Artificial intelligence could help NHS physios with exercise compliance

^{Ben Wanless: People need to understand new technology – not only how it works, but how it is going to help them}

One in seven UK adults own wearable fitness trackers, reflecting the UK’s appetite for wellbeing, says a report on AI in the NHS by think tank Reform.

Ben Wanless, consultant physiotherapist and AHP digital and innovation lead at St George's University Hospital NHS Trust, welcomed the research.

He said: ‘I work in MSK and the main benefit would be the ability to track someone’s physical activity and, very importantly, to know whether they are doing their exercises.’

The report, published in January, illustrates the areas where AI could help the NHS become more efficient and deliver better outcomes for patients. It also highlights the main barriers to the implementation of this technology and suggests some potential solutions.

AI could enable clinicians to identify those individuals with health conditions who are more likely to develop complications, it says.

One example is a team at the University of Manchester which used health data to cluster individuals into groups of people with similar characteristics. They plotted patients with diabetes, cardiovascular and respiratory disease together and are in the process of generating hypotheses that, had this approach not been taken, may never have been formed.

AI could address NHS efficiency and the funding gap by automating tasks, triaging patients to the most appropriate services and allowing them to self-care, according to the report.

For instance, there are many AI applications to enable self-care. One of these identifies where trauma patients should be treated on arrival at hospital with greater accuracy than out of hospital trauma teams.

The report warns, however, that public trust and confidence is vital for the successful development of AI. The NHS will also need to get data right to truly harness the potential of AI in healthcare. This means collecting the right type of data in the right format, increasing its quality and securely allowing access to it.

It points out that the healthcare system is still heavily reliant on paper files and most of its IT systems are not based on open-standards. This limits the exchange of information across the health system.

Increasing the quality of the data collected within the NHS is of crucial importance as the accuracy and fairness of AI algorithms are wholly dependent on the data they are being fed.

Mr Wanless said clinicians needed training and time to adopt and fully exploit AI and called for the NHS to invest in digital equipment and in supporting staff to use it.

‘People need to understand new technology – not only how it works, but how it is going to help them. And they need to know that it can be used to create more efficient processes,’ he said.

‘Just because something is digital does not mean it is better. It is only better if it improves efficiency and leads to better patient care. If you cover those things, then clinicians are more likely to engage.’