AI may help reduce common drug side effects

A team of researchers has developed a tool which uses natural language processing, an Artificial Intelligence (AI) methodology, and chemical structure analysis to measure the harmful effects of medicines, according to the study.

The new tool is designed to calculate which medicines are more likely to experience adverse anticholinergic side effects, which impact the brain by blocking a key neurotransmitter called acetylcholine.

“Use of medicines with anticholinergic effects can have significant harmful effects for example falls and confusion, which are avoidable, we urgently need to reduce the harmful side effects as this can lead to hospitalisation and death,” said Chris Fox, Professor, University of Exeter, UK.

“This new tool provides a promising avenue towards a more tailored personalised medicine approach, of ensuring the right person gets a safe and effective treatment while avoiding unwanted anticholinergic effects,” he added.

Anti-cholinergic side effects can occur from over-the-counter drugs like bladder medications, antidepressants, medications for stomach and Parkinson’s disease in older people.

The side-effects include confusion, blurred vision, dizziness, falls and a decline in brain function. It may also increase risk of dementia when used long term.

The tool assesses anticholinergic burden by assigning a score based on reported adverse events and aligning closely with the chemical structure of the drug being considered for prescription, resulting in a more accurate and latest scoring system than any previous system, according to the research published in the journal Age and Ageing.

Further, the team surveyed 110 health professionals, including pharmacists and prescribing nurses.

Of this group, 85 per cent said they would use a tool to assess risk of anticholinergic side effects, if available. The team also gathered usability feedback to help improve the tool further.

“Our tool is the first to use innovative artificial intelligence technology in measures of anticholinergic burden, ultimately, once further research has been conducted the tool should support pharmacists and prescribing health professionals in finding the best treatment for patients”, said Dr Saber Sami at University of East Anglia.