A Machine-Learning Algorithm Can Detect Osteoarthritis Before it Develops

Published on September 25, 2020
Image Credit: [Pixabay/Naturwohl-Gesundheit]

A machine-learning has been able to accurately predict the onset of osteoarthritis from looking at MRI that were taken years before symptoms begin. According to a study published Tuesday in PNAS (Proceedings of the National Academy of Sciences of the United States of America).

The program was created by researchers at Carnegie Mellon University College of Medicine and University of Pittsburgh School of Medicine and in Pittsburgh. The team figured that machine learning could be used to visualize sensitive cartilage phenotypes that are signs of of a future osteoporosis progression.

The study authors wrote, ‘Our approach combines optimal mass transport theory with statistical pattern recognition’. For the study, the team reviewed knee MRIs from individuals who had been enrolled in the National Institutes of Health Osteoarthritis Initiative which is a multicenter, prospective observational study of osteoarthritis of the knee They focused on a subset around of 86 patients who had had little or no evidence of damage to the cartilage at the beginning of the study.

In the study, the research team reviewed many knee MRIs from those who had been enrolled in the National Institutes of Health Osteoarthritis Initiative. They focused on 86 individuals that had almost no little or no evidence of damage to their knee-cartilage.

The algorithm was able to correctly predict osteoarthritis in 78% of cases examined in the study. This level of accuracy was achieved using MRIs that were performed three years prior to the onset of symptoms. It was able to detect signs of the disease that are far too subtle for radiologists to notice.

There aren’t currently any drugs on the market that can prevent presymptomatic osteoarthritis from developing into its full-blown counterpart, joint deterioration. There are, however, drugs that do help prevent people from contracting a related condition, rheumatoid arthritis.

In a news release, the researchers say that their goal, currently, is to more develop the same types of drugs for osteoarthritis, which would reduce the need for more invasive osteoarthritis treatments.

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. Then we can give them the experimental drug and see whether it stops the disease from developing.

Kenneth Urish, MD, Ph.D., associate medical director of the bone and joint center at the University of Pittsburgh Medical Center (UPMC) Magee-Women’s Hospital.
Enjoyed this video?
"No Thanks. Please Close This Box!"