NHS AI expansion to help tackle missed appointments and improve waiting times

The NHS is set to roll out AI to reduce the number of missed appointments and free up staff time to help bring down the waiting list for elective care.

The expansion to ten more NHS Trusts follows a successful pilot in Mid and South Essex NHS Foundation Trust, which has seen the number of did not attends (DNAs) slashed by almost a third in six months.

Created by Deep Medical and co-designed by a frontline worker and NHS clinical fellow, the software predicts likely missed appointments through algorithms and anonymised data, breaking down the reasons why someone may not attend an appointment using a range of external insights including the weather, traffic, and jobs, and offers back-up bookings.

The appointments are then arranged for the most convenient time for patients – for example, it will give evening and weekend slots to those less able to take time off during the day.

The system also implements intelligent back-up bookings to ensure no clinical time is lost while maximising efficiency.

It has been piloted for six months at Mid and South Essex NHS Foundation Trust, leading to a 30% fall in non-attendances. A total of 377 DNAs were prevented during the pilot period and an additional 1,910 patients were seen. It is estimated the trust, which supports a population of 1.2 million people, could save £27.5 million a year by continuing with the programme.

The AI software is now being rolled out to ten more trusts across England in the coming months.

As part of a focus to recover elective care following the pandemic and bring down long waits for routine care, the NHS is embracing new technology and innovations like AI to reduce hundreds of thousands of missed hospital appointments every month, ensuring that clinical time is used effectively and meaning patients on the waiting list can be seen more quickly.

Published data shows that of 124.5 million outpatient appointments across the NHS in England last year, eight million (6.4%) were not attended by the patient. It is estimated this level of missed appointments has an annual cost to the NHS of £1.2 billion.

Figures for last year also show the highest proportion of missed appointments were physiotherapy - with more than one in 10 appointments marked as DNAs (11%) - followed by cardiology (8.9%), ophthalmology (8.8%), and trauma and orthopaedics (7.9%). 

Dr Vin Diwakar, National Director for Transformation at NHS England, said: “The NHS has long been a pioneer of innovation, embracing new ways of working so patients get the help they need in a timely way, and 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.

“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.

"And the work being done across the country through these AI pilots shows that initiatives like this can deliver results in a short period of time, while also supporting patients to take control over their own care and help to better understand and reduce health inequalities."

Last week's budget committed to an additional £3.4 billion of capital funding, so the NHS can double investment in new technology and continue to build on the work already being done.

New initiatives rolled out in the NHS have seen DNAs reduce by about half a million a year, and with the additional investment, it is expected this could lead to hundreds of thousands of DNAs being avoided each month.

Health Minister Lord Markham said: “Artificial intelligence is transforming the way we deliver healthcare, and this technology will help cut waiting lists and allow hundreds of thousands more patients to be seen every year. 

“Alongside this, it will free up doctors’ time, deliver quicker test results, and save tens of millions of pounds every year.

“These kind of benefits are exactly why AI forms a central part of our £3.4bn plan to boost productivity in the NHS – alongside a wider package to replace outdated IT systems and unlock up to £35 billion in savings.” 

Charlotte Williams, Chief Strategy and Improvement Officer at Mid and South Essex NHS Foundation Trust, said:  “Reducing wasted appointments, providing a better service to our patients and supporting those who may find it difficult to attend has really shown positive impact.

“Embracing new technologies is something the Trust is passionate about, it also supports better access for people who are disabled and for working women, as a working mum I know how sometimes it can be hard to juggle work and childcare as well as managing your own health needs.” 

At University Hospitals Coventry and Warwickshire (UHCW) NHS Trust they 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.

Process mining also allows the Trust to look at a cohort of patients who may be being treated by several specialities and whether their appointments can be grouped together at the same time.

During the pilot, they used AI to look at DNAs - which are more common among those with high deprivation scores - and identified a spike in last-minute cancellations after two SMS reminders had been sent. Through this work, they found messaging patients 14 days before an appointment and a follow-up four days before was most effective, as it meant they could cancel earlier and re-book the appointment in plenty of time.

As a result, the trust saw their DNAs in this subset of patients drop from 10% to 4%, and they are now looking at expanding process mining to theatres to see where they can make efficiencies and improvements there.

