New Research Explores Using AI to Diagnose Congenital Heart Diseases

The AI-based cardiac disorder detection system will support physicians in the early diagnosis of congenital heart diseases instead of children undergoing expensive and lengthy diagnostic procedures directly.

Walton Institute at South East Technological University (SETU) is proud to announce that Dr Lizy Abraham, Head of the Emerging Networks Labs Division, has been named one of the successful awardees to secure funding under the SFI-IRC Pathway programme.

Minister for Further and Higher Education, Research, Innovation and Science, Patrick O’Donovan TD has announced a €14.6 million investment in 25 new research projects as part of the collaborative initiative between Science Foundation Ireland (SFI) and the Irish Research Council (IRC) to support early-career research across all disciplines and to encourage a cohesive research ecosystem in Ireland.

Dr Lizy’s project will explore An Artificial Intelligence (AI) – based Automated Approach for the Classification of Paediatric Heart Murmurs and Disease Diagnosis using Wireless Phonocardiography.

Congenital Heart Diseases (CHDs) are malformations that occur due to abnormal development of the heart at the birth of a child. Listening to the heart with a stethoscope to identify heart murmurs continues to be the most common clinical screening method to detect heart problems in newborns. However, it depends greatly on the physician’s experience.

The gold standard for diagnosis of CHD is echocardiography, but this has its limitations when performed on children as it takes almost 30 to 45 minutes, and the child should remain still during this time. Referring all children with a murmur for this expensive and lengthy diagnostic procedure is simply not feasible or cost-effective.

Using intelligent techniques to analyse a phonocardiogram (PCG) – a plot of heart murmurs obtained with a digital stethoscope – offers a valuable alternative. PCG signals combined with the power of AI can provide an objective interpretation of heart sounds to complement traditional auscultation methods.

“This research proposes an automated AI-based cardiac disorder detection system using the PCG heart sound signals,” explains Dr Lizy. “This will support physicians and primary health care providers in the early diagnosis of congenital heart diseases, instead of children undergoing expensive and lengthy diagnostic procedures directly.”

The funding, covering a four-year period, will provide additional support for a postgraduate student. The project will kick off in September 2024.