LONDON — Personalized treatments for Parkinson’s disease may soon be a reality. Scientists have used artificial intelligence (AI) to identify different variations of the disease, taking a significant step toward targeted therapies for patients from all backgrounds.
The research team accurately classified four subtypes of Parkinson’s disease, with one classification reaching an impressive 95 percent accuracy. Researchers at the Francis Crick Institute and UCL Queen Square Institute of Neurology announced this breakthrough.
Parkinson’s disease is a neurodegenerative condition characterized by involuntary shaking of the body, slow movement, and stiff, inflexible muscles. It results from the misfolding of key proteins and dysfunction in the clearance of faulty mitochondria, which are vital for energy production within a cell.
Typically affecting those over the age of 50, there are currently approximately one million people living with Parkinson’s in the United States alone, with around 90,000 people receiving this diagnosis every year.
The study involved scientists working with the technology company Faculty AI, using machine learning to predict the subtypes of the disease. They accomplished this by analyzing images of patient-derived stem cells. Their results have been published in the journal Nature Machine Intelligence.
Before this research, there was no accurate way to differentiate the subtypes of Parkinson’s. Consequently, people often received nonspecific diagnoses and lacked access to targeted treatments, support, or care.
While the majority of Parkinson’s disease cases develop sporadically, some are linked to genetic mutations. In this study, the researchers created a human model of the brain disease “in a dish” by generating stem cells from patients’ cells. They then chemically induced four different subtypes of Parkinson’s disease and “trained” a computer program to recognize each subtype.
This innovative approach enabled the computer to predict the specific subtype of Parkinson’s when presented with previously unseen images. This research heralds a promising new era in the understanding and treatment of this complex and debilitating condition.
“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,” says Sonia Gandhi, the assistant research director and group leader of the Neurodegeneration Biology Laboratory at the Crick, in a media release.
“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,” Gandhi continues.
“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 personalized medicine.”
“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,” adds study author James Evans, a PhD student at the Crick and University College London.
“Using AI in this study enabled us to evaluate a larger number of cell features, and assess the importance of these features in discerning 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.”
The project was developed during the disruption to the lab’s research in the midst of the COVID-19 pandemic, during which the whole team undertook an intensive coding course, developing skills that they are now applying to current projects.
The 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 (i.e., without genetic mutations) can be classified in a similar way.
South West News Service writer Jim Leffman contributed to this report.