Michael J. Fox Foundation & IBM study effects of Parkinson's Disease
Parkinson's Disease is a neurological disease that is commonly associated with tremors and slow movement - particularly affecting the middle-aged and elderly, however, in many cases early-onset Parkinsons can present much earlier in life.
In New Zealand, approximately one in 100 people over the age of 60 are diagnosed with Parkinson's, according to Health Navigator.
Medical researchers and practitioners still have many questions about Parkinson's progression. Last year IBM Research and the Michael J. Fox Foundation announced a collaboration on a new effort to uncover more about the disease.
IBM Research's Kristen Severson explains in a blog that six million people worldwide live with Parkinson's, and that number is expected to double by 2040. As a result, there is an urgent need for research and a better understanding of the disease.
Together, IBM Research and the Michael J. Fox Foundation for Parkinson's Research are using technology to help medical researchers and clinicians understand more about how the disease progressions, with the help of modelling and a machine learning algorithm.
The process will include using time series and forecasting models. These, however, can be difficult to apply to Parkinson's as the underlying biology is not fully characterised, which means stages of the disease can be hard to track, Severson says.
Despite the lack of certainty, disease states are useful because they can summarise problems related to motor skills and other symptoms. These can be leveraged for progression modelling.
“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,” says Severson.
The research will focus on helping researchers to learn disease states and model medication effects. A hidden Markov model will be the framework for the approach and will use variational inference to learn the personalised effects.
“After learning the model, insights can be derived both from interpreting the parameters of the model to learn more about the disease, as well as analysing predictions for a particular cohort of patients,” says Severson.
“Developing the tools for analysis is only the first step in the collaboration with The Michael J. Fox Foundation. Our next results will focus on the clinical insights we have derived by applying these models to the extensive amounts of data collected by The Michael J. Fox Foundation's landmark clinical study, the Parkinson's Progression Markers Initiative,” Severson states.
“Although the work was motivated by PD, we hope it might be useful or inspire similar work and exploration in other chronic conditions such as diabetes, Alzheimer's disease, and ALS.