Murphy, Rachel M. https://orcid.org/0000-0002-2602-5658
Mishra, Nishant
de Keizer, Nicolette F. https://orcid.org/0000-0002-6651-1730
Dongelmans, Dave A. https://orcid.org/0000-0001-8477-6671
Jager, Kitty J. https://orcid.org/0000-0003-0444-8569
Abu-Hanna, Ameen https://orcid.org/0000-0003-4324-7954
Klopotowska, Joanna E. https://orcid.org/0000-0002-9707-5740
Calixto, Iacer https://orcid.org/0000-0001-6244-7906
Funding for this research was provided by:
Amsterdam University Medical Centers (23088)
ZonMw (848018004)
Nederlandse Organisatie voor Wetenschappelijk Onderzoek (NWO-2024.015)
Nederlandse Organisatie voor Wetenschappelijk Onderzoek (NGF.1607.22.014)
Article History
Received: 3 September 2025
Accepted: 28 January 2026
First Online: 22 February 2026
Declarations
:
: This study was part of project “Towards a leaRning mEdication Safety system in a national network of Intensive Care Units – timely detection of adverse drug Events” funded partly by Innovation Fund 2019 of Amsterdam UMC (project no. 23088) and by The Netherlands Organization for Health Research and Development (ZonMw project no. 848018004). This study was also part of the project “Research in clinical prediction models and natural language processing with deep learning” funded by the Dutch Research Council (NWO, project no. NWO-2024.015) of the research program Computing Time on National Computer Facilities. The computational resources used were financed by the Dutch Research Council (NWO). I.C. and N.M. are part of the project “CaRe-NLP” with project no. NGF.1607.22.014 of the research program “NGF - AiNed Fellowship,” which is (partly) financed by the Dutch Research Council (NWO). The funders had no role in the design of the study, the collection, analysis, and interpretation of data, or in the writing of the manuscript.
: The authors have no conflicts of interests that are directly relevant to the content of this article.
: This study was exempted from requiring ethics approval on 3 June 2019 (non-WMO waiver W19_207 no. 19.252) by the Medical Ethics Committee of the Amsterdam University Medical Centre, University of Amsterdam, the Netherlands, as it did not fall within the scope of the Dutch Medical Research Involving Human Subjects Act (WMO). Prior to obtaining the data from the Research Data Management office of Amsterdam UMC, we performed a Data Protection Impact Assessment, which was assessed and approved by the privacy officer of Amsterdam UMC.
: In accordance with Dutch and Amsterdam UMC regulation regarding reuse of routine care data for research, informed consent of patients is not required for anonymized data. Patients who do not agree to the reuse of their routine care data for research are excluded from data extractions by the Research Data Management office.
: Not applicable.
: The Dutch ADE corpus was generated as part of a previous study and can be requested for research purposes upon reasonable request and subject to certain limitations. For more details, please visit: . The ICU-AKI corpus and the WINGS corpus cannot be shared to preserve the privacy of the patients involved and research agreements with third parties.Availability of CodeWe have shared all the code necessary to reproduce all our experiments at .
: Rachel M. Murphy: conceptualization, data curation, methodology, project administration, visualization, writing—original draft preparation, and writing—review and editing; Nishant Mishra: formal analysis, methodology, software, visualization, writing—original draft preparation, and writing—review and editing; Nicolette F. de Keizer: funding acquisition, supervision, and writing—review and editing; Dave A. Dongelmans: funding acquisition, supervision, and writing—review and editing; Kitty J. Jager: funding acquisition and writing—review and editing; Ameen Abu-Hanna: funding acquisition, methodology, supervision, and writing—review and editing; Joanna E. Klopotowska: conceptualization, funding acquisition, methodology, project administration, resources, supervision, and writing—review and editing; Iacer Calixto: conceptualization, formal analysis, methodology, resources, software, supervision, writing—original draft preparation, and writing—review and editing.