Using a randomly selected sample from a real-world single-center cohort of patients, we demonstrated that machine learning based ML-FFRCT determination has good reproducibility and reliability.
Non-invasive determination of FFR has the potential to further enhance the gate-keeper role of CT angiography in patients evaluated for coronary artery disease by providing a functional compliment to anatomic assessment. Machine learning based FFR determination takes this one step further by offering several distinct advantages all the while maintaining comparative test characteristics to the current computational fluid dynamics-based approach[4,15].Specifically the advantages of a switch from off-site to on-site ML-based FFR determination may translate into reductions in test turn-around time (currently as high as 24 hours), rejection rate (~ 15%),[16–18] and cost combined with increased patient data protection by eliminating the need for data exporting and related infrastructural and logistical considerations .
Of the few studies that have looked at reproducibility of non-invasive FFR measurement, most have been on computational fluid dynamics-based methods. For example, a study with repeated off-site non-invasive FFRCT measurement (CFD-based method) on 25 patients showed good reproducibility. The study also went on report no significant difference when comparing FFRCT with FFR obtained from an invasive gold standard. However, few studies tackled potential operator dependence similar to the aim of our study. These studies featuring both on-site and off-site approaches have reported a high degree of inter-operator correlation which was consistent among operators of different expertise and training.[20,21] Moreover, the previously cited study also emphasized decreased variabilities in operators receiving face-to-face training . As such in-person training may counter a potential source of variability which has been the incorrect determination of centerline[20,22].
A case can be made to the generalizability of our findings to those presenting to a tertiary care cardiology practice as our study used a representative sample from a real-world cohort of patients with consistent results across spectrums of image quality and calcification.
However, our study is not without its limitations. This is an observational single center study including patients who had undergone both CCTA and SPECT with a relatively small sample size. Secondly, no comparison of ML-FFRCT measurements were made with a gold standard. However, two prior studies using invasive FFR as a gold standard have shown a high degree of accuracy with no significant change in variability between operators of varying levels of expertise[20,23]. Thirdly, the studied ML prototype is not yet approved for clinical use. But a meta-analysis showing high concordance between ML- FFRCT determination by machine learning (similar to our ML prototype) to invasive and computational flow dynamics, the studied ML prototype is yet not approved for clinical use. Although, the two investigators who processed images had no background in CCTA interpretation, it can be argued that future application of these approaches will be carried out by non-physicians and previous studies have confirmed consistent correlation in ML-FFRCT across a broad range of expertise .
In conclusion, we have shown a high degree of inter-operator reliability for machine learning based FFRCT in a representative patient population was excellent. Our study contributes to the body of literature supporting the role of machine learning based FFRCT determination in providing timely data for guiding revascularization strategies among patients being evaluated for coronary artery disease.