Skip to the story
All StoriesPoliticsConflict & SecurityBusiness & EconomyScience & TechHealthClimateMedia
All stories
Health29 outlets ran this5 min read

Imperial College AI detects heart disease from ECGs in under two seconds

Researchers say the tool could prioritise echocardiogram referrals for patients flagged as high risk

AI-assisted coverage comparison, editor-supervised · How this was made

Published
ai image

What this story says

  • Researchers at Imperial College London developed an AI tool that analyses ECGs in under two seconds to detect heart failure and valve disease.
  • The AI identified up to 81% of heart failure cases and 90% of valve disease cases in a US study of 67,000 patients.
  • The tool is intended as a screening method to prioritise echocardiogram referrals, not as a final diagnostic test.
  • The findings were presented at the European Society of Cardiology congress in Munich.

Who covered it

Left 40%(4)Centre 10%(1)Right 50%(5)

Percentages are shares of the 10 outlets carrying a published leaning rating. 19 of the 29 outlets we know ran this story carry no rating and are not counted in them. Coverage measured .

Trust

78/100

Craft

75/100

Hype

25/100

29 sources · methodology

Researchers at Imperial College London developed an artificial intelligence tool that analyses electrocardiograms in under two seconds. The system detects signs of heart failure and valve disease that clinicians may not reliably identify through routine visual assessment of ECG traces.

The AI was trained on over 1.6 million ECGs from Brazil and several million from the United States. In a study involving 67,000 patients in the US, the tool identified up to 81% of heart failure cases and 90% of valve disease cases. The findings were presented at the European Society of Cardiology congress in Munich.

The tool is intended as a screening method to prioritise patients for echocardiogram referrals. Researchers expect it to help reduce waiting times for scans, which can currently take months. The AI is not designed to replace echocardiograms or clinical examinations as a final diagnostic test.

What the coverage left out

None of the right-rated digests mentioned the number of people in the UK with undiagnosed heart conditions or the length of NHS waiting lists for cardiology. The Daily Mirror’s full report was the only one to cite figures for undiagnosed hypertension, diabetes, and heart disease in the UK.

The separate AI study diagnosing high blood pressure and diabetes from facial videos was covered only by the Daily Mirror. No other outlet mentioned this development or its potential implications for screening.

Tags:#ArtificialIntelligence#HeartDisease#MedicalInnovation#NHS#ECG#Echocardiogram

Still developing. We have re-checked which outlets are covering this 8 times, most recently on 1 Sept 2026, 23:45, and will add the sides that appear.

How each side covered it

Our own reading of the reporting listed below, written from the outlets’ articles rather than quoted from them. The reasoning is set out on our methodology page.

Left

4 rated outlets

  • The four left-rated digests led on the potential for faster diagnosis and the scale of undiagnosed heart conditions in the UK. The Daily Mirror’s full report highlighted that the AI could flag heart failure and valve disease from routine ECGs, which currently cannot detect them. It also covered a separate AI study that diagnosed high blood pressure and diabetes from a five-second facial video.
  • The Daily Mirror quoted Dr Ahmed El-Medany, who led the ECG analysis, saying the AI performed at “superhuman” levels and could be “transformative” for the NHS. It reported that around 16 million people in the UK have hypertension, four million have Type 2 diabetes, and over eight million have heart diseases, many undiagnosed. The report also noted that half a million people are on NHS cardiology waiting lists.
  • TNW’s digest focused on the AI’s ability to identify signs of heart failure and valve disease that clinicians cannot detect from the same ECG trace. SANA’s digest described the tool as capable of accelerating diagnosis and early detection. Hot News’s digest emphasised the technology’s potential to speed up treatment for high-risk patients.

Centre

1 rated outlet

  • Analytics Insight’s full report led on the AI’s development and its potential to help doctors decide which patients need faster cardiac scans. It described the tool as analysing “subtle electrical patterns” within ECG recordings that may not be detectable through routine visual assessment.
  • The report quoted Dr El-Medany calling the technology “superhuman” for its ability to detect patterns invisible to clinicians. It also quoted Professor Fu Siong Ng, who said the AI could help prioritise patients for echocardiograms, reducing waiting times. The report noted that the tool is being developed through Cardiovolt.ai, a spinout from Imperial College London.

