GIÁ TRỊ CỦA TRÍ TUỆ NHÂN TẠO (AI-QCT) TRONG NÂNG CAO ĐỘ CHÍNH XÁC CHẨN ĐOÁN VÀ PHÂN TẦNG NGUY CƠ MẢNG XƠ VỮA MẠCH VÀNH TRÊN CCTA
VALUE OF ARTIFICIAL INTELLIGENCE-ENABLED QUANTITATIVE COMPUTED TOMOGRAPHY (AI-QCT) IN ENHANCING DIAGNOSTIC ACCURACY AND RISK STRATIFICATION OF CORONARY PLAQUE ON CCTA
Thông tin bài viết
Tải bài viết
Cách trích dẫn
Tóm tắt
Nghiên cứu nhằm đánh giá vai trò của định lượng mảng xơ vữa tự động bằng trí tuệ nhân tạo (AI-QCT) trong việc nâng cao độ chính xác chẩn đoán và phân tầng nguy cơ so với đánh giá bằng mắt thường theo tiêu chuẩn CAD-RADS 2.0 trên bệnh nhân hẹp mạch vành không tắc nghẽn (<50%) qua chụp cắt lớp vi tính mạch vành (CCTA). Dữ liệu trích xuất từ Pubmed, Research Gate, Science Direct trong 6 năm gần đây. Các tiêu chí lựa chọn tập trung vào nghiên cứu lâm sàng về AI-QCT, đặc điểm mảng xơ vữa nguy cơ cao và hệ thống CAD-RADS 2.0. Kết quả ghi nhận AI-QCT mang lại hiệu quả vượt trội với độ nhạy trong phát hiện mảng xơ vữa nguy cơ cao (85%-94%, có thể đạt gần 99% ở một số nghiên cứu). Chỉ số diện tích dưới đường cong (AUC) trong phân tầng nguy cơ tim mạch đạt 0,8 đến 0,93 (đa số ≥ 0.85). Việc tích hợp AI-QCT vào phân tích CCTA và hệ thống CAD-RADS 2.0 mang giá trị chiến lược kép: triệt tiêu sai số chủ quan để tối ưu phân tầng nguy cơ và tạo nền tảng cá thể hóa điều trị dự phòng và nâng cao tiên lượng lâm sàng dài hạn cho bệnh nhân
Từ khóa
Tài liệu tham khảo
- Damluji AA, Nanna MG, Mason P, Lowenstern A, Orkaby AR, Washam JB, et al. Coronary Artery Revascularization in the Older Adult Population: A Scientific Statement From the American Heart Association. Circulation 2025;152:e494–525. https://doi.org/10.1161/CIR.0000000000001387. DOI: https://doi.org/10.1161/CIR.0000000000001387
- Çelik MC, Kalçık M, Birgün A, Yetim M, Bekar L, Karavelioğlu Y. Endothelial dysfunction and vascular stiffness: molecular drivers of cardiovascular aging. Explor Cardiol 2025;3:101279. https://doi.org/10.37349/ec.2025.101279. DOI: https://doi.org/10.37349/ec.2025.101279
- Vink AS, A.M. Beijk M. The Treatment of Complex Coronary Artery Disease. Rev Cardiovasc Med 2025;26:46214. https://doi.org/10.31083/RCM46214. DOI: https://doi.org/10.31083/RCM46214
- Caractéristiques angiographiques des septuagénaires hospitalisés n.d. https://studylibfr.com/doc/2482372/caract%C3%A9ristiques-angiographiques-des-septuag%C3%A9naires-hospi. (accessed May 2, 2026).
- Các tiến bộ trong chẩn đoán và điều trị bệnh mạch vành | Tim mạch học | Hội Tim mạch học thành phố Hồ Chí Minh 2025. https://timmachhoc.vn/cac-tien-bo-trong-chan-doan-va-dieu-tri-benh-mach-vanh/ (accessed May 2, 2026).
