Robots in Rheumatoid Arthritis treatment

Rheumatoid arthritis (RA) is a chronic inflammatory disease affecting around 1% of the world’s population. The disease causes swelling and pain in the joints, and if left untreated, it can cause stiffness, joint destruction, and disabilities. RA can lead to reduced quality of life and diminished work capacity.
 
RA has become more widespread among the elderly, and with the worldwide population increasingly aging, RA is soon going to present a larger problem for a health care system with an already severe shortage of rheumatologists and no prospects of increasing hospital budgets.
Early detection, followed by monitoring, plays a key role in managing and treating the disease. Ultrasound examination of joints has proven to be a sensitive imaging tool for detecting signs of early disease and evaluate arthritis activity in established disease. Unfortunately, ultrasound examinations have a long waiting list that delays the patients’ treatments.
 
RoPCA’s ultrasound platform ARTHUR and the artificial intelligence DIANA present a solution, both to the increasing number of RA patients, the hospital cost, and the lack of specialists.

ARTHUR

ARTHUR is the automated ultrasound platform for scanning rheumatoid arthritis patients. The platform automatically captures ultrasound images of fingers and wrist joints and evaluates the image quality using deep learning. The images are then evaluated for disease activity by DIANA, which sends the images with signs of disease onward for a rheumatologist to assess.
Conventional ultrasound examinations are dependent on manual labor and ultrasound diagnostics are time-consuming for doctors and therefore represent a high cost for hospitals. Patients can as a result look forward to a long waiting list. ARTHUR can free up the doctor’s time because it isn’t operator dependent and it interacts directly with the patient, without the need for a doctor.
 
The long waiting list for patients under investigation for RA or with an established case of RA means there is a risk of missing early disease, and for the patients with confirmed RA, too much time passes between the disease control checkups. When ARTHUR takes care of scanning the patients, the doctors can better prioritize which patients to see first, and thereby reduce the waiting time.
 
RA drugs are increasingly being used, and extremely expensive, frequent monitoring is consequently needed to adjust the treatments. ARTHUR’s patient monitoring ensures that ineffective treatment gets replaced fast or that the treatment gets reduced if the patient is in remission.
 
Ultrasound suffers from a central problem. The quality of the ultrasound scanning is operator dependent and difficult to repeat, which causes variability in the scanning results. This irregularity can influence the monitoring of the disease progression. The ARTHUR platform is capable of automatic ultrasound scanning that ensures a systematic and uniform method to perform ultrasound scans every time.

DIANA

ROPCA have developed AI solutions for analyzing the ultrasound images that are captured 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 for training our networks to be able to recognize the degree of RA directly from the ultrasound images captured by ARTHUR.
 
Our dedicated AI team is continuously working on improving our AI solutions to optimize performance and to increase transparency in the prediction pipeline. We work closely with the experts in this field to achieve this vision.
AI segmentering
* Areas marked by AI

Do you want to know more?