Scientists have developed an artificial intelligence (AI) tool that can classify four subtypes of Parkinson’s disease with up to 95% accuracy.

Researchers from the Francis Crick Institute and the UCL Queen Square Institute of Neurology in London “trained” a computer program to recognise the subtypes of the condition using images of stem cells from patients.

The team said their work, published in the journal Nature Machine Intelligence, could pave the way for personalised medicine and targeted drug discovery.

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.”

Parkinson’s is a condition in which parts of the brain become progressively damaged over many years.

Symptoms include involuntary shaking of particular parts of the body, slow movement, and stiff and inflexible muscles.

But there is also a wide range of other physical and psychological symptoms such as depression and anxiety, problems sleeping, and memory problems.

These vary from person to person due to differences in the underlying mechanisms causing the disease.

The researchers said that until now, there was no way to accurately differentiate Parkinson’s subtypes.

It means people are given nonspecific diagnoses and do not always have access to targeted treatments, support or care, the team added.

For the study, the researchers generated stem cells, which have the ability to develop into specialised cell types in the body, from patients’ own cells.

The team then used those cells to chemically create four different subtypes of Parkinson’s: two involving pathways leading to toxic build-up of a protein called alpha-synuclein and two involving pathways associated with dysfunctional mitochondria, the cell’s battery packs.

Working with the British technology company Faculty AI, the team developed machine-learning algorithms which were able to accurately predict the Parkinson’s subtype when presented with images it had not seen before.

James Evans, a PhD student at the Crick and UCL, and first co-author of the study, said: “Now that we use more advanced image techniques, we generate vast quantities of data, much of which is discarded when we manually select a few features of interest.

“Using AI in this study enabled us to evaluate a larger number of cell features, and assess the importance of these features in discerning (the) disease subtype.

“Using deep learning, we were able to extract much more information from our images than with conventional image analysis.

“We now hope to expand this approach to understand how these cellular mechanisms contribute to other subtypes of Parkinson’s.”