NHS will expand use of waiting list-busting AI after pilot

AI for waiting-list
Bradley Pisney

Artificial intelligence software designed to tackle missed appointments and reduce waiting lists will see its use by the NHS ramp up after a successful pilot deployment.

The software, created by Deep Medical and described as an “AI receptionist”, will be used by 10 NHS trusts across England after being put through its paces by Mid and South Essex NHS Foundation Trust.

The software uses insights, including people’s jobs, childcare commitments, live traffic, and weather updates to determine those most unlikely to show up, and re-arranges appointments at what it predicts will be a convenient time – for example, giving evening and weekend slots to those less able to take time off during the day.

Using machine learning, the programme populates a doctor’s patient list for the day to include additional patients.

In the pilot, the AI led to a 30% fall in ‘did not attends’ (DNAs) over six months, preventing 377 and allowing an additional 1,910 patients to be seen. The trust has estimated that could translate to a saving of £27.5 million ($35 million) a year.

The wide rollout comes as NHS England strives to bring down a 7.6 million waiting list for elective procedures, which is being exacerbated by a DNA rate of one in 20 hospital appointments. The cost of missed appointments across the whole country is about £1.2 billion, according to the NHS.

The Deep Medical software’s creators, an AI expert and junior doctor turned clinical entrepreneur, claim their product can predict DNAs with 90% accuracy.

“The use of AI to help reduce the number of missed appointments is another example of how new technologies are helping to improve care for patients, and ensuring the health service is making the best and most efficient use of taxpayers’ money,” said Dr Vin Diwakar, national director for transformation at NHS England.

“Not only can these technologies help to free up doctors’ time to treat more patients and reduce waiting times for planned care, it means a significant amount of money can be invested in frontline care, rather than lost to missed appointments,” he added.

The ramp-up in use comes after Chancellor Jeremy Hunt announced £3.4 billion of funding for the NHS to double its investment in new technology.

AI is being used in other ways to tackle waiting lists in the NHS, as well. Last year, Cheshire and Merseyside Integrated Care System (ICS) deployed an AI developed by C2-Ai to prioritise patients for elective treatment, aiming to clear the backlog more efficiently, whilst also providing support for patients while waiting.

Meanwhile, University Hospitals Coventry and Warwickshire (UHCW) NHS Trust has been using AI to help improve patient care and pathways through “process mining”, which helps them see how well their processes are working, revealing bottlenecks and other areas of improvement.

The pilot looked at DNAs and identified a spike in last-minute cancellations after two text reminders had been sent. It also found that messaging patients 14 days before an appointment and a follow-up four days before was most effective, as this meant they could cancel earlier and re-book the appointment in plenty of time. DNAs for this subset of patients dropped from 10% to 4%.

Photo by Bradley Pisney on Unsplash