AI for assessment of rheumatoid arthritis

Rheumatoid arthritis (RA) is a chronic inflammatory joint disorder that can lead to destruction of joints, reduced quality of life, and increased mortality. Currently, the classification of RA is done with a system called Disease Activity Score 28 – C-reactive Protein. Its score depends on several subjective variables. Recently, a method called OMERACT-EULAR Synovitis Score (OESS) has been adopted, which only uses ultrasound images for classification, and therefore has the potential to bring more objectivity to the treatment when coupled with the ARTHUR platform.

In ROPCA we have developed AI solutions for analyzing the ultrasound images that are captures by the ARTHUR platform. Our AI solutions are based on Convolutional Neural Networks, which are state-of-the-art algorithms for analysis of imaging data. With the help of expert rheumatologists we have acquired thousands of images and used them to train our networks to be able to recognize the degree of RA directly from the ultrasound images captured by ARTHUR.


Compared to expert rheumatologists, our Convolutional Neural Networks achieve an accuracy of 83.9%.


Our dedicated AI team is continuously working on improving our AI solutions to achieve even better performance and to increase transparency in the prediction pipeline. We work closely with the experts in this field to achieve this vision.