- Inflammatory risk and cardiovascular events in patients without obstructive coronary artery disease: the ORFAN multicentre, longitudinal cohort study - The Lancet n.d. https://www.thelancet.com/article/S0140-6736%2824%2900596-8/fulltext (accessed May 2, 2026).
- Nonobstructive coronary atherosclerosis is associated with adverse prognosis among patients diagnosed with myocardial infarction without obstructive coronary arteries - Atherosclerosis n.d. https://www.atherosclerosis-journal.com/article/S0021-9150(23)00006-0/abstract (accessed May 2, 2026).
- CAD-RADSTM 2.0 - 2022 Coronary Artery Disease-Reporting and Data System - Journal of Cardiovascular Computed Tomography n.d. https://www.journalofcardiovascularct.com/article/S1934-5925%2822%2900240-4/fulltext (accessed May 2, 2026).
- Celeng C, Takx RAP. Moving towards a uniform diagnosis of coronary artery disease on coronary CTA. Neth Heart J 2024;32:378–85. https://doi.org/10.1007/s12471-024-01903-6. DOI: https://doi.org/10.1007/s12471-024-01903-6
- SCCT Expert Consensus Document Provides Measurable Standard for Cardiac CT Angiography - Cardiac Interventions Today n.d. https://c4v8.citoday.com/news/scct-expert-consensus-document-provides-measurable-standard-for-cardiac-ct-angiography (accessed May 2, 2026).
- Large Language Models Versus Human Readers in CAD-RADS 2.0 Categorization of Coronary CT Angiography Reports | Journal of Imaging Informatics in Medicine | Springer Nature Link n.d. https://link.springer.com/article/10.1007/s10278-025-01704-2 (accessed May 2, 2026).
- CCTA Study: Plaque Burden Offers No Prognostic Benefit for Predicting Cardiac Events in Patients with Acute Chest Pain | Diagnostic Imaging n.d. https://www.diagnosticimaging.com/view/ccta-study-plaque-burden-no-prognostic-benefit-predicting-cardiac-events-acute-chest-pain (accessed May 2, 2026).
- Pinna A, Boi A, Mannelli L, Balestrieri A, Sanfilippo R, Suri J, et al. Machine Learning for Coronary Plaque Characterization: A Multimodal Review of OCT, IVUS, and CCTA. Diagnostics 2025;15:1822. https://doi.org/10.3390/diagnostics15141822. DOI: https://doi.org/10.3390/diagnostics15141822
- Artificial Intelligence–based Coronary Plaque Quantification Using Coronary CT Angiography: Current Insights and Future DirectionsRadiology: Cardiothoracic Imaging n.d. https://pubs.rsna.org/doi/10.1148/ryct.240568 (accessed May 2, 2026).
- Prognostic Value of AI-Based Quantitative Coronary CTA vs Human Reader-Based Visual Assessment: Results From the CONFIRM2 Registry | JACC: Cardiovascular Imaging n.d. https://www.jacc.org/doi/10.1016/j.jcmg.2025.09.021 (accessed May 2, 2026).
- Arterial Occlusive Disease | Assessment of atherosclerotic plaque burden: comparison of AI-QCT versus SIS, CAC, visual and CAD-RADS stenosis categories | springermedicine.com n.d. https://www.springermedicine.com/arterial-occlusive-disease/artificial-intelligence/assessment-of-atherosclerotic-plaque-burden-comparison-of-ai-qct/26990712 (accessed May 2, 2026).
- Choi AD, Marques H, Kumar V, Griffin WF, Rahban H, Karlsberg RP, et al. CT Evaluation by Artificial Intelligence for Atherosclerosis, Stenosis and Vascular Morphology (CLARIFY): A Multi-center, international study. Journal of Cardiovascular Computed Tomography 2021;15:470–6. https://doi.org/10.1016/j.jcct.2021.05.004. DOI: https://doi.org/10.1016/j.jcct.2021.05.004
- Bär S, Knuuti J, Saraste A, Klén R, Kero T, Nabeta T, et al. Derivation and validation of an artificial intelligence-based plaque burden safety cut-off for long-term acute coronary syndrome from coronary computed tomography angiography. Eur Heart J Cardiovasc Imaging 2025;26:1163–73. https://doi.org/10.1093/ehjci/jeaf121. DOI: https://doi.org/10.1093/ehjci/jeaf121
- AI-Quantitative CT Coronary Plaque Features Associate With a Higher Relative Risk in Women: CONFIRM2 Registry | Circulation: Cardiovascular Imaging n.d. https://www.ahajournals.org/doi/10.1161/CIRCIMAGING.125.018235 (accessed May 2, 2026).
- Han X, Luo N, Xu L, Cao J, Guo N, He Y, et al. Artificial intelligence stenosis diagnosis in coronary CTA: effect on the performance and consistency of readers with less cardiovascular experience. BMC Med Imaging 2022;22:28. https://doi.org/10.1186/s12880-022-00756-y. DOI: https://doi.org/10.1186/s12880-022-00756-y
- Ihdayhid AR, Sehly A, He A, Joyner J, Flack J, Konstantopoulos J, et al. Coronary Artery Stenosis and High-Risk Plaque Assessed With an Unsupervised Fully Automated Deep Learning Technique. JACC Adv 2024;3:100861. https://doi.org/10.1016/j.jacadv.2024.100861. DOI: https://doi.org/10.1016/j.jacadv.2024.100861
- Parsa S, Peng AW, Bell J, Sengupta S, Mullen S, Rogers C, et al. Artificial intelligence-enabled coronary plaque quantification for personalized risk assessment and lipid-lowering therapy: Insights from the FISH&CHIPS study✰. American Journal of Preventive Cardiology 2026;26:101452. https://doi.org/10.1016/j.ajpc.2026.101452. DOI: https://doi.org/10.1016/j.ajpc.2026.101452
- Super-Resolution Deep Learning Reconstruction for Coronary CT Angiography: Coronary Stenosis Assessment and CAD-RADS Reclassification | Radiology n.d. https://pubs.rsna.org/doi/10.1148/radiol.252163 (accessed May 2, 2026).
- The Plaque Analysis Classifies the Coronary Artery Disease‐Reporting and Data System (CAD‐RADS) Stenosis and Plaque Burden Categories: Association of the Plaque Features, Fat Attenuation Index, Coronary Computed Tomography Fractional Flow Reserve, and the Combination of Stenosis and Calcification - Chen - 2024 - Clinical Cardiology - Wiley Online Library n.d. https://onlinelibrary.wiley.com/doi/full/10.1002/clc.24305 (accessed May 2, 2026).
- Brendel JM, Walterspiel J, Hagen F, Kübler J, Brendlin AS, Afat S, et al. Coronary artery disease detection using deep learning and ultrahigh-resolution photon-counting coronary CT angiography. Diagn Interv Imaging 2025;106:68–75. https://doi.org/10.1016/j.diii.2024.09.012. DOI: https://doi.org/10.1016/j.diii.2024.09.012
- Huang Z, Xiao J, Wang X, Li Z, Guo N, Hu Y, et al. Clinical Evaluation of the Automatic Coronary Artery Disease Reporting and Data System (CAD-RADS) in Coronary Computed Tomography Angiography Using Convolutional Neural Networks. Academic Radiology 2023;30:698–706. https://doi.org/10.1016/j.acra.2022.05.015. DOI: https://doi.org/10.1016/j.acra.2022.05.015
Giấy phép
© 2026 Tác giả. Xuất bản bởi Tạp chí Sức khỏe và Lão hóa.

Tác phẩm này được cấp phép theo Giấy phép Creative Commons Ghi công-Phi thương mại-Không phái sinh 4.0 Quốc tế.
