AI Model Predicts Hospital Stay Lengths for Patients with Learning Disabilities

AI model predicts hospital stay lengths for people with learning disabilities | Newswise

A new artificial intelligence (AI) model has been developed to predict how long a person with a learning disability is likely to stay in hospital, offering valuable insights that could improve care and resource planning. Developed by computer scientists at Loughborough University as part of the 'DECODE' project, the model aims to tackle healthcare challenges faced by people with learning disabilities and multiple health conditions. This group has a life expectancy 20 years lower than the UK average, often due to poorer physical and mental health and a higher likelihood of having multiple chronic illnesses. These factors increase the risk of preventable complications, reduced quality of life, and prolonged hospital stays. How the AI model works The Loughborough University researchers used GP and hospital data from over 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. "The model generates predictions by assessing factors such as a patient's age, medication history, lifestyle, and existing health conditions", explains Professor Georgina Cosma, an expert in AI for healthcare at Loughborough University and DECODE co-investigator. "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 who would be discharged sooner. Hospitalisation trends The AI model was also used to analyse the hospital data to identify key reasons for hospitalisations and health patterns among people with learning disabilities and multiple health conditions. The top five primary conditions and top five common conditions treated or investigated during hospitalisations for (a) males and (b) females with learning disabilities and multiple long-term conditions. He said: "This research demonstrates how AI could help tackle these vast inequalities by spotting patterns and predicting resource needs, which could all improve patient outcomes. "However, prediction alone is not enough - we must ensure these insights drive real-world changes, reducing avoidable hospital admissions and ensuring people with learning disabilities receive timely, effective, and personalised support. "As the Government develops the 10 Year NHS Plan, they must prioritise using technology to address health inequalities and ensure the healthcare system meets the needs of people with a learning disability." Next steps The insights from this study and the wider DECODE project will be used to support the NHS in developing risk prediction algorithms to assist clinicians in decision-making. Dr Satheesh Gangadharan, Consultant Psychiatrist with the Leicestershire Partnership NHS Trust and the DECODE Co-Principal Investigator, said: "We are in the process of applying this knowledge into practice as well as sharing it widely. "While hospital care is an important part of healthcare provision, we are exploring ways to minimise the need for hospitalisation by exploring where health interventions could be delivered earlier and people with learning disabilities could be engaged in their care better." 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. 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." Read the full study The findings of the AI analysis and the development of the predictive model have been published in Frontiers in Digital Health. The paper also details techniques used to reduce bias in the AI model, ensuring fair and accurate predictions across ethnic groups. Lead author Emeka Abakasanga, a Computer Science Research Associate at Loughborough University, said: "We hope this paper and its findings contribute to fairer healthcare interventions in hospital admissions for diverse patient groups within the learning disability cohort." Additional information: DECODE

AI model predicts hospital stay lengths for people with learning disabilities

A new artificial intelligence (AI) model has been developed to predict how long a person with a learning disability is likely to stay in hospital, offering valuable insights that could improve care and resource planning. Developed by computer scientists at Loughborough University as part of the DECODE project, the model aims to tackle health care challenges faced by people with learning disabilities and multiple health conditions. The research is published in the journal Frontiers in Digital Health. This group has a life expectancy 20 years lower than the UK average, often due to poorer physical and mental health and a higher likelihood of having multiple chronic illnesses. These factors increase the risk of preventable complications, reduced quality of life, and prolonged hospital stays. How the AI model works The Loughborough University researchers used GP and hospital data from over 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. "The model generates predictions by assessing factors such as a patient's age, medication history, lifestyle, and existing health conditions," explains Professor Georgina Cosma, an expert in AI for health care at Loughborough University and DECODE co-investigator. "With early and accurate predictions, hospitals can plan better and provide more personalized 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 who would be discharged sooner. Hospitalization trends The AI model was also used to analyze the hospital data to identify key reasons for hospitalizations and health patterns among people with learning disabilities and multiple health conditions. It found: He said, "This research demonstrates how AI could help tackle these vast inequalities by spotting patterns and predicting resource needs, which could all improve patient outcomes. "However, prediction alone is not enough -- we must ensure these insights drive real-world changes, reducing avoidable hospital admissions and ensuring people with learning disabilities receive timely, effective, and personalized support. "As the Government develops the 10 Year NHS Plan, they must prioritize using technology to address health inequalities and ensure the health care system meets the needs of people with a learning disability." Next steps The insights from this study and the wider DECODE project will be used to support the NHS in developing risk prediction algorithms to assist clinicians in decision-making. Dr. Satheesh Gangadharan, Consultant Psychiatrist with the Leicestershire Partnership NHS Trust and the DECODE Co-Principal Investigator, said, "We are in the process of applying this knowledge into practice as well as sharing it widely. "While hospital care is an important part of health care provision, we are exploring ways to minimize the need for hospitalization by exploring where health interventions could be delivered earlier and people with learning disabilities could be engaged in their care better." 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. 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 personalized prediction tool can reduce emergency admissions and improve quality of life for patients with learning disabilities and multiple long-term conditions."

