The Effect of Ambient Artificial Intelligence Documentation on Clinician Workload, Efficiency, and Patient Experience in a Multisite Emergency Department Network
Applied Clinical Informatics · 2026-08 · 17 (04) · 767-780
DOI: 10.1055/a-2939-3038 ↗Auf einen Blick
In 14 Notaufnahmen war Ambient-AI-Dokumentation mit besserer wahrgenommener Zuhörqualität und geringerer Belastung verbunden. Die aktive Bearbeitungszeit änderte sich nicht.
Fragestellung
Wie wirkt sich Ambient-AI-Dokumentation in einem Notaufnahmenetzwerk auf Patientenerfahrung, Dokumentationseffizienz, Arbeitsbelastung und Durchsatz aus?
Methode
Retrospektive beobachtende Kohortenstudie zur Einführung von Ambient AI in 14 EDs von Mai 2024 bis Juni 2025.
Ergebnisse
Ambient AI wurde in 8,6 % von 315.242 ED-Notizen genutzt. Zuhören: 82,0 vs. 76,6 %; OR 1,39; p = 0,003. Aktive Bearbeitungszeit: +0,17 min; 95 %-KI −1,00 bis +1,55; p = 0,349. NASA-TLX: −40,2 Punkte; 95 %-KI 30,4–50,1.
Schlussfolgerung der Autor:innen
Ambient-AI-Dokumentation war mit besserer patientenberichteter Zuhörqualität, früherem Abschluss der Notizen, weniger übernommenem Inhalt und geringerer kognitiver Belastung verbunden, ohne die aktive Bearbeitungszeit pro Notiz zu verändern.
Kernaussagen
- 8,6 % von 315.242 Notizen nutzten Ambient AI
- NASA-TLX sank um 40,2 Punkte
- Aktive Bearbeitungszeit unterschied sich nicht
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Multizentrische Studie in der Zeitschrift Applied Clinical Informatics, online erschienen am 14.09.2026. Verfasst von Markos G Kashiouris und 6 weiteren Autor:innen. Beteiligte Einrichtung: INOVA Health System, Virginia, United States, Falls Church. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Documentation, Artificial Intelligence, Workload. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Ambient artificial intelligence (AI) documentation systems have emerged as a potential solution to clerical burden in medicine, yet evidence in emergency settings remains limited.
Objectives
The objective of this study is to evaluate the ambient AI on patient experience, documentation efficiency, clinician workload, and clinical throughput across a large emergency department (ED) network.
Methods
This is a retrospective, observational cohort study of ambient AI rollout across 14 EDs (May 2024–June 2025). Clinicians applied the tool on a voluntary basis and contributed both AI-assisted and conventional notes. Outcomes included patient-reported experience, active editing time, disposition-to-completion time, copied-forward content, and on-time note completion. Clinician workload was assessed with pre- and postimplementation surveys including the NASA Task Load Index (TLX).
Results
Ambient AI was used in 8.6% of 315,242 ED clinical notes. AI use was associated with higher top-box ratings for clinician listening (82.0 vs. 76.6%; odds ratio [OR]: 1.39; p = 0.003) but not likelihood to recommend (77.6 vs. 75.0%; OR: 1.15; p = 0.185). Within-clinician paired analysis showed no difference in active editing time between AI and conventional notes (median difference: +0.17 min; 95% confidence interval [CI]: −1.00 to +1.55; p = 0.349), and clinicians typed 722 fewer characters per AI-assisted note. Documentation finalized 3.4 h earlier for admitted and 6.0 h earlier for discharged patients; the disposition-to-completion difference was +5.06 h (p = 0.337), reflecting attenuation of early-adopter’s advantage. AI-assisted notes were half as likely to include copied content (9.4 vs. 18.3%; OR: 0.46; p < 0.001). NASA-TLX workload decreased by 40.2 points (95% CI: 30.4–50.1).
Conclusion
Ambient AI documentation was associated with improved patient-reported listening, earlier note completion, reduced copied-forward content, and lower clinician-perceived cognitive burden, without altering active editing time per note. These findings suggest a scalable tool for reducing clerical burden in high-throughput emergency care, while introducing new responsibilities for clinicians to review, edit, and sign machine-generated notes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- INOVA Health System, Virginia, United States, Falls Church.
ORCID-Profile: Markos G Kashiouris, Brent Dibble
Zitieren
APA
Kashiouris, M. G., Miner, A., Saleh, S., Scripps, M., Stanton, L., Samuel, G., & Dibble, B. (2026). The Effect of Ambient Artificial Intelligence Documentation on Clinician Workload, Efficiency, and Patient Experience in a Multisite Emergency Department Network. Applied Clinical Informatics, 17(04), 767-780. https://doi.org/10.1055/a-2939-3038
Vancouver
Kashiouris MG, Miner A, Saleh S, Scripps M, Stanton L, Samuel G, et al. The Effect of Ambient Artificial Intelligence Documentation on Clinician Workload, Efficiency, and Patient Experience in a Multisite Emergency Department Network. Applied Clinical Informatics. 2026;17(04):767-780. doi:10.1055/a-2939-3038
BibTeX
@article{Kashiouris2026,
author = {Kashiouris, Markos G and Miner, Andrew and Saleh, Sameh and Scripps, Matthrew and Stanton, Lindsey and Samuel, Golda and Dibble, Brent},
title = {The Effect of Ambient Artificial Intelligence Documentation on Clinician Workload, Efficiency, and Patient Experience in a Multisite Emergency Department Network},
journal = {Applied Clinical Informatics},
year = {2026},
volume = {17},
number = {04},
pages = {767--780},
doi = {10.1055/a-2939-3038}
}
EUVIMED