Learning with an evolving medicine label: how artificial intelligence-based medication recommendation systems must adapt to changing medication labels.

Dickinson, Harriet Aprilia; Feifel, Jan; Muylle, Katoo; Ochi, Taichi; Vallejo-Yagüe, Enriqueta (2024). Learning with an evolving medicine label: how artificial intelligence-based medication recommendation systems must adapt to changing medication labels. (In Press). Expert Opinion on Drug Safety Taylor & Francis 10.1080/14740338.2024.2338252

Full text not available from this repository. (Request a copy)

Artificial intelligence or machine learning (AI/ML) based systems can be used to help personalize prescribing decisions for individual patients. These AI/ML clinical decision support systems may provide either specific or more open-ended recommendations for the most appropriate medications to prescribe. These systems must fundamentally relate to the label of the medicines involved. The label of a medicine is an approved guide that indicates how to prescribe the drug in a safe and effective manner. The label for a medicine may evolve as new information on safety and effectiveness emerges, leading to the addition or removal of warnings, drug-drug interactions, or to permit new indications. Therefore, any AI/ML recommendation system would need to reference these label updates. However, the speed and consistency which these updates are made may influence the safety of prescribing decisions, since change control procedures and revalidation of algorithms may slow down any changes. This is especially important if changes need to be made quickly to protect patients. These considerations highlight the important role that pharmacoepidemiologists and drug safety professionals must play within this conversation. Furthermore, the guiding role that regulators have in regulating the development and use of these AI/ML clinical decision support systems is highlighted.

Item Type:	Journal Article (Original Article)
Division/Institute:	04 Faculty of Medicine > Medical Education > Institute of General Practice and Primary Care (BIHAM)
UniBE Contributor:	Vallejo Yagüe, Enriqueta
Subjects:	600 Technology > 610 Medicine & health 300 Social sciences, sociology & anthropology > 360 Social problems & social services
ISSN:	1474-0338
Publisher:	Taylor & Francis
Language:	English
Submitter:	Pubmed Import
Date Deposited:	11 Apr 2024 09:46
Last Modified:	18 Apr 2024 15:48
Publisher DOI:	10.1080/14740338.2024.2338252
PubMed ID:	38597245
Uncontrolled Keywords:	Artificial intelligence CDS clinical decision support SaMD drug label machine learning precision medicine
URI:	https://boris.unibe.ch/id/eprint/195859