Singapore, 20 Sep 2019 — Heart disease may soon be detected remotely, thanks to a wearable ultrasound device incorporating an Artificial Intelligence (AI)-assisted Automatic Heart Diagnosis System (AHDS) to be developed by a team of researchers from Ngee Ann Polytechnic (NP), National Heart Centre Singapore (NHCS) and Kumamoto University (KU), Japan.
Through the novel combination of wireless ultrasound and AI technologies, the device may be applied for the screening of various heart conditions in the early stages as well as treatment monitoring in the later stages. NP’s research team led by Dr Rajendra Archarya has extensive experience in signal and imaging processing techniques for diagnostic applications in cardiology. For instance, they have developed a machine learning system that has the potential to automatically diagnose coronary artery disease, myocardial infarction and congestive heart failure accurately on electrocardiogram. The collaboration will also leverage KU’s expertise in the research and development of non-invasive remote ultrasound technology as well as clinical inputs from Associate Professor Tan Ru San, Senior Consultant, and his team from the Department of Cardiology at NHCS.
Typically, a series of tests and evaluations have to be performed by doctors to diagnose heart conditions. In cardiology, ultrasound is a ubiquitous and versatile technique that allows real-time imaging of the heart and blood vessels for assessment of cardiovascular health. The ultrasound probe is placed on the skin overlying the heart or blood vessel of interest during the test, and the signal obtained is transmitted via a wire that attaches the ultrasound probe to the scanner, which processes the signal to produce images. While the technique is portable, diagnostic information can only be garnered at the time of the scan, which typically lasts 30 to 60 minutes.
The team plans to deploy the prototype for clinical trials at a community hospital in Singapore.
English
Automatic Heart Diagnosis System-NP x KU x NHCS_media release (final).pdf