fbpx
Connect with us

News

NHS AI Lab calls for ‘proof of concept’ projects to develop AI in healthcare

Avatar photo

Published

on

An expert AI team which is part of the NHS Transformation Directorate will develop a new round of projects where artificial intelligence can overcome issues in healthcare. 

The NHS AI Lab Skunkworks team of data scientists, engineers and project leaders are providing free short-term expertise and resources to public sector health and social care organisations. 

They are now calling for applications – as part of a ‘proof of concept’ scheme, and will hopefully develop AI to support health in both clinical and business contexts.

AI – proof of concept

A ‘proof of concept’ programme is essentially a pilot project which demonstrates a design, idea or trial in the hope of proving it effective and feasible. 

In this case, AI will be developed for varied tasks, including the finding of optimal placement schedules for nursing students. 

It may also be used for automated bed allocation, and using machine learning to better understand risk within the NHS. 

Lab Skunkworks will support the health service in learning how to best benefit from AI solutions – which should alleviate pressures and improve healthcare  in the long term.

AI in action – nurse placements

As part of the huge project, a tool or approach will be developed which automatically generates student nurse placement schedules. 

The idea is that it will adhere to the requirements and constraints of the different stakeholders, while additionally providing a more diverse range of placements for the students.

A report reads: “We worked with Imperial College Healthcare NHS Trust, in conjunction with North West London CCGs to undertake this project to develop an AI-driven solution to the problem of placing students. 

“Imperial hosts students from seven universities, placing them across three hospitals, totalling more than 80 wards and placement settings. 

“Imperial College Healthcare NHS Trust is one the largest acute trusts in the UK (according to the Kings Fund), so would provide substantial evidence as to whether this solution was viable. 

“The data used was anonymised as this task could be undertaken without needing to provide any details on a personal level. 

“Instead, information about the hospitals were taken, and randomly generated student profiles were created containing examples of the information the Trust would have about each student.

“The task posed here is one of optimisation, of which there are many different approaches. 

“The method selected was a Genetic Algorithm, where the best version of something is found through a process which is like the evolutionary process seen in nature.”

The algorithm 

  • Create a population of objects (in this case, it was a population of potential schedules for all students)
  • Apply ‘mutations’ and produce ‘offspring’ from this population of objects
  • Mutations were produced by randomly changing the allocated ward for a random placement
  • Offspring were produced by combining schedules e.g. taking the front half of one schedule, and the back half of another schedule and sticking them together to produce a hybrid
  • Put the ‘mutated’ and ‘offspring’ objects back into the population, and score the population
  • The scoring part is key, as this is what dictates what a ‘good’ schedule looks like. This is where you define what absolutely cannot be in a schedule, and what you’d like a good schedule to have
  • Repeat the process hundreds of times until you have found a schedule which meets all your needs.

Read about other case studies and examples here.

Working with you

If you have an idea  for using AI-driven technology to explore your data the team would love hear from you. 

  • Become a member of the AI Virtual Hub to hear about new initiatives and discuss the use of AI for health and care.
  • Contact the NHS AI Lab Skunkworks team at [email protected] 

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Trending stories