| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Coenen, Adriaan, et al.
(författare)
-
Diagnostic Accuracy of a Machine-Learning Approach to Coronary Computed Tomographic Angiography-Based Fractional Flow Reserve Result From the MACHINE Consortium
- 2018
-
Ingår i: Circulation Cardiovascular Imaging. - : LIPPINCOTT WILLIAMS & WILKINS. - 1941-9651 .- 1942-0080. ; 11:6
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Coronary computed tomographic angiography (CTA) is a reliable modality to detect coronary artery disease. However, CTA generally overestimates stenosis severity compared with invasive angiography, and angiographic stenosis does not necessarily imply hemodynamic relevance when fractional flow reserve (FFR) is used as reference. CTA-based FFR (CT-FFR), using computational fluid dynamics (CFD), improves the correlation with invasive FFR results but is computationally demanding. More recently, a new machine-learning (ML) CT-FFR algorithm has been developed based on a deep learning model, which can be performed on a regular workstation. In this large multicenter cohort, the diagnostic performance ML-based CT-FFR was compared with CTA and CFD-based CT-FFR for detection of functionally obstructive coronary artery disease. Methods and Results: At 5 centers in Europe, Asia, and the United States, 351 patients, including 525 vessels with invasive FFR comparison, were included. ML-based and CFD-based CT-FFR were performed on the CTA data, and diagnostic performance was evaluated using invasive FFR as reference. Correlation between ML-based and CFD-based CT-FFR was excellent (R=0.997). ML-based (area under curve, 0.84) and CFD-based CT-FFR (0.84) outperformed visual CTA (0.69; Pamp;lt;0.0001). On a per-vessel basis, diagnostic accuracy improved from 58% (95% confidence interval, 54%-63%) by CTA to 78% (75%-82%) by ML-based CT-FFR. The per-patient accuracy improved from 71% (66%-76%) by CTA to 85% (81%-89%) by adding ML-based CT-FFR as 62 of 85 (73%) false-positive CTA results could be correctly reclassified by adding ML-based CT-FFR. Conclusions: On-site CT-FFR based on ML improves the performance of CTA by correctly reclassifying hemodynamically nonsignificant stenosis and performs equally well as CFD-based CT-FFR.
|
|
| 5. |
|
|
| 6. |
- Hill, JA, et al.
(författare)
-
Medical Misinformation
- 2019
-
Ingår i: Circulation. Cardiovascular imaging. - 1942-0080. ; 12:2, s. e008809-
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Nagueh, Sherif F., et al.
(författare)
-
Interobserver Variability in Applying American Society of Echocardiography/European Association of Cardiovascular Imaging 2016 Guidelines for Estimation of Left Ventricular Filling Pressure
- 2019
-
Ingår i: Circulation Cardiovascular Imaging. - 1941-9651 .- 1942-0080. ; 12:1
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND:Assessment of left ventricular (LV) filling pressure is among the important components of a comprehensive echocardiographic report. Previous studies noted wide limits of agreement using 2009 American Society of Echocardiography/European Association of Echocardiography guidelines, but reproducibility of 2016 guidelines update in estimating LV filling pressure is unknown.METHODS:Echocardiographic and hemodynamic data were obtained from 50 patients undergoing cardiac catheterization for clinical indications. Clinical and echocardiographic findings but not invasive hemodynamics were provided to 4 groups of observers, including experienced echocardiographers and cardiology fellows. Invasively acquired LV filling pressure was the gold standard.RESULTS:In group I of 8 experienced echocardiographers from the guidelines writing committee, sensitivity for elevated LV filling pressure was 92% for all observers, and specificity was 93 +/- 6%. Fleiss kappa-value for the agreement in group I was 0.80. In group II of 4 fellows in training, sensitivity was 91 +/- 2%, and specificity was 95 +/- 2%. Fleiss kappa-value for the agreement in group II was 0.94. In group III of 9 experienced echocardiographers who had not participated in drafting the guidelines, sensitivity was 88 +/- 5%, and specificity was 91 +/- 7%. Fleiss kappa-value for the agreement in group III was 0.76. In group IV of 7 other fellows, sensitivity was 91 +/- 3%, and specificity was 92 +/- 5%. Fleiss kappa-value for the agreement in group IV was 0.89.CONCLUSIONS:There is a good level of agreement and accuracy in the estimation of LV filling pressure using the American Society of Echocardiography/European Association of Cardiovascular Imaging 2016 recommendations update, irrespective of the experience level of the observer.
|
|
| 10. |
|
|
