Guardian

Scientists develop AI tool to spot heart failure risk five years before it strikes

Daily Mirror

New AI tool can spot heart disease five years before it develops

Daily Mail

Experts develop simple scan that can predict deadly heart failure - five years before it strikes

Radcliffe Department of Medicine, University of Oxford

New AI tool can predict heart failure at least five years before it develops

Independent

AI can predict a patients chance of getting heart disease five years before it develops

JACC Journals

Early Prediction of Heart Failure From Routine Cardiac CT Using Radiomic Phenotyping of Epicardial Fat

British Heart Foundation

Nature

Artificial intelligence bias in the prediction and detection of cardiovascular disease

Metaculus

Date AI Prescribes Most US Medication?

BeginnersinAI

Elon Musk

Rishi Sunak

Kamala Harris

Bill Gates

Andrew Ng

Yoshua Bengio

Fei-Fei Li

Demis Hassabis

Melanie Mitchell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Connor Leahy

Eliezer Yudkowsky

Jaan Tallinn

Marc Andreessen

Eric Schmidt

Norbert Wiener

Arthur Clarke

Irving John Good

Claude Shannon

Hans Moravec

John Smart

There's a "wall of fear-mongering and doomerism" in the AI world right now.

"Worrying about AI today is like worrying about overpopulation on Mars."

Concerns that AI could pose a threat to humanity is "preposterously ridiculous."

Claiming AI poses an existential threat is "such an extreme" and risks "wip[ing] out some of its potential benefits."

"I'm more concerned about... the risks that are here and now [than the existential threat of AI]."

Current AI is "not anywhere close" to posing an existential threat but it could in the future.

AI is the "biggest existential threat" to humanity.

AGI's worst-case scenario would be "lights-out for all of us."

Powerful AI systems "taking control" pose an "existential threat."

AI has a "10 to 25 per cent" chance of destroying humanity.

"The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die."

Does AI Pose an Existential Threat to Humanity?

Stuart Russell

Shane Legg

Society is more likely to get "cat-level" or "dog-level" AI years before human-level AI.

"[W]e will eventually reach AGI... and quite possibly before the end of this century."

"Superhuman AIs" will be achieved "between a few years and a couple of decades."

"Digital intelligence" could overtake us within "5 to 20 years."

We may achieve "something like AGI or AGI-like in the next decade."

"[W]e could get to real AGI in the next decade."

"Human-level" AI could occur in "two or three years."

"I'd be surprised if we don't have AGI by [2029]."

Will AI Surpass Human Intelligence, and When?

In their research published in the Journal of the American College of Cardiology on Wednesday, researchers at the University of Oxford said they have developed an AI tool that can predict a person's risk of heart failure up to five years before the condition develops, using routine cardiac CT scans.

In their research published in the Journal of the American College of Cardiology on Wednesday, researchers at the University of Oxford said they have developed an AI tool that can predict a person's risk of heart failure up to five years before the condition develops, using routine cardiac CT scans.

The tool detects textural changes in fat surrounding the heart that signal inflammation in the heart muscle — changes invisible to the human eye and undetectable through standard medical imaging tests.

The tool detects textural changes in fat surrounding the heart that signal inflammation in the heart muscle — changes invisible to the human eye and undetectable through standard medical imaging tests.

The AI was trained and validated using data from 72,751 adults across nine NHS centers in England between 2007 and 2022, predicting heart failure risk within five years with 86% accuracy.

The AI was trained and validated using data from 72,751 adults across nine NHS centers in England between 2007 and 2022, predicting heart failure risk within five years with 86% accuracy.

Patients in the highest risk group were around 20 times more likely to develop heart failure than those in the lowest risk group and had approximately a one-in-four chance of developing the condition within five years.

Patients in the highest risk group were around 20 times more likely to develop heart failure than those in the lowest risk group and had approximately a one-in-four chance of developing the condition within five years.

Around 350,000 patients are referred for cardiac CT scans in the U.K. each year. Researchers are seeking regulatory approval to add the tool to routine scan analysis in NHS radiology departments.

Around 350,000 patients are referred for cardiac CT scans in the U.K. each year. Researchers are seeking regulatory approval to add the tool to routine scan analysis in NHS radiology departments.

Researchers also plan to adapt the tool for use with any chest CT scan, not only cardiac scans. The British Heart Foundation funded the study.

Researchers also plan to adapt the tool for use with any chest CT scan, not only cardiac scans. The British Heart Foundation funded the study.

Guardian #

Daily Mirror #

Daily Mail #

Radcliffe Department of Medicine, University of Oxford #

Independent #

JACC Journals #

British Heart Foundation #

Nature #

Metaculus #

Researchers at the University of Oxford have developed an AI tool that can predict a person's risk of heart failure up to five years before the condition develops, using routine cardiac CT scans.

