NHS trials AI technology offering same-day diagnosis of aggressive lung cancer

Artificial intelligence (AI) is set to slash the time it takes for NHS patients to receive a lung cancer diagnosis.

The program analyses X-ray scans immediately after they are carried out and alerts doctors if any worrying signs are spotted.

It means a diagnosis could be reduced from as long as a week down to the same day.

Experts say early diagnosis is crucial for treating lung cancer, which is so aggressive that spotting it even just a few days earlier can save lives.

Doctors reviewing x-rays for possible signs of lung cancer can take up to a week to provide a diagnosis, which can harm the patient’s long-term prospects 

The software, developed by British Covid vaccine firm AstraZeneca and Indian tech company Qure AI, is being rolled out across Greater Manchester as part of a pilot study involving more than 250,000 people over the next six months

The software, developed by Indian tech company Qure.ai is being rolled out across Greater Manchester as part of a pilot study being led by British Covid vaccine firm AstraZeneca involving more than 250,000 people over the next six months. Doctors involved say that, if successful, the system could be used across the NHS.

AstraZeneca is now the second Covid vaccine-maker to turn its focus to artificial intelligence, as experts predict all NHS doctors will soon be expected to work with the high-tech software.

Every year, nearly 50,000 Britons are diagnosed with lung cancer. During that time, more than 35,000 people die of the disease, making it the UK’s biggest cancer killer.

An X-ray is usually the first test carried out for signs of the disease, which include growths in the lungs that could be tumours, and fluid or swollen lymph glands in the chest.

‘I’d say it is the hardest X-ray to analyse,’ says Professor Matt Evison, consultant chest physician at the Greater Manchester Cancer Alliance.

‘Because you’ve got so much going on in that area of the body – the spine as well as the lungs – you have to look very carefully. This means that it can take up to a week for patients to get their results.

‘Given how aggressive lung cancer is, this wait can make a real difference to how effective treatment will be.’

According to one study in The Lancet medical journal, delayed diagnosis and treatment of lung cancer in England is responsible for almost five per cent of deaths from the disease.

The AI software flags X-rays which show concerning signs of disease, so doctors can have a closer look at them first.

‘We still look at all the scans,’ says Prof Evison, ‘but this new system means we check the most worrying ones as a priority. You could get results the same day.

‘This is more important than ever given the immense pressure the health service is under right now. We need to make these diagnoses quickly, but we only have finite resources.

‘If this works, I could absolutely see this being used across the country.’

The news comes just days after Covid vaccine developer BioNTech – which worked with pharmaceutical giant Pfizer to create the first approved jab in the US – announced that it had bought the British artificial intelligence company InstaDeep for £562 million. BioNTech plans to use the firm’s technology to accelerate the process of developing drugs and vaccines.

Experts say AI will play an increasingly important role in the NHS over the coming decade.

‘Every NHS doctor will be trained to work with artificial intelligence in the near future,’ says Professor Nick Hawes, an AI expert at the University of Oxford. ‘It could be used to decide which treatment works best for a newly diagnosed cancer patient or create a much more effective 111 phone referral system.

‘Artificial intelligence will never replace doctors, but it will be an accompanying tool which speeds up the medical process.’