Professor Andy Hardy, Chief Executive Officer, University Hospitals Coventry and Warwickshire NHS Trust said:  “Working with IBM and Celonis we have been able to continue a patient-first approach, while combining process research and process mining to identify areas we can further improve patient experiences and outcomes - through these exciting technologies we have been able to make changes far more quickly than we would have before, and have seen the number of missed appointments drop as a result.

"Using AI gives us a far bigger picture of our patient demographics and needs, rather than just booking them in for appointments chronologically, and it massively improves the patient experience - we know that getting patients seen quickly improves outcomes, and we are looking forward to continuing to work with AI and expand its use beyond DNAs, where even more patients will benefit."

Sheffield Children's NHS Foundation Trust has been piloting an AI tool developed by Alder Hey Innovation, which uses a range of markers including some that relate to health inequalities, to predict and identify children most at risk of missing their appointments.

Two of the major reasons for appointments being missed - known as "was not brought" in paediatric care - were parents forgetting to attend as they did not get reminders, or because they had no money for travel, so these were the areas Sheffield Children's focused on through the pilot to help remove those barriers.

The AI Predictor sent an additional text reminder with an offer of support to patients identified as having a greater than or equal to 50% chance of missing their appointments, which went out the day before the appointment. 

Over the first 12 months of the pilot 53,800 texts were sent - based on a benchmark non-attendance rate of 19.27% they expected 8,581 missed appointments, but through this initiative just under 6,500 patients were recorded as "was not brought" during the year. Almost 200 more appointments were attended each month as a result of this work.

They also used the AI Predictor to identify patients with a greater than or equal to 85% chance of missing their appointment, and contacted them to offer funded transport.  Over a 13-week period between September and December 2023, more than 300 families worked with the Sheffield Children's team, and as a result 152 had transport arranged via taxi, or bus tickets and parking permits paid for, and a further 129 appointments were rebooked to more convenient times. Based on their benchmark, this meant an additional five attendances each week by the highest risk patients.

 The pilots have been so successful at Sheffield Children's they are looking to continue and develop the initiatives so that they can make further reductions, and continue to learn and refine the understanding of missed appointments and the link to health inequalities.

Ruth Brown, Chief Executive of Sheffield Children’s NHS Foundation Trust and co-chair of the Children’s Hospital Alliance, said: “As part of our mission to provide a healthier future for children and young people we are committed to working together in partnership to tackle health inequalities in our communities - South Yorkshire is the fourth most deprived Integrated Care System in the country and Sheffield has five wards where more than 50% of children live in poverty, and we know there is a strong correlation between deprivation and lack of attendance for outpatient appointments.

"At Sheffield Children’s we are also keen to embrace technology and this opportunity to test out the effectiveness of Artificial Intelligence was one we welcomed, and it’s clear from our pilots - funded through the Children’s Hospital Alliance -  that our AI-driven interventions to support families with text reminders and transport and parking support have been very successful in reducing the number of Was Not Brought episodes.

"Missed appointments are lost opportunities to deliver healthcare to those who often need it the most, and each additional attendance we are able to support in this way means patient care is delivered, increasing patient safety; lives are improved; and an appointment space is freed up for another patient. This drives wider improvement of waiting lists and supports waiting list recovery and outstanding patient care."

Deep Medical was co-founded by Dr Benyamin Deldar and AI expert David Hanbury. Dr Deldar is a member of the NHS Clinical Entrepreneur Programme (NHS CEP) which is a development programme aimed at equipping NHS staff to develop commercial skills, knowledge and experience that will help them transform healthcare and stay within the health service.

Dr Deldar, co-founder of Deep Medical, said: “With a National NHS backlog of six million awaiting outpatient care and over eight million missed appointments each year, Deep Medical could help save lives by offering appointments to help bridge healthcare gaps for faster, more personalised experience without the long wait.

"We’ve already seen how the AI software has helped reduce missed appointments by 30% and gets other patients into the remaining 70% of missed appointments. This means, over time, Deep Medical will allow more and more appointments to be utilised; saving money and providing vital care to the public."