AI model aims to predict how medicines taste

decorative
decorative
decorative A team from the UCL Global Business School for Health (GBSH) and the UCL School of Pharmacy are using data collected from an "electric tongue" to create an AI model for predicting the bitterness of drugs. Taste is key to making sure people regularly take their medications and is an important part of drug development. For example, taste has been identified as the biggest barrier in compliance for children taking medicine, but taste is also an issue for adults, especially adults taking long-term medication, such as for HIV. A research team led by Dr Hend Abdelhakim (UCL Global Business School for Health) used an e-tongue (a device made of sensors responding to taste) to assign bitterness scores to medicines, and in turn estimate the aversiveness expected from the clinical dose planned. The e-tongue measures how much the bitter molecules stick on a plastic sensor that acts like the human tongue, and then it compares it with a clear sample. The difference between the two measurements represents a theoretical bitterness level of a medicine. Using an e-tongue means drugs can be tested more quickly and effectively compared to the alternative option of conducting a human trial, but now the team are collaborating with machine learning experts including Dr David Shorthouse (UCL School of Pharmacy) to speed up drug development further using an AI model.
account creation

TO READ THIS ARTICLE, CREATE YOUR ACCOUNT

And extend your reading, free of charge and with no commitment.



Your Benefits

  • Access to all content
  • Receive newsmails for news and jobs
  • Post ads

myScience