Machine learning may help predict risk of freezing of gait in Parkinson’s disease

Difficulty taking steps forward, often referred to as the freezing of gait (FOG), is a common symptom experienced by people with Parkinson’s and one that can be difficult to predict.

China-based researchers suggest that machine learning – artificial intelligence (AI) that uses algorithms to analyse data – could help predict the risk of freezing of gait developing in the early stages of the condition.

Their study, published in ‘npj Parkinson’s Disease’, gave laboratory and clinical data to a machine learning model brain. This information was collected from 158 adults with untreated early-stage Parkinson’s and 73 healthy adults over a five-year period.

They found that the risk of FOG could be predicted with an accuracy rate of up to 78%. The study authors suggested that machine learning methods “have the potential to help predict future FOG in patients with early Parkinson’s at an individual level”.

Read more:

Long-term exposure to air pollution could impact Parkinson’s disease mortality risk

Could living near nature help to slow Parkinson’s disease progression?