Use of Artificial Intelligence-Based Software to Aid in the Identification of Ultrasound Findings Associated With Fetal Congenital Heart Defects.
Authors
Affiliations (1)
Affiliations (1)
- Maternal Fetal Medicine Division Mount Sinai West, and the Division of Pediatric Cardiology, Icahn School of Medicine at Mount Sinai Hospital, Carnegie Imaging for Women PLLC, the New York University School of Medicine, and Maternal Fetal Medicine Associates, New York, New York; Pediatrics - Cardiology, Stanford University School of Medicine, Stanford, Pediatric Cardiology, Palo Alto Medical Foundation, Sutter Health, Palo Alto, and the Fetal Diagnostic Center of Pasadena, Pasadena, California; Université Grenoble Alpes, Fetal and Pediatric Cardiology, CHU Grenoble Alpes, Grenoble, the Medical Training Center, Rouen, and Centre d'Echographie de l'Odéon, UE3C-Unité d'explorations cardiologiques - Cardiopathies Congénitales, Cardiology, Hopital universitaire Necker-Enfants malades, and BrightHeart, Paris, France; Maternal Fetal Medicine, Michigan Perinatal Associates and Corewell Health, and Corewell Health East, Dearborn, and Wayne State University School of Medicine, Detroit, Michigan; Fetal Echocardiography and Perinatal Research-Valley Health System, Paramus, New Jersey; the Division of Maternal Fetal Medicine, Pennsylvania Hospital, University of Pennsylvania, Philadelphia, Pennsylvania; and Maternal Fetal Medicine, Perinatal Specialists of the Palm Beaches, West Palm Beach, Florida.
Abstract
To evaluate whether artificial intelligence (AI)-based software was associated with enhanced identification of eight second-trimester fetal ultrasound findings suspicious for congenital heart defects (CHDs) among obstetrician-gynecologists (ob-gyns) and maternal-fetal medicine specialists. A dataset of 200 fetal ultrasound examinations from 11 centers, including 100 with at least one suspicious finding, was retrospectively constituted (singleton pregnancy, 18-24 weeks of gestation, patients aged 18 years or older). Only examinations containing two-dimensional grayscale cines with interpretable four-chamber, left ventricular outflow tract, and right ventricular outflow tract standard views were included. Seven ob-gyns and seven maternal-fetal medicine specialists reviewed each examination in randomized order both with and without AI assistance and assessed the presence or absence of each finding suspicious for CHD with confidence scores. Outcomes included readers' performance in identifying the presence of any finding and each finding at the examination level, as measured by the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity. In addition, reading time and confidence were evaluated. The detection of any suspicious finding significantly improved for AI-aided compared with unaided readers with a significantly higher AUROC (0.974 [95% CI, 0.957-0.990] vs 0.825 [95% CI, 0.741-0.908], P=.002), sensitivity (0.935 [95% CI, 0.892-0.978] vs 0.782 [95% CI, 0.686-0.878]), and specificity (0.970 [95% CI, 0.949-0.991] vs 0.759 [95% CI, 0.630-0.887]). AI assistance also resulted in a significant decrease in clinician interpretation time and increase in clinician confidence score (226 seconds [95% CI, 218-234] vs 274 seconds [95% CI, 265-283], P<.001; 4.63 [95% CI, 4.60-4.66] vs 3.90 [95% CI, 3.85-3.95], P<.001, respectively). The use of AI-based software to assist clinicians was associated with enhanced identification of findings suspicious for CHD on prenatal ultrasonography.