Prediction of drug-drug interactions (DDIs) in children

Lead Research Organisation: University College London
Department Name: Institute of Health Informatics

Abstract

To use Machine Learning and Artificial Intelligence to make better paediatric DDI predictions.

Project Motivations
Predicting and adjusting doses of drugs susceptible to Drug-Drug Interactions is usually attained in adult drug development by running healthy volunteer DDI studies. However, many DDI's are mediated via enzymes which show developmental differences throughout childhood, and no healthy child is ever enrolled in a DDI study. Hence, the prediction and mitigation of DDI's in children relies heavily on extrapolation from adults and mechanistic physiologically-based systems pharmacology modelling. Yet, extrapolations and mechanistic physiologically-based systems pharmacology models have their limitations and can result in poor paediatric DDI prediction accuracy. In this project, we aim to use ML and AI with both adult and paediatric DDI data to improve paediatric DDI predictions.

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S021612/1 01/04/2019 30/09/2027
2418828 Studentship EP/S021612/1 28/09/2020 30/09/2024 Victoria Smith