Fetal EchoScan

Fetal EchoScan is a machine learning-based diagnostic software designed to assist physicians in interpreting second-trimester fetal heart ultrasound examinations to identify suspicious cardiac abnormalities. Its development involved a computational approach to recognize specific radiographic findings, and studies demonstrated its high sensitivity and specificity, significantly improving physician diagnostic accuracy.

The Fetal EchoScan, a radiological computer-assisted diagnostic software developed by BrightHeart, has successfully undergone regulatory review and achieved substantial equivalence to a legally marketed predicate device. Classified as a Class II medical device, it is now permitted for marketing, contingent on adherence to general controls, including annual registration, device listing, good manufacturing practices, and truthful labeling, confirming its compliance with necessary regulatory standards for market entry. Fetal EchoScan functions as a machine learning-based software specifically designed to aid physicians in the interpretation of second-trimester fetal heart ultrasound examinations for pregnant women. It is adept at identifying suspicious radiographic findings, such as an overriding artery, various septal defects, abnormal outflow tract relationships, and discrepancies in cardiac size or axis deviations. Performance data, derived from both standalone testing and a comprehensive clinical reader study, consistently demonstrated high sensitivity and specificity in detecting these abnormalities, with the reader study particularly highlighting a significant improvement in physicians' diagnostic accuracy, evidenced by increases in area under the curve (AUC), sensitivity, and specificity when using the Fetal EchoScan compared to unaided readings.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific machine learning algorithms are employed by Fetal EchoScan, and how are they trained to ensure robustness across diverse ultrasound imaging equipment and patient populations?; Beyond the mentioned findings (overriding artery, septal defects, abnormal outflow tract relationships, cardiac size discrepancies, axis deviations), what is the device's performance in detecting other less common but significant fetal cardiac anomalies?; Was the clinical reader study conducted across multiple institutions or with diverse physician experience levels to assess the generalizability of improved diagnostic accuracy?; What are the false positive and false negative rates for each specific abnormality detected, and how do these impact clinical management decisions?; Are there any known limitations or specific types of ultrasound image quality where Fetal EchoScan's performance might be compromised, and what are the recommendations for mitigating these?