Published in:
01-06-2020 | Computed Tomography | Original Paper
Correlation of machine learning computed tomography-based fractional flow reserve with instantaneous wave free ratio to detect hemodynamically significant coronary stenosis
Authors:
Stefan Baumann, Markus Hirt, U. Joseph Schoepf, Marlon Rutsch, Christian Tesche, Matthias Renker, Joseph W. Golden, Sebastian J. Buss, Tobias Becher, Waldemar Bojara, Christel Weiss, Theano Papavassiliu, Ibrahim Akin, Martin Borggrefe, Stefan O. Schoenberg, Holger Haubenreisser, Daniel Overhoff, Dirk Lossnitzer
Published in:
Clinical Research in Cardiology
|
Issue 6/2020
Login to get access
Abstract
Background
Fractional flow reserve based on coronary CT angiography (CT-FFR) is gaining importance for non-invasive hemodynamic assessment of coronary artery disease (CAD). We evaluated the on-site CT-FFR with a machine learning algorithm (CT-FFRML) for the detection of hemodynamically significant coronary artery stenosis in comparison to the invasive reference standard of instantaneous wave free ratio (iFR®).
Methods
This study evaluated patients with CAD who had a clinically indicated coronary computed tomography angiography (cCTA) and underwent invasive coronary angiography (ICA) with iFR®-measurements. Standard cCTA studies were acquired with third-generation dual-source computed tomography and analyzed with on-site prototype CT-FFRML software.
Results
We enrolled 40 patients (73% males, mean age 67 ± 12 years) who had iFR®-measurement and CT-FFRML calculation. The mean calculation time of CT-FFRML values was 11 ± 2 min. The CT-FFRML algorithm showed, on per-patient and per-lesion level, respectively, a sensitivity of 92% (95% CI 64–99%) and 87% (95% CI 59–98%), a specificity of 96% (95% CI 81–99%) and 95% (95% CI 84–99%), a positive predictive value of 92% (95% CI 64–99%), and 87% (95% CI 59–98%), and a negative predictive value of 96% (95% CI 81–99%) and 95% (95% CI 84–99%). The area under the receiver operating characteristic curve for CT-FFRML on per-lesion level was 0.97 (95% CI 0.91–1.00). Per lesion, the Pearson’s correlation between the CT-FFRML and iFR® showed a strong correlation of r = 0.82 (p < 0.0001; 95% CI 0.715–0.920).
Conclusion
On-site CT-FFRML correlated well with the invasive reference standard of iFR® and allowed for the non-invasive detection of hemodynamically significant coronary stenosis.