A study has been published in the journal PLOS Medicine by the researchers of the University of Toronto on February 26th, 2019.
This research describes a computational approach that could accurately predict the severity of disease in patients of arthritis to help the doctors in giving them better treatments.
The research is based on machine learning which is a form of artificial intelligence. It lays down the method to identify continuous patterns from the set of data of the disease. During the study, this approach classified the patients into seven different groups based on the patterns of painful joints in their bodies.
Moreover, this approach accurately predicted which children will go into remission faster and which one will develop a more severe form of the disease.
After having knowledge of such algorithm, patients will have to experience milder forms of the disease. This could eventually lead to spare them from other treatments and side effects of its medicines. This machine learning tool is developed by Quaid Morris, Dr. Rae Yeung, and recently-graduated Simon Eng.
Prof. Quaid Morris, a professor of Computer Science at the University of Toronto said, "The final stage of treatment is very effective in some children, but also very expensive, and it's not clear what the long-term effects are."
Prof. Morris added, "When you are inhibiting the function of the immune system, this type of treatment can be associated with potential side-effects including increased risk of infection and others.”
Dr. Rae Yeung, a professor of Paediatrics, Immunology and Medical Science at the University of Toronto said, "Identifying this group of children early will help us target the right treatments early and prevent unnecessary pain and disability from the ongoing active disease."
Arthritis is a severe inflammation in the joints that causes pain. It not only affects the old age people but children can be affected by this disease too. It can even cause lifelong severe pain and disability in children.
The researchers are still unaware of its starting points but the disease takes place when the immune system starts attacking the lining of the joints leading to swelling and pain. This disease has no cure and its treatment invites expensive medications.
During the research, the children who developed arthritis were examined who were not been treated with medications yet. The clinical data from 640 children were analyzed. All the participants received the proper physical examinations including documenting the painful joints in the body.
This collected information exposed seven major patterns of the activity of joints in the pelvic area, toes, knees, fingers, wrists, and ankles. Many participants showed active joints in this analysis.
The study makes it evident that better reports of joint involvement are needed that could predict the course of the disease and its severity.
One of the researchers of the study had said that machine learning was used to detect seven patterns of this disease initially. It was then observed that many patients did not fall in any of the found patterns and those were found with the wicked version of the disease.
Now it has been stated that we can examine this disease better after grouping the children differently into the patterns to find their response to the given treatments.