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
De Filippo, O., Mineo, R., Millesimo, M., Wańha, W., Proietto Salanitri, F., Greco, A., Leone, A. M., Franchin, L., Palazzo, S., Quadri, G., Tuttolomondo, D., Fabris, E., Campo, G., Giachet, A. T., Bruno, F., Iannaccone, M., Boccuzzi, G., Gaibazzi, N., Varbella, F., Wojakowski, W., Maremmani, M., Gallone, G., Sinagra, G., Capodanno, D., Musumeci, G., Boretto, P., Pawlus, P., Saglietto, A., Burzotta, F., Aldinucci, M., Giordano, D., De Ferrari, G. M., Spampinato, C., D'Ascenzo, F., Non-invasive physiological assessment of intermediate coronary stenoses from plain angiography through artificial intelligence: the STARFLOW system, <<EUROPEAN HEART JOURNAL. QUALITY OF CARE & CLINICAL OUTCOMES (ONLINE)>>, 2024; (Oct 9): N/A-N/A. [doi:10.1093/ehjqcco/qcae024] [https://hdl.handle.net/10807/296076]
Non-invasive physiological assessment of intermediate coronary stenoses from plain angiography through artificial intelligence: the STARFLOW system
Greco, Antonio;Leone, Antonio Maria;Burzotta, Francesco;
2024
Abstract
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
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
