Machine learning predicts subtypes of Parkinson’s disease

Carried out in collaboration between the Francis Crick Institute, UCL Queen Square Institute of Neurology and Faculty AI, the team’s research has shown that computer models can classify four subtypes of Parkinson’s disease, with one reaching an accuracy of 95 per cent and showing potential for personalised therapy. Their work is detailed in Nature Machine Intelligence.

Parkinson’s disease is a neurodegenerative condition impacting movement and cognition. Symptoms and disease progression vary from person to person due to differences in the underlying mechanisms causing the disease. 

Until now there hasn’t been a way to accurately differentiate subtypes, which means people are given nonspecific diagnoses and do not always have access to targeted treatments, support or care.

Parkinson’s disease involves misfolding of key proteins and dysfunction in the clearance of faulty mitochondria, the source of energy production in the cell. Most cases of Parkinson’s disease start sporadically, but some can be linked to genetic mutations.

According to the Francis Crick Institute, the researchers generated stem cells from patients’ own cells and chemically created four different subtypes of Parkinson’s disease, two involving pathways leading to toxic build-up of α-synuclein and two involving pathways leading to defunct mitochondria, to create a ‘human model of brain disease in a dish’.

MORE FROM ARTIFICIAL INTELLIGENCE

They then imaged the disease models in microscopic detail and labelled key cell components including lysosomes, which are involved in breaking down worn-out parts of the cell. The researchers ‘trained’ a computer program to recognise each subtype, which was then able to predict the subtype when presented with images it had not seen before.

The mitochondria and lysosomes were the most important features in predicting the correct subtype – confirming their involvement in how Parkinson’s disease develops – but other areas of the cell like the nucleus were also found to be important, as well as aspects of the images that cannot be explained yet.

In a statement, Sonia Gandhi, assistant research director and group leader of the Neurodegeneration Biology Laboratory at the Crick, said, “We understand many of the processes that are causing Parkinson’s in people’s brains. But, while they are alive, we have no way of knowing which mechanism is happening, and therefore can’t give precise treatments.

“We don’t currently have treatments which make a huge difference in the progression of Parkinson’s disease. Using a model of the patient’s own neurons, and combining this with large numbers of images, we generated an algorithm to classify certain subtypes - a powerful approach that could open the door to identifying disease subtypes in life. Taking this one step further, our platform would allow us to first test drugs in stem cell models, and predict whether a patient’s brain cells would be likely to respond to a drug, before enrolling into clinical trials. The hope is that one day this could lead to fundamental changes in how we deliver personalised medicine.”

Next steps for the research team are to understand disease subtypes in people with other genetic mutations, and to work out whether sporadic cases of Parkinson’s disease can be classified in a similar way.