NHS doctors want ChatGPT AI to write patient heart reports so they can see more people
- Heart experts say using AI to write reports frees up time to see more patients
NHS heart experts want to use the artificial intelligence program ChatGPT to write vital patient reports – as they say it would free up time and allow more people to see.
The free-to-use software is already used by students and office workers to perform certain tasks.
And according to Dr Samer Alabed, a heart radiologist at Sheffield Teaching Hospitals NHS Foundation Trust, the AI program could be trained to interpret heart scans and take notes.
“It takes radiologists 45 minutes to analyze these scans and then write a report,” says Dr Alabed. ‘We estimate that NHS clinicians spend 115,000 hours each year compiling heart scan reports.
“If we could use software like ChatGPT to do this job, we could free up an incredible amount of time that could be used to treat more patients.”
NHS heart experts want to use ChatGPT artificial intelligence program to write vital patient reports –
Doctors say it would free up time and allow them to see more people
The software may also be able to do this in non-medical language so that patients can understand their results without the help of a doctor.
Dr. Alabed and his team are already experimenting with the program and hope to soon set up a clinical trial with a large group of patients with heart disease. The project is seen as the next step in the growing use of artificial intelligence in the NHS.
In December, the MoS revealed that clinicians at Sheffield Teaching Hospitals had begun using a specially designed AI program that could analyze MRI scans of the heart and perform complex measurements to determine if there were signs of disease.
These measurements usually take doctors 20 minutes, but the program can complete them in less than a minute. However, doctors have yet to write down their findings.
Dr. Alabed believes that the whole process can be completely done by AI. However, he adds that the team is still experiencing problems with ChatGPT that need to be resolved before the software can be used on the NHS.
“When we enter measurements into ChatGPT, we find that sometimes it adds extra details that are made up or not accurate,” he says.
“The next step is figuring out how to train it to be accurate every time so patients get the right diagnosis.”