Approved research

Assessing novel risk factors using multimodal data to enable the prediction of developing Parkinson's disease

Lay summary

Parkinson's disease is a brain disease that results in people developing difficulties with movement such as difficulties walking, making fine movements with their fingers and also developing problems such as stiffness and tremor. Some people with Parkinson's can also develop problems with their memory or hallucinations. Parkinson's develops when brain cells in a very small and specific part of the brain involved in movement unfortunately degenerate and die, this area is called the 'substantia nigra'. We currently don't have any treatments that slow down the progression of Parkinson's which will continue to deteriorate over years.

One problem with developing new treatments for Parkinson's is that by the time people have developed the movement related symptoms of Parkinson's they will frequently have actually had symptoms for years. In fact, the processes that ultimately lead to the development of Parkinson's may begin decades before the development of symptoms. When people do develop the movement symptoms of Parkinson's they have already lost a significant proportion (roughly 50%) of the brain cells in the substantia nigra. Therefore, to enable effective treatment of Parkinson's we need to be able to identify people in the earliest stages of the disease to then target with any potential treatments that may slow down the progression of the disease.

We have identified a naturally occurring bile acid (ursodeoxycholic acid) as a promising treatment for slowing down the progression of Parkinson's. We now want to investigate if other medical conditions or environmental factors that affect the bile acids in the body may affect the risk of developing Parkinson's. After identifying any relevant new risk factors that affect the bile acid composition within an individual, we will then use a machine learning method (sometimes referred to or used interchangeably with artificial intelligence) to develop a predictive model that can look to identify individuals at high risk of being in the early stages of Parkinson's before the development of the movement symptoms.

We would envisage this project taking between 12 and 36 months to complete. Identifying new risk factors implicated in the development of Parkinson's may help guide the investigation and development of new treatments for Parkinson's. A predictive model of Parkinson's could also be utilised in identifying people who may best be targeted in future clinical trials of new drugs.