Researchers at the UK Dementia Research Institute in Edinburgh are using artificial intelligence to accelerate the search for treatments targeting neurological conditions including motor neurone disease.
Scientists analyse patient data, including voice recordings and eye scans, alongside lab-grown brain cells, to determine whether existing approved drugs could be repurposed for neurological conditions.
The team believes AI-powered pattern recognition could identify effective treatments in years rather than decades, a significant reduction on traditional drug discovery timelines.
Trial participant Steven Barrett, diagnosed with MND ten years ago, describes the research as a bright light of hope for himself and others living with the condition.
Barrett had been preparing for retirement after a decorated career in the civil service when he began noticing numbness in his leg, which eventually led to his MND diagnosis.
MND is a degenerative neurological condition with no current cure. Barrett describes its impact plainly: “MND is a horrible disease, it strips you of who you are.”
He added: “It rips any sense of future that you may feel that you had planned for yourself, all that goes.”
Barrett participates in the MND-SMART trial, which tests several drugs simultaneously rather than dividing participants into treatment and placebo groups in the conventional manner.
“For me the research is much more than taking a tablet, it’s taking a tablet with the intention of delivering outcomes, that may or may not help me but help others,” Barrett said.
The Institute is building a database of patients with Parkinson’s, dementia and MND, collecting iris scans, voice recordings and blood samples to cultivate stem cells into neurones for testing.
Machine learning algorithms, trained to identify drugs capable of converting a neurological disease signature into a healthy one, then assess existing compounds against multiple batches of those lab-grown neurones.
Approximately 1,500 drugs have already been developed and approved to treat other conditions, and Institute chief executive Professor Siddarthan Chandran says any one of them could potentially benefit the brain.
“The brain is the most complicated organ in the body, so we’ve got to contend with the paradox of that complexity,” Chandran told reporters, noting that recent technological advances have transformed research capabilities.
“A combination of AI and new technologies mean we can now do things which would have been unbelievable when I was at medical school,” Chandran added.
Because candidate drugs already carry regulatory approval, repurposing them can prove more straightforward than developing entirely new compounds, which can take more than ten years to reach market.
Similar AI-driven research has emerged elsewhere. Scientists at the Massachusetts Institute of Technology used generative AI to identify novel antibiotic compounds targeting superbugs and conditions including Parkinson’s disease.
In 2024, researchers at Harvard University developed a neural network model called TxGNN to identify existing drugs that could treat rare conditions, reflecting broader momentum in the field.
The wider research landscape has faced challenges, however. A recent review of Alzheimer’s drugs lecanemab and donanemab, examining 17 studies involving 20,342 volunteers, found their effect on disease progression was not significant enough to produce a meaningful difference for patients.
That conclusion drew criticism from other scientists in the field. Despite the setback, Chandran remains confident, stating that neurological research has reached a tipping point of change.