EUVIMEDEUVIMED entdecken
Open Access

Evaluating an AI Decision Support System for the Emergency Department: Retrospective Study

Yvette Van Der Haas iD, Wiesje Roskamp iD, Lidwina Elisabeth Maria Chang-Willems iD, Boudewijn van Dongen iD, Swetta Jansen iD, Annemarie de Jong iD, Renata Medeiros de Carvalho iD, Dorien Melman iD, Arjan van de Merwe, Marieke Bastian-Sanders iD, Bart Overbeek iD, Rogier Leendert Charles Plas iD und 2 weitere

JMIR AI · 26.01.2026 · 5 · e80448

DOI: 10.2196/80448 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR AI, online erschienen am 26.01.2026. Verfasst von Yvette Van Der Haas und 13 weiteren Autor:innen. Beteiligte Einrichtung: Eindhoven University of Technology, Eindhoven, The Netherlands. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Overcrowding in the emergency department (ED) is a growing challenge, associated with increased medical errors, longer patient stays, higher morbidity, and increased mortality rates. Artificial intelligence (AI) decision support tools have shown potential in addressing this problem by assisting with faster decision-making regarding patient admissions; yet many studies neglect to focus on the clinical relevance and practical applications of these AI solutions.

Objective

This study aimed to evaluate the clinical relevance of an AI model in predicting patient admission from the ED to hospital wards and its potential impact on reducing the time needed to make an admission decision.

Methods

A retrospective study was conducted using anonymized patient data from St. Antonius Hospital, the Netherlands, from January 2018 to September 2023. An Extreme Gradient Boosting AI model was developed and tested on these data of 154,347 visits to predict admission decisions. The model was evaluated using data segmented into 10-minute intervals, which reflected real-world applicability. The primary outcome measured was the reduction in the decision-making time between the AI model and the admission decision made by the clinician. Secondary outcomes analyzed the performance of the model across various subgroups, including the age of the patient, medical specialty, classification category, and time of day.

Results

The AI model demonstrated a precision of 0.78 and a recall of 0.73, with a median time saving of 111 (IQR 59-169) minutes for true positive predicted patients. Subgroup analysis revealed that older patients and certain specialties such as pulmonology benefited the most from the AI model, with time savings of up to 90 minutes per patient.

Conclusions

The AI model shows significant potential to reduce the time to admission decisions, alleviate ED overcrowding, and improve patient care. The model offers the advantage of always providing weighted advice on admission, even when the ED is under pressure. Future prospective studies are needed to assess the impact in the real world and further enhance the performance of the model in diverse hospital settings.

Schlagwörter

Stichwörter der Autor:innen

AIartificial intelligenceclinical impactemergency departmenthealth care

Autor:innen und Institutionen

  • Eindhoven University of Technology, Eindhoven, The Netherlands.
  • St. Antonius Ziekenhuis, Utrecht, The Netherlands.

ORCID-Profile: Yvette Van Der Haas, Wiesje Roskamp, Lidwina Elisabeth Maria Chang-Willems, Boudewijn van Dongen, Swetta Jansen, Annemarie de Jong, Renata Medeiros de Carvalho, Dorien Melman, Marieke Bastian-Sanders, Bart Overbeek, Rogier Leendert Charles Plas, Marleen Vreeburg, Thomas van Dijk

Zitieren

APA

Van Der Haas, Y., Roskamp, W., Chang-Willems, L. E. M., van Dongen, B., Jansen, S., de Jong, A., Medeiros de Carvalho, R., Melman, D., van de Merwe, A., Bastian-Sanders, M., Overbeek, B., Plas, R. L. C., Vreeburg, M., & van Dijk, T. (2026). Evaluating an AI Decision Support System for the Emergency Department: Retrospective Study. JMIR AI, 5, e80448. https://doi.org/10.2196/80448

Vancouver

Van Der Haas Y, Roskamp W, Chang-Willems LEM, van Dongen B, Jansen S, de Jong A, et al. Evaluating an AI Decision Support System for the Emergency Department: Retrospective Study. JMIR AI. 2026;5:e80448. doi:10.2196/80448

BibTeX
@article{VanDerHaas2026,
  author = {Van Der Haas, Yvette and Roskamp, Wiesje and Chang-Willems, Lidwina Elisabeth Maria and van Dongen, Boudewijn and Jansen, Swetta and de Jong, Annemarie and Medeiros de Carvalho, Renata and Melman, Dorien and van de Merwe, Arjan and Bastian-Sanders, Marieke and Overbeek, Bart and Plas, Rogier Leendert Charles and Vreeburg, Marleen and van Dijk, Thomas},
  title = {Evaluating an AI Decision Support System for the Emergency Department: Retrospective Study},
  journal = {JMIR AI},
  year = {2026},
  volume = {5},
  pages = {e80448},
  doi = {10.2196/80448}
}
Kostenlos starten →