The number of patients missing doctor’s appointments has been cut by almost a third in an artificial intelligence (AI) trial that could save the cash-strapped NHS a fortune.
No-shows are responsible for more than a million missed GP appointments every month – equivalent to one in twenty scheduled consultations.
This increases pressure on a healthcare system already burdened by the demands of an aging population.
Now a Leeds-based software company has developed an AI tool that predicts which patients are likely to not turn up for their appointments.
AI victory: TPP has developed a tool that reduces the number of patients who don’t show up for GP appointments
The company, TPP, uses machine learning models to analyze patterns in patient behavior based on a range of factors.
The algorithms analyze demographic details including age, gender and appointment booking history.
Younger male adults from lower socio-economic backgrounds in urban areas are most likely to miss GP appointments, Dr Chris Bates, TPP’s director of research and analysis, told the Mail on Sunday.
He said patients who live closest to their GP surgery are more likely to miss a consultation than those who live further away, although it is not clear why this is the case.
Armed with the information about the type of patient most likely to miss an appointment, GP practices can take action to encourage them to show up, for example by sending them extra text alerts just before the appointment is due, or by to call.
The idea is not to deprive patients of the opportunity to see their doctor based on an AI profile, but instead to encourage them to come by giving them additional reminders.
“There has been too much hype about AI in healthcare and not enough has been delivered – we are changing this,” he said.
“This is a brilliant example of what machine learning will bring to healthcare, helping to tackle real-world problems for frontline teams and patients,” added Dr. Bates added.
Missed appointments cost the NHS £216 million a year, according to its own figures – enough to pay for 2,325 full-time doctors.
The scale of the crisis prompted former Prime Minister Rishi Sunak to consider fining patients £10 for each missed consultation, but the idea was quietly abandoned.
A successful trial of the technology in Norfolk is now being rolled out across the country.
“Since we started using the report we have seen our DNA (Did Not Attend) rate fall by 30 per cent, which equates to hundreds of appointments since the start of the pilot,” said Karen Bell, operations manager at the Trinity and Bowthorpe practice, which has more than 11,000 patients.
Patients marked as red or orange and at risk of not attending will be sent a text message the night before their appointment, she added.
TPP is also using AI to help oncologists detect ovarian and other cancers in patients much earlier than previously possible.
“The DNA Algorithm is just the start – we are about to launch a range of AI solutions focused on the NHS’s key clinical and operational priorities,” added Dr. Bates added.