Heart failure, atrial fibrillation, and heart valve disease are serious conditions that often go undetected until advanced stages. Heart failure alone affects over a million people in the UK, with more than 70% diagnosed only after emergency hospital admission. Yet half of these patients will already have shown symptoms such as breathlessness, fatigue, or swelling. Early diagnosis is vital, and a new device now promises to pick up these conditions within seconds.

Researchers at Imperial College London (London, UK) have tested an artificial intelligence (AI)-enabled stethoscope designed to detect three heart conditions in a single sitting. About the size of a playing card, it records ECG signals and heart sounds, sending the data to secure cloud storage for AI analysis. Trained on tens of thousands of health records, the stethoscope has been manufactured by Eko Health (Oakland, CA, USA) and identifies subtle abnormalities invisible to the human ear.

The TRICORDER trial, one of the first large-scale AI research programs in British GP surgeries, involved 12,725 patients across 96 clinics. These patients were compared with those from another 109 control practices in the area. Patients assessed with the AI stethoscope were 2.33 times more likely to be diagnosed with heart failure, 3.45 times more likely with atrial fibrillation, and 1.92 times more likely with valve disease. The study showed that while two-thirds of suspected heart failure cases flagged by the tool were later ruled out, it has the potential to catch cases that would otherwise be missed.

The device could help primary care professionals identify patients who need potentially life-saving treatment sooner, before they become dangerously unwell. Researchers suggest that a wider rollout of the technology would require better integration into GPs' existing routines, as a significant number of surgeries stopped using the device after a year. The technology is already available in some clinics and is being extended to practices in Wales, South London, and Sussex.

“Our study shows that three heart conditions can now be identified in one sitting. Importantly, this technology is already available to some patients and being widely used in GP surgeries,” said Professor Nicholas Peters, senior investigator from Imperial College London and consultant cardiologist at Imperial College Healthcare NHS Trust.

http://www.gzjiayumed.com/en/index.asp