Pointers at Glance
- Research led by the University of Exeter and Kent and Medway NHS and Social Care Partnership Trust, published in Age and Aging, assessed a new tool designed to calculate which medicines are assumed to experience adverse anticholinergic effects on the body and brain.
- AI tools could assist clinicians in assessing which patients are believably encountering harmful drug side effects.
Anticholinergic drug side effects include dizziness, confusion, blurred vision, falls, and a decline in brain function. These effects may probably increase the risks of falls and may be associated with increased mortality. They have also been connected to a higher risk of dementia when used long-term.
Researchers have now developed an AI tool to calculate medicines’ harmful effects. The team created a new online tool, International Anticholinergic Cognitive Burden Tool (IACT), which uses natural language processing, an AI methodology, and chemical structure analysis to identify medications with anticholinergic drug side effects.
It is the first tool to incorporate a machine learning technique to develop an automatically updated tool available on a website portal. The anticholinergic burden is assessed by assigning a score based on reported adverse events and closely aligning with the drug’s chemical structure for a prescription. It results in a more accurate and up-to-date scoring system than any previous system.
Finally, after further research and modeling with real-world patient data, the AI tool developed could assist in prescribing and reducing risks from common medicines.
The team surveyed 110 health professionals that included pharmacists and prescribing nurses. Eighty-five percent of this group said they would use a tool to assess the risk of anticholinergic side effects, if available. The team also collected usability feedback to help improve the tool further.
The research team collaborates with AKFA University Medical School, Uzbekistan, and the Universities of East Anglia, Aston, Kent, and Aberdeen. They aim to continue the AI tool development with the goal that it can be deployed in day-to-day practice, which this study supports.