The Times (UK)

Verifying Device

Nordic AI Institute

National Institutes of Health (NIH)

ClinicalTrials.gov

Cardiovascular News

Study Highlights Challenges In Using Ai Ecg Detection To Screen For Structural Heart Disease

Berci

The Sun

The Guardian

Superhuman AI tool spots heart disease in less than 2 seconds

dave lawrence

Dinis Guarda

Mirror

Ai Face Scans Heart Nhs 37608672

troovus

Dr. Ali Khan

Analytics Insight

AI Detects Hidden Heart Disease from ECGs in Under Two Seconds

Firstpost

Superhuman Ai Tool Study Finds Hidden Heart Disease Can Be Detected From Routine Ecg In Just 2 Seconds 14042383.Html

The Telegraph

Nhs To Use Ai Catch Undetectable Heart Disease Blink Of Eye

‘Superhuman’ AI tool spots heart disease in less than 2 seconds

Nature

Bridging the gap from clinical to home ECG: quantifying and overcoming accuracy loss in AI-enabled single-lead ECG models

An AI system developed at Imperial College London can reportedly analyze a standard ECG in under two seconds to detect signs of heart failure and heart valve disease. Findings were presented at the European Society of Cardiology annual congress in Munich in late August.

An AI system developed at Imperial College London can reportedly analyze a standard ECG in under two seconds to detect signs of heart failure and heart valve disease. Findings were presented at the European Society of Cardiology annual congress in Munich in late August.

In a U.S. trial involving around 67,000 patients, the AI correctly identified up to 81% of heart failure cases and up to 90% of those with heart valve disease. The system was trained on more than 10.6 million ECG recordings.

In a U.S. trial involving around 67,000 patients, the AI correctly identified up to 81% of heart failure cases and up to 90% of those with heart valve disease. The system was trained on more than 10.6 million ECG recordings.

Dr. Ahmed El-Medany, who led the Imperial College London analysis, described the system as "superhuman" for its ability to detect ECG patterns that clinicians cannot consistently identify on their own.

Dr. Ahmed El-Medany, who led the Imperial College London analysis, described the system as "superhuman" for its ability to detect ECG patterns that clinicians cannot consistently identify on their own.

The AI is designed as a screening and prioritisation tool rather than a standalone diagnostic device, as confirming heart failure or valve disease still requires an echocardiogram. Some NHS patients currently wait months for that scan after referral.

The AI is designed as a screening and prioritisation tool rather than a standalone diagnostic device, as confirming heart failure or valve disease still requires an echocardiogram. Some NHS patients currently wait months for that scan after referral.

The AI is currently being trialled on 600 NHS patients in London and Bristol, with a potential national rollout across six hospitals if results prove successful. Imperial College London has also established a spinout company, Cardiovolt.ai, to support clinical development.

The AI is currently being trialled on 600 NHS patients in London and Bristol, with a potential national rollout across six hospitals if results prove successful. Imperial College London has also established a spinout company, Cardiovolt.ai, to support clinical development.

Separately, researchers at the University of Tokyo found that an AI model could detect hypertension with over 90% accuracy and diabetes with over 80% accuracy from a five-second facial video, without requiring a blood pressure cuff or blood sample.

Separately, researchers at the University of Tokyo found that an AI model could detect hypertension with over 90% accuracy and diabetes with over 80% accuracy from a five-second facial video, without requiring a blood pressure cuff or blood sample.

The Times (UK) #

National Institutes of Health (NIH) #

Cardiovascular News #

The Sun #

The Guardian #

Mirror #

Analytics Insight #

Firstpost #

The Telegraph #

The Guardian #3763

Nature #

AI diagnosing heart failure from an ECG in under two seconds is a genuine breakthrough that could save thousands of lives. Trained on over 10 million real ECG results, the tool hit up to 90% accuracy spotting conditions invisible to the human eye. With nearly 400,000 people stuck on NHS waiting lists for heart tests, this technology is exactly the kind of fix the system desperately needs.

AI diagnosing heart failure from an ECG in under two seconds is a genuine breakthrough that could save thousands of lives. Trained on over 10 million real ECG results, the tool hit up to 90% accuracy spotting conditions invisible to the human eye. With nearly 400,000 people stuck on NHS waiting lists for heart tests, this technology is exactly the kind of fix the system desperately needs.

Ali Khan

Nordic Artificial Intelligence Institute

Labeling this ECG tool "superhuman" is pure hype that obscures serious performance problems outside hospital settings. In community populations, the model's positive predictive value dropped to just 14%, meaning six out of seven positive results were wrong. Deploying this at scale would flood the system with unnecessary follow-up testing, burdening health care resources without delivering reliable answers.

Labeling this ECG tool "superhuman" is pure hype that obscures serious performance problems outside hospital settings. In community populations, the model's positive predictive value dropped to just 14%, meaning six out of seven positive results were wrong. Deploying this at scale would flood the system with unnecessary follow-up testing, burdening health care resources without delivering reliable answers.

Berci Meskó

AI: Health Care

UK Elections: Health

AI Detects Heart Failure via ECG in Under 2 Seconds

AI Detects Heart Failure via ECG in Under 2 Seconds

Artificial Intelligence

Cardiovascular disease

Medicine & healthcare

United Kingdom

AI diagnosing heart failure from an ECG in under two seconds is a genuine breakthrough that could save thousands of lives. Trained on over 10 million real ECG results, the tool hit up to 90% accuracy spotting conditions invisible to the human eye. With nearly 400,000 people currently stuck on NHS waiting lists for heart tests, this technology could provide the kind of solution the system desperately needs.

AI diagnosing heart failure from an ECG in under two seconds is a genuine breakthrough that could save thousands of lives. Trained on over 10 million real ECG results, the tool hit up to 90% accuracy spotting conditions invisible to the human eye. With nearly 400,000 people currently stuck on NHS waiting lists for heart tests, this technology could provide the kind of solution the system desperately needs.

Labeling this ECG tool "superhuman" is hyperbole that exaggerates what this technology can actually do. Strong performance in a large U.S. trial is encouraging, but AI-ECG performance has been shown to fall in broader, lower-risk populations, where disease is less prevalent, milder and presents differently. In one community study, positive predictive value was just 14%. So the real test is whether these results will hold up in everyday NHS screening.

Labeling this ECG tool "superhuman" is hyperbole that exaggerates what this technology can actually do. Strong performance in a large U.S. trial is encouraging, but AI-ECG performance has been shown to fall in broader, lower-risk populations, where disease is less prevalent, milder and presents differently. In one community study, positive predictive value was just 14%. So the real test is whether these results will hold up in everyday NHS screening.

AI Detects Heart Failure via ECG in Under 2 Seconds

AI Detects Heart Failure via ECG in Under 2 Seconds

The Spin

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

AI Detects Heart Failure via ECG in Under 2 Seconds

AI Detects Heart Failure via ECG in Under 2 Seconds

The Spin

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters