Non-invasive physiological assessment of intermediate coronary stenoses from plain angiography through artificial intelligence: the STARFLOW system

被引：0

作者：

De Filippo, Ovidio ^{[1
]}

Mineo, Raffaele ^{[2
]}

Millesimo, Michele ^{[1
]}

Wanha, Wojciech ^{[3
]}

Salanitri, Federica Proietto ^{[2
]}

Greco, Antonio ^{[4
]}

Leone, Antonio Maria ^{[5
,6
]}

Franchin, Luca ^{[7
]}

Palazzo, Simone ^{[2
]}

Quadri, Giorgio ^{[8
]}

Tuttolomondo, Domenico ^{[9
]}

Fabris, Enrico ^{[10
]}

Campo, Gianluca ^{[11
]}

Giachet, Alessandra Truffa ^{[12
]}

Bruno, Francesco ^{[1
,6
]}

Iannaccone, Mario ^{[13
]}

Boccuzzi, Giacomo ^{[13
]}

Gaibazzi, Nicola ^{[9
]}

Varbella, Ferdinando ^{[14
]}

Wojakowski, Wojciech ^{[3
]}

Maremmani, Michele ^{[15
]}

Gallone, Guglielmo ^{[1
,16
]}

Sinagra, Gianfranco

Capodanno, Davide ^{[4
]}

Musumeci, Giuseppe ^{[8
]}

Boretto, Paolo ^{[1
]}

Pawlus, Pawel ^{[3
]}

Saglietto, Andrea ^{[1
,16
,17
]}

Burzotta, Francesco ^{[5
]}

Aldinucci, Marco ^{[16
,17
]}

Giordano, Daniela ^{[2
]}

De Ferrari, Gaetano Maria ^{[1
,16
,17
]}

Spampinato, Concetto ^{[2
]}

D'Ascenzo, Fabrizio ^{[1
,16
,17
]}

机构：

[1] Citta Salute & Sci Hosp, Cardiovasc & Thorac Dept, Div Cardiol, Corso Bramante 88, I-10126 Turin, Italy

[2] Univ Catania, Dept Elect Elect & Comp Engn, Viale Andrea Doria 6, I-95125 Catania, Italy

[3] Med Univ Silesia, Dept Cardiol & Struct Heart Dis, 18 Medykow St, PL-40752 Katowice, Poland

[4] Univ Catania, Div Cardiol, Azienda Osped Univ Policlin G Rodolico San Marco, Via S Sofia 78, I-95123 Catania, Italy

[5] Osped Isola Tiberina Gemelli Isola, Via Ponte Quattro Capi 39, I-00186 Rome, Italy

[6] Univ Cattolica Sacro Cuore, Dept Cardiovasc & Thorac Sci, Largo A Gemelli 1, I-00168 Rome, Italy

[7] Azienda Sanit Univ Friuli Cent, Santa Maria Misericordia Hosp, Cardiol Dept, Piazzale Santa Maria Misericordia 15, I-33100 Udin, Italy

[8] A O Ordine Mauriziano Umberto 1, Cardiol Dept, Largo Filippo Turati 62, I-10128 Turin, Italy

[9] Parma Univ Hosp, Dept Cardiol, Viale Antonio Gramsci 14, I-43126 Parma, Italy

[10] Univ Trieste, Azienda Sanit Univ Giuliano Isontina ASUGI, Cardiothoracovascular Dept, Via Giacomo Puccini 50, I-34148 Trieste, Italy

[11] Azienda Osped Univ Ferrara, Cardiovasc Inst, 8 Cona A Ferrara,Via Aldo Moro, I-44124 Cona A Ferrara, Italy

[12] Cardinal Massaia Hosp, Div Cardiol, Corso Dante Alighieri 202, I-14100 Asti, Italy

[13] San Giovanni Bosco Hosp, Div Cardiol, ASL Citta Torino, Piazza Donatore Sangue 3, I-10154 Turin, Italy

[14] Infermi Hosp, Intervent Cardiol Unit, Via Rivalta 29, I-10098 Rivoli, Torino, Italy

[15] Policlin San Marzo Grp San Donato, Dept Cardiol, Corso Europa 7, I-24046 Bergamo, Italy

