Why the study?
Fractional flow reserve is the reference standard for assessing the functional impact of coronary stenosis, prompting evaluation of artificial intelligence models to predict non-invasive measurements.
Can artificial intelligence models accurately predict coronary stenosis severity using non-invasive fractional flow reserve compared to invasive measurements?
Can artificial intelligence models accurately predict coronary stenosis severity using non-invasive fractional flow reserve compared to invasive measurements?
A feed-forward neural network shows promise in predicting fractional flow reserve non-invasively, achieving 72% diagnostic accuracy in a small real-world patient sample.
No takes yet. Share an insight, caveat, or question.
AI models may noninvasively estimate FFR; leaves open prospective validation before clinical use.
Carson et al. (2020) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: