Artificial Intelligence can Predict Osteoarthritis

Machine-learning algorithm that can detect subtle signs of osteoarthritis years before symptoms begin has been designed by researchers.

The results are published in PNAS.The gold standard for detecting arthritic is x-ray. However, by the time arthritis is detected, the damage has been done.

‘AI can be trained to detect subtle signs of osteoarthritis from MRI images. This technology can be used to prevent osteoarthritis before the disease worsens.’

People can be treated with preventive drugs rather than undergoing joint replacement surgery by using this predictive approach.

The primary treatment for osteoarthritis is joint replacement. Osteoarthritis is so common that knee replacement is the most common surgery in the U.S. for people above 45 years.

The researchers observed MRIs from thousands of people for 7 years to understand how osteoarthritis of the knee develops.

The study was focused on a subset of patients who had little evidence of cartilage damage at the start of the study.

Subtle patterns on the MRI not visible to the naked eye can be detected by the computer to predict their future risk of osteoarthritis.

A model was trained on a subset of knee MRI data and tested on patients it had never seen before. The process was repeated dozens of times.

The algorithm predicted osteoarthritis with 78% accuracy from MRIs performed three years before symptom onset.

There are no drugs currently that can prevent pre-symptomatic osteoarthritis. However, there are a few highly effective drugs that can prevent patients from developing a related condition called rheumatoid arthritis.

The goal is to develop the same types of drugs for osteoarthritis. Many candidates already are in the preclinical phase.

"Instead of recruiting 10,000 people and following them for 10 years, we can just enroll 50 people whom we know are going to be getting osteoarthritis in two or five years," Urish said. "Then we can give them the experimental drug and see whether it stops the disease from developing."



Source: Medindia