Machine learning predicts arthritis severity in children

Researchers have developed a machine learning system that predicts the severity of arthritis in a pediatric population, allowing for treatment to be personalized. Findings of their research were published in PLOS Medicine.

In its most severe forms, arthritis in children can cause lifelong pain and disability; however, some children are not impacted by the disease for long. If physicians know which children will need mild treatment options, it could spare them from unwarranted treatment and potential medication side effects. 

The researchers, led by Rae Yeung, MD, PhD, professor of pediatrics, immunology and medical science at the University of Toronto and senior scientist and staff rheumatologist at The Hospital for Sick Children (SickKids), sought to develop a machine learning method that could predict disease severity in children.

"Knowing which children will benefit from which treatment at which time is really the cornerstone of personalized medicine and the question doctors and families want answered when children are first diagnosed,” Yeung said in a prepared statement. 

Yeung and colleagues specifically looked at the data of 640 patients with newly diagnosed arthritis who were part of the Research in Arthritis in Canadian Children, Emphasizing Outcomes (ReACCh-Out). Data was sourced from 2005 to 2010, and physical exams detailed the location of the painful joints in the body.

The algorithm was able to categorize patients into seven distinct groups, according to the areas of swelling or painful joints in the body—pelvic girdle, fingers, wrists, toes, ankles, knees and indistinct. The researchers found some patients matched multiple models. 

To determine whether their disease outcomes would differ, the researchers further stratified the 640 patients into three groups by degree of localization: localized, partially localized or extended, with the percentage of their active joint aligning with their assigned pattern. Patients who did not present localized patterns took longer to go into remission and their outcomes were worse.

"Identifying this group of children early will help us target the right treatments early and prevent unnecessary pain and disability from ongoing active disease," Yeung said.

Of note, there is no cure for arthritis. As the disease progresses, treatment becomes more aggressive and medications are more costly—starting from ibuprofen to steroids to biological agents to the most severe, which switch off parts of the immune system. Inhibiting the function of the immune system can cause side effects including an increased risk of infection.

“Now we understand the disease much better, we can group children into these different categories to predict response to treatment, how fast do they go into remission and whether or not we can tell they are in remission and remove therapy,” said co-researcher Quaid Morris, PhD, professor of computer science at the University of Toronto. 

""

As a senior news writer for TriMed, Subrata covers cardiology, clinical innovation and healthcare business. She has a master’s degree in communication management and 12 years of experience in journalism and public relations.

Around the web

With generative AI coming into its own, AI regulators must avoid relying too much on principles of risk management—and not enough on those of uncertainty management.

Cardiovascular devices are more likely to be in a Class I recall than any other device type. The FDA's approval process appears to be at least partially responsible, though the agency is working to make some serious changes. We spoke to a researcher who has been tracking these data for years to learn more. 

Updated compensation data includes good news for multiple subspecialties. The new report also examines private equity's impact on employment models and how much male cardiologists earn compared to females.

Trimed Popup
Trimed Popup