[16] Univ Turin, Dept Med Sci, Turin, Italy

[17] Corso Bramante 88, I-10126 Turin, Italy

来源：

EUROPEAN HEART JOURNAL-QUALITY OF CARE AND CLINICAL OUTCOMES | 2024年

关键词：

Artificial intelligence; Fractional flow reserve; Instantaneous waves-free ratio; Percutaneous coronary intervention; Coronary physiology; FRACTIONAL FLOW RESERVE; WAVE-FREE RATIO; DIAGNOSTIC-ACCURACY; ARTERY-DISEASE; FOLLOW-UP; INTERVENTION; MULTICENTER; PERFORMANCE; QUANTIFICATION; OUTCOMES;

D O I：

10.1093/ehjqcco/qcae024

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Background Despite evidence supporting use of fractional flow reserve (FFR) and instantaneous waves-free ratio (iFR) to improve outcome of patients undergoing coronary angiography (CA) and percutaneous coronary intervention, such techniques are still underused in clinical practice due to economic and logistic issues.Objectives We aimed to develop an artificial intelligence (AI)-based application to compute FFR and iFR from plain CA.Methods and results Consecutive patients performing FFR or iFR or both were enrolled. A specific multi-task deep network exploiting 2 projections of the coronary of interest from standard CA was appraised. Accuracy of prediction of FFR/iFR of the AI model was the primary endpoint, along with sensitivity and specificity. Prediction was tested both for continuous values and for dichotomous classification (positive/negative) for FFR or iFR. Subgroup analyses were performed for FFR and iFR. A total of 389 patients from 5 centers were enrolled. Mean age was 67.9 +/- 9.6 and 39.2% of patients were admitted for acute coronary syndrome. Overall, the accuracy was 87.3% (81.2-93.4%), with a sensitivity of 82.4% (71.9-96.4%) and a specificity of 92.2% (90.4-93.9%). For FFR, accuracy was 84.8% (77.8-91.8%), with a sensitivity of 81.9% (69.4-94.4%) and a specificity of 87.7% (85.5-89.9%), while for iFR accuracy was 90.2% (86.0-94.6%), with a sensitivity of 87.2% (76.6-97.8%) and a specificity of 93.2% (91.7-94.7%, all confidence intervals 95%).Methods and results Consecutive patients performing FFR or iFR or both were enrolled. A specific multi-task deep network exploiting 2 projections of the coronary of interest from standard CA was appraised. Accuracy of prediction of FFR/iFR of the AI model was the primary endpoint, along with sensitivity and specificity. Prediction was tested both for continuous values and for dichotomous classification (positive/negative) for FFR or iFR. Subgroup analyses were performed for FFR and iFR. A total of 389 patients from 5 centers were enrolled. Mean age was 67.9 +/- 9.6 and 39.2% of patients were admitted for acute coronary syndrome. Overall, the accuracy was 87.3% (81.2-93.4%), with a sensitivity of 82.4% (71.9-96.4%) and a specificity of 92.2% (90.4-93.9%). For FFR, accuracy was 84.8% (77.8-91.8%), with a sensitivity of 81.9% (69.4-94.4%) and a specificity of 87.7% (85.5-89.9%), while for iFR accuracy was 90.2% (86.0-94.6%), with a sensitivity of 87.2% (76.6-97.8%) and a specificity of 93.2% (91.7-94.7%, all confidence intervals 95%).Conclusion The presented machine-learning based tool showed high accuracy in prediction of wire-based FFR and iFR. Graphical Abstract

引用

页码：343 / 352

页数：10

共 31 条

[11] Diagnosis of Ischemia-Causing Coronary Stenoses by Noninvasive Fractional Flow Reserve Computed From Coronary Computed Tomographic Angiograms Results From the Prospective Multicenter DISCOVER-FLOW (Diagnosis of Ischemia-Causing Stenoses Obtained Via Noninvasive Fractional Flow Reserve) Study [J].

Koo, Bon-Kwon ;

Erglis, Andrejs ;

Doh, Joon-Hyung ;

Daniels, David V. ;

Jegere, Sanda ;

Kim, Hyo-Soo ;

Dunning, Allison ;

DeFrance, Tony ;

Lansky, Alexandra ;

Leipsic, Jonathan ;

Min, James K. .

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2011, 58 (19) :1989-1997

[12] State-of-the-Art Deep Learning in Cardiovascular Image Analysis [J].

Litjens, Geert ;

Ciompi, Francesco ;

Wolterink, Jelmer M. ;

de Vos, Bob D. ;

Leiner, Tim ;

Teuwen, Jonas ;

Isgum, Ivana .

