Subtypes of Parkinson’s disease have been identified, paving the way for more targeted and personalised treatments.
Researchers at Weill Cornell Medicine used machine learning to define three subtypes of the disease based on the pace at which the disease progressed.
Professor Fei Wang said the subtypes had distinctive driver genes, which meant they could be used to create targeted treatment responses.
“In addition to having the potential to become an important diagnostic and prognostic tool, these subtypes are marked by distinct driver genes. These markers could also suggest ways the subtypes can be targeted with new and existing drugs,” Professor Wang said.
He said Parkinson’s disease was highly heterogeneous, “which means that people with the same disease can have very different symptoms”.
“This indicates there is not likely to be a one-size-fits-all approach to treating it. We may need to consider customized treatment strategies based on a patient’s disease subtype.”
Professor Wang said the researchers defined the subtypes based on their distinct patterns of disease progression and were able to identify them by using deep learning-based approaches to analyze deidentified clinical records from two large databases.
