UCLH and UCL working together to find AI solutions to operational and research questions 

26/07/2019 00:00 

UCLH has developed artificial intelligence to predict which patients are most likely to miss appointments.

A team of researchers from UCLH and UCL has been scrutinising appointments for MRI scans to create an algorithm which can help identify 90 per cent of those patients unlikely to attend their appointment.

Another team of UCL researchers working with colleagues from King’s College London is developing a new artificial intelligence (AI)-based method for detecting the brain’s response to treatment in multiple sclerosis (MS).

And the government has awarded a third team of researchers at UCL and UCLH £3.3 million in funding to apply artificial intelligence to tackle the global threat of anti-microbial resistance (AMR).

These are just three of many ongoing collaborations being facilitated by the NIHR UCLH Biomedical Research Centre which is spearheading UCLH’s research hospital initiative which seeks to embed advanced modelling techniques into real world clinical practice.

Anti-microbial resistance
The AMR project is being led by Prof Judy Breuer at UCL and her team, which includes Prof Peter Wilson at UCLH. The Precision AMR initiative aims to improve tests for antimicrobial resistance and to develop AI algorithms to rapidly interpret test results.

The team also hopes to enable earlier diagnosis and treatment with the right antibiotic; ensure treatment with the right dose and combination of drugs; and prevent the spread of antibiotic resistant infections.

They also want to be able to confirm more quickly cases where no antibiotic resistant infection is present in patients, so that unnecessary treatment is not given.

Brain’s response to MS treatment
The development of a new AI-based method for detecting the brain’s response to treatment in multiple sclerosis hopes to surpass what a human expert is able to do using conventional techniques.

The researchers, including Dr Parashkev Nachev and Prof Olga Ciccarelli of UCL and UCLH, hope this method will be used in future to predict an individual’s response to a drug before they start treatment, and which drug a patient should be given.

One way of assessing MS treatment response is by analysing patients’ MRI scans. At present, radiologists assess scans by counting the number of lesions and measuring lesion volumes, comparing these observations with those made on scans done before treatment started.

But the researchers’ new AI-based method of analysing scans means that regions of the brain can be analysed in much greater detail, and in a way which more closely reflects the complexity of the brain.

Patients failing to attend appointments
Researchers created an algorithm using records from 22,000 appointments for MRI scans, allowing them to identify 90 per cent of those patients who would turn out to be no-shows.

“On average we estimate this could save £2-3 per appointment,” Dr Nachev told The Guardian. “Given that a big hospital could have nearly a million scheduled events per year, that could potentially be a lot of resource.”

The team took data such as the time of day, number of previous scans and how far from the hospital the person lived. The data did not include gender, age or ethnicity, details which are kept in a patient’s medical records, but are not as easy to extract from the hospital’s appointments database. These factors could help improve predictions but they chose not to include them because they wanted to come up with a tool that could be readily rolled out under existing IT infrastructure.

The technology could allow the hospital to target reminder phone calls at those most likely to be unreliable. Currently, the hospital calculates it has to call 11 people to prevent one appointment being missed. Under a more targeted system, this could be reduced to five.

 Latest news

 GP Contact details

GP communications
2nd floor central
250 Euston Road
London NW1 2PG

General enquiries
Telephone: 020 3447 9083
Email: UCLH.gpqueries@nhs.net

GP web app:
Telephone: 020 3447 9000

GP enquiry lines and web app:
Call UCLH services direct from your smart phone or tablet: www.uclh.nhs.uk/mobile

Bookmark and Share
UCLH Instagram