‘Superhuman’ AI Tool Spots Heart Disease in Less Than 2 Seconds
Technology trained on millions of routine ECGs could fast-track high-risk patients for treatment
TL;DR
- A new AI tool can analyze routine ECGs to detect heart disease in under two seconds.
- The technology is trained on millions of patients and extracts more information from ECGs than the human eye can see.
- It can spot signs of heart failure and heart valve disease, common forms of heart disease.
- In a trial, the AI identified up to 81% of patients with heart failure and up to 90% with heart valve disease.
- This breakthrough could significantly boost early diagnosis, enabling faster access to lifesaving medicines.
- ECGs are a common medical test, with about a billion performed globally each year.
- The AI tool aims to prioritize patients for echocardiograms, reducing waiting times.
- It also has the potential to identify heart conditions in individuals where they are not initially suspected.
- Future developments may include handheld AI-led ECG readers.
- Separately, AI analysis of facial videos shows promise in detecting undiagnosed high blood pressure and type 2 diabetes.