Using machine learning to predict intestinal inflammation in relatives of people with Crohn’s

What this research looked at

Close family members of people with Crohn's have a greater risk of developing Crohn's themselves. This includes parents, brothers, and sisters. 

This research looked at ways to find those close family members who are at greatest risk of developing Crohn’s. This would mean they could be monitored and diagnosed earlier. Early diagnosis is important because it can allow early treatment. Early treatment with biologic medicines has better outcomes for people with Crohn’s. 

What the researchers found

The researchers collected data from 480 healthy people who had a close family members with Crohn's. They looked at their DNA to see if they had any known risk factors for developing Crohn's. 

They used a computer to look for patterns in the data, known as machine learning. 

Due to delays the researchers could not complete the clinical follow-up. They were not able to see if the patterns they found could predict who would develop Crohn's. But, the researchers plan to complete this in future studies. 

The data they collected is a valuable tool for future studies and model-testing. 

What the researchers think this could mean for people with Crohn’s and Colitis

The researchers hope to improve how we monitor people who have a close family members with Crohn’s.

The researchers will continue to develop this tool.  The tool could help doctors to identify people who may be at greater risk of develop Crohn's. This would allow closer monitoring of these people, earlier diagnosis and earlier treatment. 

Who is led this research: Dr Natalie Prescott, King's College London
Our funding: £99,754
Duration: 24 months
Official title of application: Using machine learning to predict intestinal inflammation in asymptomatic relatives of patients with Crohn’s Disease