Aishani Vengala - Department of Pediatrics
Congenital heart disease (CHD) is a serious condition affecting about eight in every thousand births worldwide. Early detection is crucial as it prepares parents and healthcare providers for the necessary medical interventions. Traditionally, ultrasound scans are used to detect CHD during pregnancy, but these have limitations, often missing critical cases. In a recent study, researchers explored a novel approach using non-invasive fetal electrocardiography (ECG) combined with artificial intelligence (AI) to improve the detection rates of CHD. This method involves placing electrodes on the mother’s abdomen to capture the fetal heart's electrical activity. The captured data is then analyzed using an artificial neural network, a type of AI that mimics the human brain's learning process.
The study involved 122 fetal ECG recordings, with nearly half showing signs of CHD. The AI model achieved an accuracy of 71%, detecting 63% of all CHD cases and 75% of the most severe cases requiring immediate intervention after birth. The method was most effective when at least 37.5 minutes of ECG data was analyzed. This new approach has several advantages. It is non-invasive, reducing risks associated with other methods. It also does not rely on the expertise of a sonographer, as the AI can consistently analyze the data. However, the study found that detection performance varied slightly with gestational age and the length of ECG recordings. While promising, this method is still in its early stages. The study highlights the need for further research to improve the AI model's performance and to validate its clinical benefits. If successful, this technique could complement traditional ultrasound screenings, potentially becoming a standard practice for prenatal CHD detection and improving outcomes for affected infants.
References:
De Vries IR, Van Laar JOEH, Van der Hout-van der Jagt MB, Clur SB, Vullings R. Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease. Acta Obstet Gynecol Scand. 2023 Nov;102(11):1511-1520. doi: 10.1111/aogs.14623. Epub 2023 Aug 10. PMID: 37563851; PMCID: PMC10577634.
Edited by Aarti Palaniappan - Explorative Section Editor
コメント