Currently, osteoarthritis is detectable only after the disease has already taken hold.

Osteoarthritis, the painful and incurable joint disease that afflicts over 3 million Americans, may soon be detected much earlier thanks to artificial intelligence (AI). (UPMC)

Researchers at the University of Pittsburgh Medical Center (UPMC) and Carnegie Mellon University have harnessed AI to detect osteoarthritis years before symptoms even start to appear.

The upshot of this is that patients can take medication rather than being faced with painful and expensive joint replacement surgery. In fact, knee replacement is the most common surgery in the U.S. for people over 45 years of age.

Diagnosing osteoarthritis

“The gold standard for diagnosing arthritis is x-ray. As the cartilage deteriorates, the space between the bones decreases,” said study co-author Kenneth Urish, M.D., Ph.D., associate professor of orthopedic surgery at Pitt and associate medical director of the bone and joint center at UPMC Magee-Women’s Hospital in a statement. “The problem is, when you see arthritis on x-rays, the damage has already been done. It’s much easier to prevent cartilage from falling apart than trying to get it to grow again.”

However, AI can detect signals of the disease in MRIs that are not visible using traditional methods.

Machine learning

The researchers referred to knee MRIs from the Osteoarthritis Initiative. This organization had studied thousands of people over seven years to map the development of knee osteoarthritis.

Shinjini Kundu, M.D., Ph.D., and lead author of the study, trained a machine learning algorithm on images from the knee MRI data. She then used the algorithm on new patients to test its predictive capabilities.

The researchers found that the algorithm predicted osteoarthritis with 78% accuracy from MRIs performed three years before the commencement of symptoms.

Use in drug development for osteoarthritis

No drugs currently prevent osteoarthritis from developing to a point when joints need to be replaced. Several drugs are currently in the preclinical stage of development, though.

Meanwhile, the AI method allows for real-time testing of drugs as the disease progresses. “Instead of recruiting 10,000 people and following them for 10 years, we can just enroll 50 people who we know are going to be getting osteoarthritis in two or five years,” says Urish. “Then we can give them the experimental drug and see whether it stops the disease from developing.”

Related Story:   AI Could Improve Hearing For Millions of Americans