The AI model was trained using seven years of patient data.

Researchers at IBM (NYSE: IBM) and the Michael J Fox Foundation for Parkinson’s Research have developed an AI model that helps predict the progression of Parkinson’s disease. The model groups typical symptom patterns of the disease and predicts the timing and severity of these symptoms. (MARKTECHPOST)

The researchers used de-identified data from the Parkinson’s Progression Markers Initiative (PPMI) as input for machine learning – up to seven years of longitudinal patient data, the most ever used in a Parkinson’s disease study. Longitudinal patient data refers to descriptions of a patient’s clinical status gathered over time.

This approach enabled the algorithm to assimilate complex symptom and progression patterns that it could use in its predictions.

“Hopefully, by using machine learning to learn from large amounts of patient data, clinicians and researchers could have a new tool to better predict the notoriously varying progression of symptoms in individual Parkinson’s patients,” authors Kristen Severson, Soumya Ghosh, and Jianying Hu sain in an IBM blog. “They can then better manage and treat the disease, as well as use the best candidates for more targeted and effective clinical trials.”

Parkinsons’s: New insights

Parkinsons disease progresses through diverse pathways and at any time, a patient’s state can vary in terms of movement, tremor, posture, as well as depression, anxiety, cognitive impairment and other disorders.

Despite these factors, the AI model could still make accurate predictions regarding the progression of the disease.

“Having learned the model using one dataset, it was able to successfully predict an advanced state of Parkinson’s disease associated with outcomes such as dementia and the inability to walk unassisted,” the researchers wrote.

Related Story:  AI May Provide An Objective Second Opinion On Parkinson’s

Image credit: Parkinson’s Foundation