New machine learning model could help pinpoint stages of Parkinson’s

A new machine learning model aims to help clinicians understand how Parkinson’s progresses in an individual, in relation to the emergence of symptoms of the condition.

The model, designed by US technology company IBM in collaboration with US charity The Michael J Fox Foundation (MJFF), assesses how advanced an individual’s Parkinson’s is – and takes into consideration how medication may mask visible symptoms such as tremors. Researchers at IBM plan to train the model using data from people with Parkinson’s, collected by MJFF, to help define each stage of the condition.

Kristen Severson, a postdoctoral researcher at IBM Research said: “In the future, progression models such as ours may help support various clinical applications. For example, once the disease states are learned, clinicians could quantitatively group patients as well as better predict progression – which could potentially help to inform more personalised patient care and management, as well as more effective drug trials.”

Read more:

Can over-the-counter drugs reduce risk of developing genetic Parkinson’s?

US hospital initiative improves on-time administration of Parkinson’s medication