AI predicts hospital stay lengths for people with learning disabilities
- 4 March 2025
- An AI model, developed in June 2024 by computer scientists at Loughborough University, is predicting how long a person with a learning disability is likely to stay in hospital
- It aims to tackle healthcare challenges faced by people with learning disabilities and multiple health conditions by offering valuable insights that could improve care and resource planning
- Results from the AI model show that cancer is the leading cause of hospital admissions for men and women with learning disabilities and multiple health conditions
Computer scientists at Loughborough University have developed an AI model to predict how long a person with a learning disability is likely to stay in hospital.
It was created as part of the ‘DECODE’ project, a collaborative research project funded by the National Institute for Health and Care Research (NIHR) that brings together researchers, clinicians and patients from seven UK universities and partner hospitals to Develop and Enhance the Care coordination for people with intellectual disabilities and multiple long term Conditions (DECODE).
The model, developed in June 2024, aims to tackle healthcare challenges faced by people with learning disabilities and multiple health conditions by offering insights that could improve care and resource planning.
Loughborough University researchers used GP and hospital data from more than 9,600 patients with learning disabilities and multiple health conditions to develop an AI model capable of predicting hospital stay lengths within the first 24 hours of admission.
Professor Georgina Cosma, an expert in AI for healthcare at Loughborough University and DECODE co-investigator, said: “The model generates predictions by assessing factors such as a patient’s age, medication history, lifestyle, and existing health conditions.
“With early and accurate predictions, hospitals can plan better and provide more personalised care, ensuring fair treatment for all patients.”
The AI model was tested using the dataset it was trained on and was 76% effective in distinguishing between patients likely to have prolonged hospital stays and those would be discharged sooner.
Results, detailed in a paper in the Frontiers in Digital Health published on 14 February 2025, showed that cancer is the leading cause of hospital admissions for men and women with learning disabilities and multiple health conditions, with epilepsy the most frequently treated condition for both genders during hospital stays.
On average, people with learning disabilities and multiple health conditions stay in hospital for three days and stays exceeding 129 days are often linked to mental illness, the AI model also found.
The insights from the study and the wider DECODE project will be used to support the NHS in developing risk prediction algorithms to assist clinicians in decision-making.
Professor Thomas Jun, an expert in sociotechnical system design at Loughborough University and DECODE co-principal investigator, said: “We’re now expanding our study to include a more diverse group of over 20,000 patients across England to ensure our predictive model is as accurate and effective as possible.
“We’re also seeking additional funding for a clinical trial to test how this personalised prediction tool can reduce emergency admissions and improve quality of life for patients with learning disabilities and multiple long-term conditions.”
The data used to train the AI model came from GPs and hospitals in Wales. As part of their next steps, the researchers are applying the model to datasets from hospitals in England to assess whether similar patterns emerge across different populations.