JACC-CARDIOVASCULAR IMAGING, 2019, 12 (08) :1549-1565

[13] Diagnostic Accuracy of Fractional Flow Reserve From Anatomic CT Angiography [J].

Min, James K. ;

Leipsic, Jonathon ;

Pencina, Michael J. ;

Berman, Daniel S. ;

Koo, Bon-Kwon ;

van Mieghem, Carlos ;

Erglis, Andrejs ;

Lin, Fay Y. ;

Dunning, Allison M. ;

Apruzzese, Patricia ;

Budoff, Matthew J. ;

Cole, Jason H. ;

Jaffer, Farouc A. ;

Leon, Martin B. ;

Malpeso, Jennifer ;

Mancini, G. B. John ;

Park, Seung-Jung ;

Schwartz, Robert S. ;

Shaw, Leslee J. ;

Mauri, Laura .

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2012, 308 (12) :1237-1245

[14] Diagnostic Performance of a Machine Learning-Based CT-Derived FFR in Detecting Flow-Limiting Stenosis [J].

Morais, Thamara Carvalho ;

Assuncao-Jr, Antonildes Nascimento ;

Dantas Junior, Roberto Nery ;

Grego da Silva, Carla Franco ;

de Paula, Caroline Bastida ;

Torres, Roberto Almeida ;

Magalhaes, Tiago Augusto ;

Nomura, Cesar Higa ;

Rodrigues de Avila, Luiz Francisco ;

Parga Filho, Jose Rodrigues .

ARQUIVOS BRASILEIROS DE CARDIOLOGIA, 2021, 116 (06) :1091-1098

[15] Virtual Fractional Flow Reserve From Coronary Angiography: Modeling the Significance of Coronary Lesions Results From the VIRTU-1 (VIRTUal Fractional Flow Reserve From Coronary Angiography) Study [J].

Morris, Paul D. ;

Ryan, Desmond ;

Morton, Allison C. ;

Lycett, Richard ;

Lawford, Patricia V. ;

Hose, D. Rodney ;

Gunn, Julian P. .

JACC-CARDIOVASCULAR INTERVENTIONS, 2013, 6 (02) :149-157

[16]

Neumann FJ, 2019, EUR HEART J, V40, P79, DOI [10.1093/eurheartj/ehy855, 10.15829/1560-4071-2019-8-151-226]

[17] 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].

Norgaard, Bjarne L. ;

Leipsic, Jonathon ;

Gaur, Sara ;

Seneviratne, Sujith ;

Ko, Brian S. ;

Ito, Hiroshi ;

Jensen, Jesper M. ;

Mauri, Laura ;

De Bruyne, Bernard ;

Bezerra, Hiram ;

Osawa, Kazuhiro ;

Marwan, Mohamed ;

Naber, Christoph ;

Erglis, Andrejs ;

Park, Seung-Jung ;

Christiansen, Evald H. ;

Kaltoft, Anne ;

Lassen, Jens F. ;

Botker, Hans Erik ;

Achenbach, Stephan .

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2014, 63 (12) :1145-1155

[18] Utilization and Outcomes of Measuring Fractional Flow Reserve in Patients With Stable Ischemic Heart Disease [J].

Parikh, Rushi V. ;

Liu, Grace ;

Plomondon, Mary E. ;

Sehested, Thomas S. G. ;

Hlatky, Mark A. ;

Waldo, Stephen W. ;

Fearon, William F. .

JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2020, 75 (04) :409-419

[19] Feasibility of coronary angiogram-derived vessel fractional flow reserve in the setting of standard of care percutaneous coronary intervention and its correlation with invasive FFR [J].

Pizzato, Patricia Ely ;

Samdani, Abdul Jawwad ;

Vergara-Martel, Armando ;

Dallan, Luis Augusto Palma ;

Pereira, Gabriel Tensol Rodrigues ;

Zago, Elder ;

Zimin, Vladislav ;

Bezerra, Hiram Grando .

INTERNATIONAL JOURNAL OF CARDIOLOGY, 2020, 301 :45-49

[20] Early Feasibility of Automated Artificial Intelligence Angiography Based Fractional Flow Reserve Estimation [J].

Roguin, Ariel ;

Abu Dogosh, Ala ;

Feld, Yair ;

Konigstein, Maayan ;

Lerman, Amir ;

Koifman, Edward .

AMERICAN JOURNAL OF CARDIOLOGY, 2021, 139 :8-14

← 1 2 3 4 →