AI may speed up search for drugs to treat brain conditions

Scientists at the UK Dementia Research Institute in Edinburgh are using artificial intelligence to accelerate the search for neurological treatments by identifying whether existing drugs can be repurposed. By using algorithms to analyze patient data—including voice recordings, eye scans, and lab-grown brain cells—researchers aim to detect disease patterns and predict suitable medicines for conditions such as motor neurone disease (MND).

Researchers hope this technology will allow them to find effective treatments in years rather than decades. This effort is supported by trial participants like Steven Barrett, a former civil servant from Alloa, Scotland, who was diagnosed with MND 10 years ago. Barrett is participating in MND-SMART, a clinical trial that tests multiple drugs simultaneously against a control group, rather than testing a single drug against a placebo.

"MND is a horrible disease, it strips you of who you are," Barrett told the BBC. "It rips any sense of future that you may feel that you had planned for yourself - all that goes." Commenting on his participation in the trial, he added, "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."

To power these trials, the institute is building a database of individuals with Parkinson's, Dementia, and MND. Clinicians collect iris scans and voice recordings, using AI to analyze the data for early indicators of future neurological issues. They also collect blood samples from volunteers to cultivate stem cells into groups of brain cells called neurones.

Existing drugs are tested on these neurones using a combination of robotics, traditional laboratory equipment, and machine learning algorithms. These algorithms are trained to identify which of the approximately 1,500 approved drugs could convert a diseased neurological signature into a healthy one. Drugs identified by the AI can then proceed directly into clinical trials.

Institute chief executive Prof Siddarthan Chandran explained that redeploying approved drugs is more straightforward and faster than developing new formulas from scratch, which can take more than 10 years. "The brain is the most complicated organ in the body, so we've got to contend with the paradox of that complexity," Chandran told the BBC, noting that new technologies now allow researchers to perform work that was previously impossible.

This research aligns with other global efforts using AI to analyze medical data. Scientists at the Massachusetts Institute of Technology in the United States have used generative AI to identify novel antibiotic compounds for superbugs like gonorrhoea, as well as treatments for Parkinson's. Additionally, in 2024, Harvard University researchers developed a neural network model called TxGNN to identify existing drugs that could treat rare conditions.

The AI-driven search for treatments comes amid ongoing discussion over traditional drug development. A recent review of 17 studies involving 20,342 volunteers analyzed the Alzheimer's drugs lecanemab and donanemab, which remove amyloid protein from the brain. The review concluded that while the drugs slowed disease progression, the effect was not significant enough to make a meaningful difference to patients, a finding that drew backlash from other scientists. Despite these debates, Professor Chandran stated he remains confident that neurological research is "at the tipping point of change."