Left ventricular assessment with artificial intelligence increases the diagnostic accuracy of stress echocardiography

Jamie M O'Driscoll, William Hawkes, Arian Beqiri, Angela Mumith, Andrew Parker, Ross Upton, Annabelle McCourt, William Woodward, Cameron Dockerill, Nikant Sabharwal, Attila Kardos, Daniel X Augustine, Katrin Balkhausen, Badrinathan Chandrasekaran, Soroosh Firoozan, Anna Marciniak, Stephen Heitner, Mrinal Yadava, Sanjiv Kaul, Rizwan SarwarRajan Sharma, Gary Woodward, Paul Leeson

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

Aims
To evaluate whether left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS), automatically calculated by artificial intelligence (AI), increases the diagnostic performance of stress echocardiography (SE) for coronary artery disease (CAD) detection.

Methods and results
SEs from 512 participants who underwent a clinically indicated SE (with or without contrast) for the evaluation of CAD from seven hospitals in the UK and US were studied. Visual wall motion scoring (WMS) was performed to identify inducible ischaemia. In addition, SE images at rest and stress underwent AI contouring for automated calculation of AI-LVEF and AI-GLS (apical two and four chamber images only) with Ultromics EchoGo Core 1.0. Receiver operator characteristic curves and multivariable risk models were used to assess accuracy for identification of participants subsequently found to have CAD on angiography. Participants with significant CAD were more likely to have abnormal WMS, AI-LVEF, and AI-GLS values at rest and stress (all P < 0.001). The areas under the receiver operating characteristics for WMS index, AI-LVEF, and AI-GLS at peak stress were 0.92, 0.86, and 0.82, respectively, with cut-offs of 1.12, 64%, and −17.2%, respectively. Multivariable analysis demonstrated that addition of peak AI-LVEF or peak AI-GLS to WMS significantly improved model discrimination of CAD [C-statistic (bootstrapping 2.5th, 97.5th percentile)] from 0.78 (0.69–0.87) to 0.83 (0.74–0.91) or 0.84 (0.75–0.92), respectively.

Conclusion
AI calculation of LVEF and GLS by contouring of contrast-enhanced and unenhanced SEs at rest and stress is feasible and independently improves the identification of obstructive CAD beyond conventional WMSI.
Original languageEnglish
Article numberoeac059
JournalEuropean Heart Journal Open
Early online date21 Sept 2022
DOIs
Publication statusE-pub ahead of print - 21 Sept 2022

Fingerprint

Dive into the research topics of 'Left ventricular assessment with artificial intelligence increases the diagnostic accuracy of stress echocardiography'. Together they form a unique fingerprint.

Cite this