Logo do repositório
 
Publicação

Diagnostic performance of a novel AI-guided coronary computed tomography algorithm for predicting myocardial ischemia (AI-QCTISCHEMIA) across sex and age subgroups

2025-12-30Artigo de investigação Acesso aberto
Ver registo simples
dc.contributor.authorKamila, Putri Annisa
dc.contributor.authorHojjati, Tara
dc.contributor.authorNurmohamed, Nick S.
dc.contributor.authorDanad, Ibrahim
dc.contributor.authorDing, Yipu
dc.contributor.authorJukema, Ruurt A.
dc.contributor.authorRaijmakers, Pieter G.
dc.contributor.authorDriessen, Roel S.
dc.contributor.authorBom, Michiel J.
dc.contributor.authorvan Diemen, Pepijn
dc.contributor.authorPontone, Gianluca
dc.contributor.authorAndreini, Daniele
dc.contributor.authorChang, Hyuk Jae
dc.contributor.authorKatz, Richard J.
dc.contributor.authorChoi, Andrew D.
dc.contributor.authorKnaapen, Paul
dc.contributor.authorBax, Jeroen J.
dc.contributor.authorvan Rosendael, Alexander
dc.contributor.authorHeo, Ran
dc.contributor.authorPark, Hyung Bok
dc.contributor.authorMarques, Hugo
dc.contributor.authorStuijfzand, Wijnand J.
dc.contributor.authorChoi, Jung Hyun
dc.contributor.authorDoh, Joon Hyung
dc.contributor.authorHer, Ae Young
dc.contributor.authorKoo, Bon Kwon
dc.contributor.authorNam, Chang Wook
dc.contributor.authorShin, Sang Hoon
dc.contributor.authorCole, Jason
dc.contributor.authorGimelli, Alessia
dc.contributor.authorKhan, Muhammad Akram
dc.contributor.authorLu, Bin
dc.contributor.authorGao, Yang
dc.contributor.authorNabi, Faisal
dc.contributor.authorAl-Mallah, Mouaz H.
dc.contributor.authorNakazato, Ryo
dc.contributor.authorSchoepf, U. Joseph
dc.contributor.authorThompson, Randall C.
dc.contributor.authorJang, James J.
dc.contributor.authorRidner, Michael
dc.contributor.authorRowan, Chris
dc.contributor.authorAvelar, Erick
dc.contributor.authorGénéreux, Philippe
dc.contributor.authorde Waard, Guus A.
dc.date.accessioned2026-01-22T11:00:14Z
dc.date.available2026-01-22T11:00:14Z
dc.date.issued2025-12-30
dc.description.abstractBackground AI-QCTISCHEMIA is a novel artificial intelligence algorithm that predicts myocardial ischemia using quantitative features from coronary computed tomography angiography, providing a noninvasive alternative to functional imaging. However, its diagnostic performance across key demographic subgroups, particularly by sex and age, remains underexplored. We aimed to evaluate the diagnostic performance of AI-QCTISCHEMIA for predicting myocardial ischemia across these subgroups. Methods This post-hoc analysis included symptomatic patients with suspected coronary artery disease from the CREDENCE (Computed Tomographic Evaluation of Atherosclerotic Determinants of Myocardial Ischemia) (n = 305; 868 vessels) and PACIFIC-1 (Comparison of Coronary Computed Tomography Angiography, Single Photon Emission Computed Tomography [SPECT], Positron Emission Tomography [PET], and Hybrid Imaging for Diagnosis of Ischemic Heart Disease Determined by Fractional Flow Reserve) (n = 208; 612 vessels) studies. All patients underwent coronary computed tomography angiography, myocardial perfusion imaging (SPECT and/or PET), and invasive coronary angiography with 3-vessel fractional flow reserve as the reference standard. Diagnostic performance was evaluated at the vessel level using receiver operating characteristic analysis and under the curve (AUC), stratified by sex and age groups. Results In computed tomographic evaluation of atherosclerotic determinants of myocardial ischemia, AI-QCTISCHEMIA demonstrated higher diagnostic performance than myocardial perfusion imaging, with AUCs of 0.87 vs 0.63 in men and 0.85 vs 0.71 in women ( P < .001 for both). Similarly, in older (?65 years) and younger (<65 years) patients, AUCs were 0.85 vs 0.67 and 0.87 vs 0.63 ( P < .001 for both). In PACIFIC-1, AI-QCTISCHEMIA outperformed SPECT in men (AUC = 0.86 vs 0.67; P < .001) and women (0.81 vs 0.65; P < .001) while performing comparably with PET (0.86 vs 0.82; P = .140; 0.81 vs 0.72; P = .214). In older patients, AI-QCTISCHEMIA showed higher performance than SPECT (0.85 vs 0.73; P < .001) and was similar to PET (0.85 vs 0.86; P = .816). In younger patients, it also outperformed SPECT (0.87 vs 0.66; P < .001) with comparable performance with PET (0.87 vs 0.84; P = .338). Conclusions AI-QCTISCHEMIA demonstrated consistently high diagnostic performance to detect myocardial ischemia across sex and age groups, significantly outperforming SPECT and showing comparable performance with PET, supporting its role as a noninvasive alternative for ischemia assessment.eng
dc.identifier.citationKamila, P. A., Hojjati, T., Nurmohamed, N. S., & Danad, I. et al. (in press). Diagnostic performance of a novel AI-guided coronary computed tomography algorithm for predicting myocardial ischemia (AI-QCTISCHEMIA) across sex and age subgroups. Journal of the Society for Cardiovascular Angiography and Interventions, Article 104064. https://doi.org/10.1016/j.jscai.2025.104064
dc.identifier.doi10.1016/j.jscai.2025.104064
dc.identifier.eid105026814087
dc.identifier.otherdc774510-4dc3-44ed-aa43-6a012c8c6b60
dc.identifier.urihttp://hdl.handle.net/10400.14/56609
dc.language.isoeng
dc.peerreviewedyes
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectArtificial intelligence
dc.subjectCoronary artery disease
dc.subjectCoronary computed tomography angiography
dc.titleDiagnostic performance of a novel AI-guided coronary computed tomography algorithm for predicting myocardial ischemia (AI-QCTISCHEMIA) across sex and age subgroupseng
dc.typeresearch article
dspace.entity.typePublication
oaire.citation.titleJournal of the Society for Cardiovascular Angiography and Interventions
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
138620196.pdf
Tamanho:
5.05 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

FM - Contribuições em Revistas Científicas / Contribution to Journals