Study: AI Detects Heart Failure via ECG in Under 2 Seconds
The system identified up to 81% of heart failure cases and 90% of valve disease cases from ECGs, researchers said.
- On Monday, Imperial College London researchers presented an AI system at the European Society congress in Munich that reads ECGs in under two seconds to identify heart conditions clinicians often miss.
- Designed to address clinical capacity problems, researchers trained models on 1.6 million ECGs from The Brazilian dataset linked to patient records, enabling the system to learn predictive patterns.
- A trial covered 67,000 patients in the United States, with the team reporting 83% to 93% accuracy for heart disease and 70% to 80% accuracy for other conditions.
- The BHF-funded work is being commercialized through a spinout called Cardiovolt, with Professor Siong serving as chief medical officer; the AI is designed for triage rather than replacing clinicians.
- Moving from academic results to routine hospital use requires clinical validation and regulatory approval; the technology could eventually expand to Handheld ECG devices, identifying conditions including diabetes and kidney disease.
36 Articles
36 Articles
ECG-CLIP improves heart disease detection using less labeled data
Clinicians often use a medical test called a 12-lead electrocardiogram (ECG) to diagnose heart problems, which uses electrodes placed on the chest and limbs to record the heart's electrical activity.
An innovation developed by Imperial College in London uses artificial intelligence to interpret electrocardiograms (ECG) in less than two seconds. The system effectively identifies the risks of heart failure and valve diseases, providing doctors with an ultra-fast diagnostic tool.
Heart failure is a common problem. A British team of researchers is training an AI with millions of heart curves. Up to 90 percent of the patients at risk should be able to detect the software using an ECG.
An AI reads an ECG in two seconds and finds what cardiologists cannot
An ECG takes a few seconds to record and costs very little. Researchers at Imperial College London have trained an AI system that can read one in under two seconds and identify signs of heart failure and valve disease that clinicians cannot detect from the same trace. The results were presented at the European Society […] This story continues at The Next Web
Coverage Details
Bias Distribution
- 50% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