New AI tool could improve care planning for patients with learning disabilities

Loughborough UniversityFeb 25 2025 A new artificial intelligence (AI) model has been developed to predict how long a person with a learning disability is likely to stay in hospital, offering valuable insights that could improve care and resource planning. Developed by computer scientists at Loughborough University as part of the 'DECODE' project, the model aims to tackle healthcare challenges faced by people with learning disabilities and multiple health conditions. This group has a life expectancy 20 years lower than the UK average, often due to poorer physical and mental health and a higher likelihood of having multiple chronic illnesses. These factors increase the risk of preventable complications, reduced quality of life, and prolonged hospital stays. How the AI model works The Loughborough University researchers used GP and hospital data from over 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. "The model generates predictions by assessing factors such as a patient's age, medication history, lifestyle, and existing health conditions", explains Professor Georgina Cosma, an expert in AI for healthcare at Loughborough University and DECODE co-investigator. "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 who would be discharged sooner. Hospitalization trends The AI model was also used to analyse the hospital data to identify key reasons for hospitalisations and health patterns among people with learning disabilities and multiple health conditions. It found: Cancer is the leading cause of hospital admissions for men and women with learning disabilities and multiple health conditions, but other top reasons differ by gender Epilepsy is the most frequently treated condition during hospital stays for both men and women, but other top reasons differ by gender 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 Patients with stays of four or more days are more likely to: Be over 50 years old Live in more deprived areas Have obesity or are less physically active Have more health conditions, a history of long hospital stays, or previous treatment for long-term conditions. Importance of the research Jon Sparkes OBE, CEO of learning disability charity Mencap, has welcomed the findings. This research demonstrates how AI could help tackle these vast inequalities by spotting patterns and predicting resource needs, which could all improve patient outcomes. However, prediction alone is not enough - we must ensure these insights drive real-world changes, reducing avoidable hospital admissions and ensuring people with learning disabilities receive timely, effective, and personalized support. As the Government develops the 10 Year NHS Plan, they must prioritize using technology to address health inequalities and ensure the healthcare system meets the needs of people with a learning disability." Jon Sparkes OBE, CEO, Mencap Next steps The insights from this study and the wider DECODE project will be used to support the NHS in developing risk prediction algorithms to assist clinicians in decision-making. Dr Satheesh Gangadharan, Consultant Psychiatrist with the Leicestershire Partnership NHS Trust and the DECODE Co-Principal Investigator, said: "We are in the process of applying this knowledge into practice as well as sharing it widely. "While hospital care is an important part of healthcare provision, we are exploring ways to minimise the need for hospitalisation by exploring where health interventions could be delivered earlier and people with learning disabilities could be engaged in their care better." 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. 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 personalized prediction tool can reduce emergency admissions and improve quality of life for patients with learning disabilities and multiple long-term conditions." Read the full study The findings of the AI analysis and the development of the predictive model have been published in Frontiers in Digital Health. The paper also details techniques used to reduce bias in the AI model, ensuring fair and accurate predictions across ethnic groups. Lead author Emeka Abakasanga, a Computer Science Research Associate at Loughborough University, said: "We hope this paper and its findings contribute to fairer healthcare interventions in hospital admissions for diverse patient groups within the learning disability cohort." Loughborough University Journal reference: Abakasanga, E., et al. (2025) Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning. Frontiers in Digital Health. doi.org/10.3389/fdgth.2025.1538793.