Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Assessing how comorbidities differ between patients with rare cardiometabolic conditions versus common cardiometabolic diseases, looking for sub-groups and how these groups were impacted by the pandemic.

An image of a plastic model of a heart.
Photo by Ali Hajiluyi on Unsplash

This project applies machine learning to patient histories, looking to identify groups of patients with rare conditions relating to or co-occurring with Cardiovascular Disease (CVD) or Diabetes. It will then examine the impact of the COVID-19 pandemic on these rare condition groups, as well as the distribution of these conditions across ethnicity groups.

Heart- and diabetes-related issues are the leading cause of death in the world. Alongside these common conditions, many patients have rare conditions related to or co-occurring with heart- or diabetes-related conditions. Because these conditions affect less than 1 in 2,000 people, patients with rare conditions are more likely to have unmet health and social needs, which would then have been confounded by the impacts of the COVID-19 pandemic. This study aims to examine these unmet needs and the impact of the COVID-19 pandemic, which will provide insight into the health inequalities experienced during the pandemic.

This work is part of the outputs of the CVD-COVID-UK / COVID-IMPACT Consortium (Project CCU069), a group from the British Heart Foundation Data Science Centre aiming to understand the connections between COVID-19 and cardiovascular diseases such as heart attacks, heart failure, stroke and blood clots in the lungs, using deidentified healthcare data.

Initially, our team are applying machine learning to explore whether there are any valuable ways to group the patients we found to have at least one of the over 200 rare conditions we included, which could be helpful to guide medical treatments or oversight. This is done through cluster analysis, where we apply machine learning technologies to the data, which try to find groups of patients with certain features in common.

Beyond this cluster analysis, we also aim to use the heart- and diabetes-related conditions patient information from this study to demonstrate the value of our Ethnicity, Health Equity and AI Project by looking at the distribution of different ethnicity groups across three categories – patients with rare CVD conditions, rare metabolic conditions and other rare conditions. Previously, other researchers in the consortium had identified some ethnicities were over-represented in these rare conditions, so we hoped to explore this in more depth using more detailed ethnicity categories and data.