New AI diagnostic technique could diagnose osteoarthritis three years before symptoms – paving the way for preventative therapies.
One of the worst things about getting older can be having to stop doing the things you always loved as a result of health conditions. Millions of people across the world are affected by osteoarthritis, for example, which can make it difficult to carry out everyday activities .
Longevity.Technology: Occurring when the protective cartilage that cushions the ends of the bones wears down, osteoarthritis is the most common type of arthritis. The risk of osteoarthritis increases with age, and is more common in women than in men.
At the moment, the major problem with diagnosis of this painful condition is that by the time symptoms appear and are spotted via X-ray, the damage has already been done. There’s no cure for osteoarthritis, but it can be managed with exercise, weight loss, supportive devices, medications and, potentially, surgery if other options aren’t working.
Now, however, a new diagnostic technique could give hope to future osteoarthritis sufferers.  Researchers from across The Johns Hopkins Hospital in the US and in Denmark have developed a technique, using artificial intelligence (AI), which is able to determine whether an individual will develop osteoarthritis up to three years before cartilage starts to wear away.
The team, made up of experts from hospitals and universities in Pittsburgh, Baltimore, Charlottesville and Copenhagen, examined 86 healthy individuals who were showing no signs or symptoms of osteoarthritis. Using AI to search for significant patterns in MRI scan images, the study was able to predict osteoarthritis with a 78% accuracy, three years before the onset of symptoms.
While further research is needed, with a larger sample size, it is now hoped that earlier diagnosis of osteoarthritis could lead to prevention, or delay, of the condition for millions of people worldwide.
“… couple pre-symptomatic OA detection with emergent clinical therapies could modify the outcome of a disease that costs the United States healthcare system $16.5 billion annually.”
“The problem is,” said co-author Kenneth Urish, associate professor of orthopedic surgery at Pittsburgh School of Medicine and associate medical director of the bone and joint center at the UPMC Magee-Womens Hospital, “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.”
It could be that those who are most at risk of osteoarthritis – for example, those who have a family member with the condition or who are women in an older age group – could, in future, be invited for screening programmes to check for likely onset of osteoarthritis.
Spotting it before it starts to damage the joints could be key to the development of future therapies, including medical treatment or lifestyle changes, that may even prevent the disease from taking hold. In future, the AI method could even be adapted for early diagnosis of other conditions which have a great impact on an older population.
One possibility could be that this latest diagnostic tool could be combined with preventative therapies. One such potential future treatment has been created by a team at Stanford who have developed a technique to boost cartilage before a problem develops.
Some trials have proven disappointing, however, such as that of senolytic therapy developer UNITY Biotechnology, which recently announced trials of a pain reliever for patients with osteoarthritis of the knee showed no statistically significant difference in pain reduction between their therapy and a placebo.
However, clinical therapies that do prove promising could be coupled with the new imaging technique.
“In the future,” said the US-Danish research team, “couple pre-symptomatic OA detection with emergent clinical therapies could modify the outcome of a disease that costs the United States healthcare system $16.5 billion annually. Furthermore, our technique is broadly applicable to earlier image-based detection of many diseases currently diagnosed at advanced stages today.”