Researchers at the University of Oxford have developed an AI tool that can predict a person's risk of heart failure up to five years before the condition develops, using routine cardiac CT scans.

Around 350,000 patients are referred for cardiac CT scans in the UK each year. Researchers are seeking regulatory approval to add the tool to routine scan analysis in NHS radiology departments.

Around 350,000 patients are referred for cardiac CT scans in the UK each year. Researchers are seeking regulatory approval to add the tool to routine scan analysis in NHS radiology departments.

The British Heart Foundation, which funded the study, said heart failure is "consistently diagnosed too late." Researchers also plan to adapt the tool for use with any chest CT scan, not only cardiac scans.

The British Heart Foundation, which funded the study, said heart failure is "consistently diagnosed too late." Researchers also plan to adapt the tool for use with any chest CT scan, not only cardiac scans.

AI tools for heart disease prediction carry serious risks if built on biased data, and deploying them without an equity framework could deepen healthcare disparities for marginalized communities. Algorithmic bias stems from flawed training datasets, poor variable selection and lack of diverse research teams — all of which produce tools that fail the populations who need them most. Responsible AI development demands continuous bias monitoring, external validation across demographic groups and meaningful patient input.

AI tools for heart disease prediction carry serious risks if built on biased data, and deploying them without an equity framework could deepen healthcare disparities for marginalized communities. Algorithmic bias stems from flawed training datasets, poor variable selection and lack of diverse research teams — all of which produce tools that fail the populations who need them most. Responsible AI development demands continuous bias monitoring, external validation across demographic groups and meaningful patient input.

A groundbreaking AI tool developed at the University of Oxford can predict heart failure up to five years early using routine cardiac CT scans, giving doctors a powerful weapon against one of medicine's most devastating conditions. Trained on over 70,000 patients across nine NHS Trusts, the tool identifies invisible fat texture changes around the heart with 86 percent accuracy. Rolling this out nationwide could save countless lives by catching heart failure before irreversible damage sets in.

A groundbreaking AI tool developed at the University of Oxford can predict heart failure up to five years early using routine cardiac CT scans, giving doctors a powerful weapon against one of medicine's most devastating conditions. Trained on over 70,000 patients across nine NHS Trusts, the tool identifies invisible fat texture changes around the heart with 86 percent accuracy. Rolling this out nationwide could save countless lives by catching heart failure before irreversible damage sets in.

The AI Doc: Or How I Became an Apocaloptimist

Artificial Intelligence

AI Tool Predicts Heart Failure 5 Years Early

Health

Science & technology

This tool gives doctors a powerful weapon against one of medicine's most devastating conditions. Trained on over 70,000 patients across nine NHS Trusts, the tool identifies subtle changes in fat texture around the heart with 86% accuracy. Rolling this out nationwide could save countless lives by catching heart failure before irreversible damage sets in.

This tool gives doctors a powerful weapon against one of medicine's most devastating conditions. Trained on over 70,000 patients across nine NHS Trusts, the tool identifies subtle changes in fat texture around the heart with 86% accuracy. Rolling this out nationwide could save countless lives by catching heart failure before irreversible damage sets in.

Beginners in AI

Such tools carry serious risks if built on biased data, and deploying them without an equity framework could deepen healthcare disparities. Algorithmic bias stems from flawed training datasets, poor variable selection and a lack of diverse research teams. Responsible AI development demands continuous bias monitoring, external validation across demographic groups and meaningful patient input.

Such tools carry serious risks if built on biased data, and deploying them without an equity framework could deepen healthcare disparities. Algorithmic bias stems from flawed training datasets, poor variable selection and a lack of diverse research teams. Responsible AI development demands continuous bias monitoring, external validation across demographic groups and meaningful patient input.

There's a 50% chance that AI will independently prescribe the majority of medication in the U.S. before August 2046, according to the Metaculus prediction community.

There's a 50% chance that AI will independently prescribe the majority of medication in the U.S. before August 2046, according to the Metaculus prediction community.

New AI Tool Predicts Heart Failure 5 Years Early

New AI Tool Predicts Heart Failure 5 Years Early

The Spin

Metaculus Prediction

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

LeCun

Marcus

Bengio

Hinton

Hassabis

Altman

Amodei

Musk

Go Deeper

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

New AI Tool Predicts Heart Failure 5 Years Early

New AI Tool Predicts Heart Failure 5 Years Early

The Spin

Metaculus Prediction

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

LeCun

Marcus

Bengio

Hinton

Hassabis

Altman

Amodei

Musk

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