Scientists at IBM Research Big Blue, with the assistance of the Michael J. Fox Foundation, have made a discovery that will help clinical researchers better understand Parkinson’s disease.

The research arm of Big Blue and the Michael J. Fox Foundation (MJFF) has built an artificial intelligence model that can group common patterns of Parkinson’s disease symptoms. She is also able to accurately determine the progression of these symptoms in a patient, regardless of whether he is taking medications to neutralize them.

A report on this discovery was published on the pages of The Lancet Digital Health. IBM Research and MJFF have been collaborating since 2018. The goal of the project is to adapt machine learning technologies to help clinical researchers further understand the foundations of Parkinson’s disease, especially in the part where the disease progresses differently in different people.

To develop the AI ​​model, the researchers used unidentified datasets from the Parkinson’s Progression Markers Initiative (PPMI).

“The dataset served as input to a machine learning approach, revealing complex patterns of symptoms and progression,” says an IBM Research research paper. “While many previous studies have focused on characterizing Parkinson’s disease using only baseline information, our method relies on seven years of patient data. In addition, the model makes limited a priori assumptions about progression pathways compared to previous studies. ”

As a result, the researchers discovered that a patient’s condition can vary depending on a number of factors. Among these factors, there are features of activity in everyday life, problems with slowing down, limb tremors, instability in body positions, as well as symptoms that are not directly related to motor skills: depression, anxiety, cognitive impairment and sleep disturbances. In addition, AI has learned to predict the onset of a severe stage of Parkinson’s disease.

Clinical trials have shown that the model proposed by IBM Research provides fairly highly accurate predictions. In the future, other factors will be added to the original data, including genetic information and data from neuroimaging. As the authors of the study note, this will ultimately help to investigate the disease in even more detail.