EP01.08: Artificial intelligence to assist in the screening fetal anomaly ultrasound scan (PROMETHEUS): a randomised controlled trial

To undertake a randomised trial of an artificial intelligence (AI) tool to assist the fetal anomaly screening ultrasound scan. Outcome measures were the diagnostic performance of the scan in detecting congenital heart disease (CHD, selected for the trial as the most common group of fetal malformations), scan duration, sonographer cognitive load, and repeatability and reproducibility of biometric measurements. Pregnant participants (all singleton pregnancies) with fetal CHD and with healthy fetuses were recruited and scanned with both methods. Screening sonographers were recruited from regional hospitals and were randomised to scan with the AI tool or in the standard fashion, blinded to the fetal CHD status. For the AI-assisted scans, the AI models identified and saved 13 standard image planes, and measured four biometrics. 78 pregnant participants (26 with fetal CHD) were recruited and scanned using both methods. 58 sonographers were recruited and randomised. The sensitivity and specificity of the AI-assisted scan in detecting CHD was 88.9% and 98.0% respectively, with the standard scan achieving 81.5% and 92.2% (not significant). The AI-assisted scans were significantly shorter in duration than the standard scans (median 11.4 min vs 19.7 min, p < 0.001). Sonographer cognitive load was significantly lower in the AI-assisted group (median NASA TLX score 35.2 vs 46.5, p < 0.001). For all four biometrics, the AI repeatability and reproducibility was superior to manual measurements. AI assistance in the routine fetal anomaly ultrasound scan results in a significant time saving of around 42%, along with a reduction in sonographer cognitive load, without a reduction in diagnostic performance. Automatically measured biometrics using our technique are highly repeatable and reproducible. Further work to integrate disease detection models into the tool prototype are ongoing.