--- title: "Imperial College AI detects heart disease from ECGs in under two seconds" publication: "MediaBias News" url: "https://mediabias.news/health/imperial-college-ai-detects-heart-disease-from-ecgs-in-under-two-seconds" api: "https://mediabias.news/api/v1/stories/imperial-college-ai-detects-heart-disease-from-ecgs-in-under-two-seconds" markdown: "https://mediabias.news/health/imperial-college-ai-detects-heart-disease-from-ecgs-in-under-two-seconds.md" audio: "https://mediabias.news/api/audio/imperial-college-ai-detects-heart-disease-from-ecgs-in-under-two-seconds" category: "Health" area: "United Kingdom" published: "2026-09-01T21:47:13.879Z" source_reported: "2026-09-01T18:39:38.000Z" updated: "2026-09-01T21:47:13.879Z" trust_score: 78 critic_score: 75 hype_score: 25 assessment_type: "coverage-and-source-reporting-analysis" fact_check_status: "not-performed" coverage_measured: "2026-09-02T00:00:10.354640+00:00" --- # 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* **Scores for the source reporting** (0-100, assessing the original journalism this article was written from, not this write-up): - Trust 78 of 100, higher is better. Two full reports corroborate key figures and methods. - Craft 75 of 100, higher is better. Quotes and figures are clearly separated from comment. - Hype 25 of 100, lower is better. Headlines are lively but not exaggerated. Scored by MediaBias News; method at https://mediabias.news/methodology. **The short version** - 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. 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. ## Who covered it Shares of the 10 covering outlets with a published leaning rating: - Left: 40% (4) - Centre: 10% (1) - Right: 50% (5) 19 of 29 covering outlets carried no usable leaning rating and were excluded from those percentages. Coverage measured 2026-09-02T00:00:10.354640+00:00. **Coverage watch:** developing. Checked 11 times; 0 checks found a material change. Most recently checked 2026-09-02T00:30:09.983Z. ## How the sides framed it ### Left - 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 - 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 - 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. ## Factuality profile of the covering outlets These are published factuality ratings of the outlets, not a verdict on whether this story or its claims are true. - mixed: 5 - high: 4 - unknown: 19 - veryHigh: 1 ## Verification scope This page compares coverage and scores the source reporting. It is not a ClaimReview verdict on whether the underlying event or claim is true. ## Original reporting this was written from - [REALITATEA.NET](https://realitatea.net/stiri/actualitate/revolutie-in-medicina-inteligenta-artificiala-depisteaza-bolile-de-inima-in-mai-putin-de-doua-secunde-cum-functioneaza-tehnologia-salvatoare-eotjru) — REVOLUTION IN THE MEDICINAL PRODUCT! Artificial Intelligence Detects Heart Disease in Less than Two Seconds: How Lifesaving Technology Works - [n-tv](https://n-tv.de/wissen/KI-erkennt-Herzleiden-innerhalb-von-Sekunden-id31256196.html) — "Superhuman" Technology: AI Detects Heart Disease Within Seconds - [DiarioBitcoin](https://diariobitcoin.com/tecnologia/una-ia-lee-un-electrocardiograma-en-dos-segundos-y-detecta-senales-que-pueden-escapar-a-los-cardiologos) — An AI Reads an Electrocardiogram in Two Seconds and Detects Signals that Can Escape to Cardiologists - [dnews.gr](https://dnews.gr/eidhseis/science/607532/yperanthropo-ergaleio-texnitis-noimosynis-entopizei-kardiakes-pathiseis-se-ligotero-apo-dyo-defterolepta) — 'Superhuman' AI Tool Detects Heart Disease in Less than Two Seconds - [FuturoProssimo](https://futuroprossimo.it/2026/09/unai-legge-lelettrocardiogramma-e-batte-i-cardiologi-in-2-secondi) — An AI Reads the Electrocardiogram and Beats the Cardiologists in 2 Seconds - [Analytics Insight](https://analyticsinsight.net/news/ai-detects-hidden-heart-disease-from-ecgs-in-under-two-seconds) — AI Detects Hidden Heart Disease from ECGs in Under Two Seconds - [news4health.gr](https://news4health.gr/digital-health/i-texniti-noimosyni-borei-na-entopisei-tin-kardiaki-aneparkeia-se-ligotero-apo-dyo-defterolepta) — Artificial Intelligence Can Detect Heart Failure in Less than Two Seconds - [TNW](https://thenextweb.com/news/imperial-ai-ecg-heart-disease-detection) — An AI reads an ECG in two seconds and finds what cardiologists cannot - [technewstube.com](https://technewstube.com/the-next-web/1863202/ai-reads-ecg-two-seconds-finds-cardiologists-cannot) — An AI reads an ECG in two seconds and finds what cardiologists cannot - [onliner.by](https://tech.onliner.by/2026/09/01/issledovateli-testiruyut-ii-sposobnyj-vyyavit-problemy-s-serdcem-za-dve-sekundy) — Researchers Test an AI Capable of Detecting Heart Problems in Two Seconds - Onlíner Technology - [healthandme.com](https://healthandme.com/health-news/new-ai-tool-reads-ecg-in-2-seconds-detects-up-to-90-of-heart-valve-disease-cases-article-156023070) — New AI Tool Reads ECG In 2 Seconds, Detects Up To 90% Of Heart Valve Disease Cases - [SANA](https://sana.sy/miscellaneous/2568775) — An Artificial Intelligence Device that Reveals Signs of Heart Disease in Less than Two Seconds. - [Mugglehead Magazine](https://mugglehead.com/ai-flags-heart-disease-from-routine-ecg-test-within-seconds) — AI flags heart disease from routine ECG test within seconds - [computersweden.se](https://computersweden.se/article/4216816/nytt-ai-verktyg-kan-upptacka-hjartsjukdom-pa-under-tva-sekunder.html) — New AI Tool Can Detect Heart Disease in Under Two Seconds - [Halk TV](https://halktv.com.tr/dunya/insanustu-yapay-zeka-kalp-hastaligini-iki-saniyede-tespit-ediyor-1052265h) — "Superhuman" Artificial Intelligence Detects Heart Disease in Two Seconds. - [Adevarul](https://adevarul.ro/stil-de-viata/tehnologie/o-noua-tehnologie-bazata-pe-ai-detecteaza-boli-de-2553262.html) — A New AI-Based Technology Detects Heart Disease in Less than Two Seconds. Doctors Are Amazed: "Superhuman Artificial intelligence." - [Startup Fortune](https://startupfortune.com/this-ai-reads-an-ecg-in-two-seconds-and-beats-cardiologists-at-diagnosis) — This AI Reads an ECG in Two Seconds and Beats Cardiologists at Diagnosis - [Firstpost News](https://firstpost.com/tech/superhuman-ai-tool-study-finds-hidden-heart-disease-can-be-detected-from-routine-ecg-in-just-2-seconds-14042383.html) — Superhuman AI tool: Study finds hidden heart disease can be detected from routine ECG in just 2 seconds - [distilledpost.com](https://distilledpost.com/post/artificial-intelligence-enables-instantaneous-detection-of-heart-disease) — Artificial Intelligence Enables Instantaneous Detection of Heart Disease - [Hot News](https://hotnews.ro/un-instrument-de-ai-suprauman-detecteaza-bolile-cardiace-in-mai-putin-de-2-secunde-2337924) — The AI "Superhuman" Instrument that Detects in Less than Two Seconds some of the Most Serious Global Conditions - HotNews.ro - [Unknown](https://dimokratia.gr/ygeia/739332/guardian-neo-ai-ergaleio-allazei-ti-diagnosi-kardiopatheion) — Guardian: New AI Tool Changes Heart Disease Diagnosis - [antena3.ro](https://antena3.ro/high-tech/medicii-au-creat-un-ai-suprauman-care-poate-depista-boli-de-inima-in-mai-putin-de-doua-secunde-cum-functioneaza-801517.html) — Doctors Have Created an AI "Superhuman" that Can Detect Heart Disease in Less than Two Seconds. - [NewsBomb](https://newsbomb.gr/ygeia/story/1760076/yperanthropo-ai-entopizei-kardiopatheies-se-ligotero-apo-2-defterolepta-vlepei-ypertasi-diaviti) — "Superhuman" AI Detects Heart Disease in Less than 2 Seconds - "Sees" Hypertension, Diabetes - [nordisch.info](https://nordisch.info/natur-forschung/bahnbrechend-herzkrankheiten-mit-ki-in-zwei-sekunden-erkennbar) — Groundbreaking: Heart Diseases with AI Can Be Detected in Two Seconds - [Daily Mirror](https://mirror.co.uk/news/health/ai-face-scans-heart-nhs-37608672) — AI could diagnose heart disease after five-second face scan - [The Sun](https://thesun.co.uk/health/40227156/doctors-diagnose-heart-disease-seconds-ai-ecg-nhs-trial) — NHS trials AI to spot heart disease in just two seconds - as 400K on waitlist - [Britské listy](https://blisty.cz/art/135746-nadlidsky-nastroj-ai-odhali-srdecni-onemocneni-za-mene-nez-2-sekundy.html) — "Superhuman" AI Tool Detects Heart Disease in Less Than 2 Seconds - [The Telegraph](https://telegraph.co.uk/news/2026/08/31/nhs-to-use-ai-catch-undetectable-heart-disease-blink-of-eye) — NHS to use AI to catch undetectable heart disease 'in blink of an eye' - [Cardiovascular News](https://cardiovascularnews.com/study-highlights-challenges-in-using-ai-ecg-detection-to-screen-for-structural-heart-disease) — Study highlights challenges in using AI-ECG detection to screen for structural heart disease ## Questions **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. --- MediaBias News — https://mediabias.news. Reproduced from https://mediabias.news/health/imperial-college-ai-detects-heart-disease-from-ecgs-in-under-two-seconds. Please cite as: MediaBias News, "Imperial College AI detects heart disease from ECGs in under two seconds", https://mediabias.news/health/imperial-college-ai-detects-heart-disease-from-ecgs-in-under-two-seconds