Characterising the dynamic inter-relationships between polypharmacy and multiple long-term conditions
Principal Investigator: Professor Nick Reynolds
Full project title: Characterising the dynamic inter-relationships between polypharmacy and multiple long-term conditions. Using artificial intelligence (AI) to map patient journeys into multimorbidity clusters in British Association of Dermatologists Biologics and Immunomodulators Register (BADBIR)
People who live with several medical conditions (MLTCs) are often prescribed multiple medicines (polypharmacy). The relationship between MLTCs and polypharmacy is complex and not well understood, but we know that such patients may experience poorer outcomes, as the prescribed medications can negatively interact with one another and cause side effects. However, some medicines may prevent the development of further MLTCs. Psoriasis is increasingly recognised as a systemic disorder with associated MLTCs. Our aim is to design interventions to ensure medicines are prescribed in combinations that support the patient, instead of doing more harm.
Our group has experience in applying new developments in computer technology and machine learning to healthcare data. In this project, we will use this approach to look for patterns of MLTCs and their association with prescription data in patients with psoriasis who have been recruited into a nation-wide study called British Association of Dermatologists Biologic and Immunomodulators Register (BADBIR).
Our goal is to better understand the dynamic relationship between MLTCs and polypharmacy and thereby to optimise the medicines prescribed for individual patients. This research will also identify key points for intervention, to maintain the best possible health trajectory for people with MLTCs.
Image (right): used with permission, showing psoriasis and psoriatic arthritis, demonstrating a patient living with more than one condition.