Establishing Artificial Intelligence for Medicines Optimisation (AIMS)

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

Abstract

AIMS will help to avoid patient morbidity associated with polypharmacy. For the patient, problematic polypharmacy can lead to an increased risk of adverse drug reactions (ADRs), adverse drug interactions (ADIs), and non-evidence based prescribing. For society, problematic polypharmacy leads to increased costs through hospitalisation from ADRs, increased risk of medication errors and significant contribution towards the £18 billion annual budget for medications in the UK.

The overall aim of this project is to develop a clinical decision support (CDS) tool that uses computational argumentation to reconcile disparate information types including national prescribing guidelines, medication side-effect profiles, patient symptoms and reported ADRs. The CDS tool would be deployed in the primary care setting to avoid the cost of expensive 'deprescribing clinics' in secondary care and support structured medication reviews that take place in GP practices.

In the early stages of the project, we will focus on using EHR datasets such as THIN to explore patterns of prescribing. Once these patterns have been established and modelled, we will then proceed to assess whether computational argumentation can be used to replicate face-to-face polypharmacy consultations. Argumentation is an emerging field that formalises the way that humans deal with incomplete and inconsistent information through the use of arguments and counterarguments.

This project relates to the EPSRC's 'Artificial intelligence technologies' research area.

Supervisor Details
- Co-primary Supervisor: Professor Reecha Sofat, Institute of Health Informatics, UCL
- Co-primary Supervisor: Professor Anthony Hunter, Computer Sciences, UCL
- Secondary Supervisor: Dr Dionisio Acosta-Mena, Cegedim

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S021612/1 01/04/2019 30/09/2027
2418704 Studentship EP/S021612/1 28/09/2020 30/09/2024 Alexander Wright