Predicting responses to arthritis treatments using machine learning

Biological therapies can slow down the progression of rheumatoid arthritis. There are multiple drugs available – which one works best depends upon the patient’s genetics. 

There is currently no clinical diagnostic test to predict which drug will work best for which patient – which means many must endure multiple rounds of treatment as doctors attempt to find the right therapy. 

Queen Mary’s Professor Costantino Pitzalis has invented a way to predict patient response to three rheumatoid arthritis drugs. This means doctors can minimise the risk of trying ineffective treatments, thereby saving time and reducing discomfort.

The method uses deep molecular phenotyping and machine learning on a small biopsy taken from the patient’s joints.

We are looking for a partner to help develop this test further.