A recurrent CNN for automatic detection and classification of coronary artery plaque and stenosis in coronary CT angiography. IEEE Trans Med Imaging 38(7):1588–1598
Elias P et al (2024) Artificial intelligence for cardiovascular care-part 1: advances. J Am Coll Cardiol 83(24):2472–2486
Norgaard BL et al (2014) Diagnostic performance of noninvasive fractional flow reserve derived from coronary computed tomography angiography in suspected coronary artery disease the NXT trial (analysis of coronary blood flow using CT angiography: next steps). J Am Coll Cardiol 63(12):1145–1155
Xu B et al (2020) Applications of artificial intelligence in multimodality cardiovascular imaging: a state-of-the-art review. Prog Cardiovasc Dis 63(3):367–376
D’Ascenzi F et al (2021) The use of cardiac imaging in the evaluation of athletes in the clinical practice: a survey by the sports cardiology and exercise section of the European association of preventive cardiology and university of Siena, in collaboration with the European association of cardiovascular imaging, the European heart rhythm association and the ESC working group on myocardial and pericardial diseases. Eur J Prev Cardiol 28(10):1071–1077
D’Ascenzi F et al (2019) Cardiovascular risk profile in Olympic athletes: an unexpected and underestimated risk scenario. Br J Sports Med 53(1):37–42
Sermesant M et al (2021) Applications of artificial intelligence in cardiovascular imaging. Nat Rev Cardiol 18(8):600–609
Slart RHJA et al (2021) Position paper of the EACVI and EANM on artificial intelligence applications in multimodality cardiovascular imaging using SPECT/CT, PET/CT, and cardiac CT. Eur J Nucl Med Mol Imaging 48(5):1399–1413
Thompson PD et al (2007) Exercise and acute cardiovascular events placing the risks into perspective-a scientific statement from the American heart association council on nutrition, physical activity, and metabolism-in collaboration with the American college of sports medicine. Circulation 115(17):2358–2368
Ding YD et al (2023) Diagnostic accuracy of noninvasive fractional flow reserve derived from computed tomography angiography in ischemia-specific coronary artery stenosis and indeterminate lesions: results from a multicenter study in China. Front Cardiovascu Med 10:1236405