AI breakthrough in NHS could 'prevent ­thousands of deaths from heart attacks'

705     0
Data from cardiac CT scans can be used alongside AI to identify heart problems (Image: PA)
Data from cardiac CT scans can be used alongside AI to identify heart problems (Image: PA)

An artificial intelligence revolution in the NHS could see thousands of heart attacks prevented, a trial shows.

Oxford University scientists have ­developed a program to identify small, previously undetectable narrowing of the arteries. About 350,000 Brits have cardiac CT scans every year but medics can only usually identify “significant” narrowing. Researchers analysed data on 40,000 patients undergoing routine scans and tracked their progress for three years.

Many patients with no significant narrowings went on to have heart attacks, some fatal. The AI program was trained using information on narrowings and other risk factors. The tool was tested on a further 3,393 patients over almost eight years and the software was able to accurately predict the risk of a heart attack. AI-generated risk scores were presented to medics for 744 patients, with 45% having their treatment plans altered by medics as a result.

Professor Charalambos Antoniades, of Oxford University and chairman of ­cardiovascular medicine at the British Heart Foundation, said: “Our study found that some patients presenting in hospital with chest pain, who are often reassured and sent back home, are at high risk of having a heart attack in the next decade, even in the absence of any sign of disease in their heart arteries. We hope that this AI tool will soon be implemented across the NHS, helping prevent ­thousands of avoidable deaths from heart attacks.”

The study is one of several machine-learning schemes being explored by the NHS. Earlier this year, the Mirror revealed how an advance in using AI to diagnose skin cancer is set to free up overstretched NHS dermatologists to see thousands more patients.

Teachers, civil servants and train drivers walk out in biggest strike in decade dqxikeidqkikdinvTeachers, civil servants and train drivers walk out in biggest strike in decade

The new technology, known as DERM, can identify 11 types of lesions, including common skin cancers, within seconds. As well as speeding up cancer diagnoses, the technology is expected to save busy dermatologists hundreds of thousands of hours, allowing them to see patients with other skin complaints, such as psoriasis, vitiligo, eczema and lupus, who get bumped down the list as cancer takes priority.

Martin Bagot

Artificial intelligence (AI), Heart disease, Heart attack, Hospitals, NHS

Read more similar news:

01.02.2023, 00:01 • Finance
Greggs, Costa & Pret coffees have 'huge differences in caffeine', says report
01.02.2023, 00:58 • News
Baby boy has spent his life in hospital as doctors are 'scared' to discharge him
01.02.2023, 12:12 • Politics
Do you support workers going on strike? Take our poll
01.02.2023, 12:40 • Politics
Sunak branded 'pathetic' for attempt to pin blame on Labour for mass strikes
01.02.2023, 13:13 • News
A twitching eye can sometimes be serious - signs, symptoms and when to see a GP
01.02.2023, 18:05 • News
Major UK hospital declares critical incident as struggling A&E department 'full'
01.02.2023, 21:13 • News
Butcher breast surgeon could have hundreds more victims after old database found
02.02.2023, 09:40 • News
Surprising symptom that 40% of women suffer weeks before a heart attack
02.02.2023, 09:43 • Politics
100,000 nurses and patients sign letter to Rishi Sunak calling for NHS wage rise
02.02.2023, 09:44 • News
Mum slams hospital after baby left disabled - 11 years later NHS admits fault