Evaluation of an artificial intelligence algorithm (HeartAssistᵀᴹ) in the assessment of fetal cardiothoracic ratio: a prospective study

Abstract

share the first authorship.Introduction: To study intra-observer and inter-observer repeatability and inter-method agreement between manual and automatic methods in assessing fetal thoracic circumference (TC), cardiac circumference (CC), and cardiac/thoracic circumference ratio (C/T). Material and methods: In a prospective study on low-risk pregnant women undergoing second-trimester ultrasonographic examination, a frame of the thoracic circumference was obtained at the level of the 4-chamber view.For each frame the TC, CC, and C/T were measured offline by 2 examiners manually and by HeartAssist TM artificial intelligence software. Intra-and inter-observer repeatability and inter-method agreement between manual and automatic methods were analysed. Results: Fifty consecutive pregnant women were considered at a median gestational age of 20.9 weeks. All intraclass correlation coefficients (ICC) comparing manual with heart assist were > 0.929. Intra-and inter-observers ICC were respectively > 0.971 and > 0.931 for all the 3 variables, representing good agreement. The time necessary to obtain the measurements was significantly lower using heart assist than the manual method (82 s vs. 22.5 s; p < 0.0001). Conclusions: Heart assist allows automatic measurement of the C/T ratio. This technique was reproducible and reached the same accuracy as that of manual measurements. Heart assist is faster than manual and has the potential to become the preferred technique to obtain cardiac biometry.