AIMS
This project aims to understand how diseases and drug treatments interact over time to worsen or improve a patients’ health. It will look at how to predict the next disease that patients might develop and find drugs that help when people have multiple conditions.
This project is an OPTIMAL (OPTIMising therapies, disease trajectories and AI assisted clinical management for patients Living with complex multimorbidity) study.
BACKGROUND
For individuals managing multiple long-term health conditions, the task of managing numerous medications can be burdensome. This is often exacerbated by treatment guidelines that focus on single diseases rather than considering the complexities of multiple conditions.
Patients with multiple health issues can be categorised into specific groups based on the combination of their illnesses. However, the current approach typically involves treating each condition in isolation. As a result, different medications are often prescribed for each condition, which may not effectively address the overall health needs of individuals coping with multiple long-term health problems. Furthermore, there is a lack of information regarding how one medication may interact with another condition, leading to uncertainty regarding the most appropriate treatment regimen.
Artificial intelligence (AI) offers promising solutions to this challenge. AI refers to computer systems capable of performing tasks that traditionally require human intelligence. By employing AI methods, healthcare professionals can access valuable insights that can enhance the care of patients with multiple health conditions. These technologies provide doctors and patients with crucial information to optimise treatment strategies and improve overall health outcomes.
RESEARCH
The research team aims to understand how different health issues develop over time, especially when they occur together in clusters. They want to explore how mental and physical health problems interact and how things like patient characteristics and the medicines they’re prescribed affect the progression of these conditions.
Using large sets of data from patients who visit GPs and hospitals, they’ll create models using AI to track how different combinations of diseases occur over time. Combining this with information about how these diseases have been treated will give them insights into which drugs might be worsening or preventing disease. They hope these models will also help us predict which patients being treated for common conditions might be at risk of developing another disease in the future.
PATIENT INVOLVEMENT
From the beginning, the researchers have involved patients in their study. They have recruited a patient/public advisory group of people with multiple long term health conditions and their carers. This group are working with the researchers throughout the project.
One of the members of the public advisory team is a patient and public involvement co-applicant and has contributed to various parts of this project including the lay summary of this research. The public advisory team will provide input to the: 1) interpreting our research findings from the perspective of patients with multiple long-term health conditions, 2) advising how to communicate our research to wider audiences, 3) advising how information on clustering should be communicated to patients, 4) identification of future research.
APPROVAL
This project was supported unanimously by the PIONEER Data Trust Committee.
This work is led by Dr Thomas Jackson, Consultant Geriatrician at University Hospitals Birmingham NHS Foundation Trust.