Right

5 rated outlets

  • The four right-rated digests led on the speed and accuracy of the AI tool. REALITATEA.NET’s digest described it as an “ultra-fast diagnostic tool” that provides doctors with rapid results. n-tv’s digest highlighted the AI’s ability to detect up to 90% of at-risk patients using an ECG.
  • Firstpost’s digest focused on the AI’s potential to help hospitals prioritise echocardiogram referrals. The Sun’s digest reported that the AI is being trialled in the NHS to diagnose heart disease in as little as two seconds. None of the right-rated digests mentioned the separate AI study on facial video diagnosis for high blood pressure and diabetes.

Questions about this coverage

How did the left and right cover Imperial College AI detects heart disease from ECGs in under two seconds?
Of the 10 outlets on this story carrying a published leaning rating, 40% are rated left, 10% are rated centre, 50% are rated right. Those percentages are shares of the rated outlets, not of every outlet that ran it, which was 29. The sections above set out what each side emphasised, in its own terms.
Is Imperial College AI detects heart disease from ECGs in under two seconds left or right?
Too few of the outlets on this story carry a published leaning rating to say. 10 of them do, and this site does not characterise a field under 12: at that size one newsroom filing moves the share by ten points. The percentages above are the count as it stands.
Is the coverage of Imperial College AI detects heart disease from ECGs in under two seconds biased?
Imperial College AI detects heart disease from ECGs in under two seconds is one event reported by 29 outlets, and this page does not rate the story as biased or unbiased. What it publishes is the spread: which outlets ran it, where named rating organisations place each of them on the spectrum, and what each side chose to lead with. A leaning rating describes an outlet's record over time, not this article, and the two should not be run together.
Which outlets covered Imperial College AI detects heart disease from ECGs in under two seconds?
29 that we know of, every one of them listed further up this page with a link to its own report and to what we hold on the publisher. Nothing here is a summary of somebody else's summary: the outlets are named so the original reporting can be read.
How accurate is the AI tool in detecting heart disease?
The AI tool identified up to 81% of heart failure cases and 90% of valve disease cases in a US study of 67,000 patients. It was trained on over 1.6 million ECGs from Brazil and several million from the US to detect patterns linked to these conditions.
How does the AI tool work?
The AI analyses electrocardiograms in under two seconds to detect signs of heart failure and valve disease. It identifies subtle electrical patterns in ECG recordings that clinicians may not reliably recognise through routine visual assessment.
Is the AI tool being used in the NHS?
The AI tool is currently being trialled on 600 NHS patients in London and Bristol. If successful, it could be rolled out across the NHS within five years to prioritise patients for echocardiogram referrals.
What did the coverage leave out?
The right-rated digests did not mention the number of people in the UK with undiagnosed heart conditions or the length of NHS waiting lists. Only the Daily Mirror covered a separate AI study diagnosing high blood pressure and diabetes from facial videos.

Read it at the source

29 outlets, grouped by the leaning a published rating gives them. Every headline links to the original; an underlined outlet name opens our profile of that publisher.

Left

4

Centre

1

Right

5

Not rated

19
Show 11 more

How did this read?

About the coverage, not about the story. We do not ask whether you agree with what happened — we have no honest use for that answer.

More in Health

All Health →
CDC Excludes Pennsylvania Measles Deaths Amid Investigation2 min readCDC Excludes Pennsylvania Measles Deaths Amid InvestigationRead storyTrump administration strikes drug pricing deals with nine companies3 min readTrump administration strikes drug pricing deals with nine companiesRead storyProvette degli esami del sangue - RIPRODUZIONE RISERVATA2 min readXylitol linked to increased heart attack and stroke riskRead story

Elsewhere on the site

Congressman Massie Accuses Prince Andrew of US Sex CrimesMedia•3 min readCongressman Massie Accuses Prince Andrew of US Sex CrimesMet Office to confirm 2026 as UK's hottest summer on recordClimate•3 min readMet Office to confirm 2026 as UK's hottest summer on recordRussian Ambassador to UK Andrei Kelin Ends TenurePolitics•3 min readRussian Ambassador to UK Andrei Kelin Ends TenureСнимка: Getty ImagesPolitics•2 min readUK doubles maximum fine for sanctions breaches to 100%
Imperial College AI detects heart disease from ECGs in under two seconds | MediaBias News