Receiving Information on Machine Learning‐Based Clinical Decision Support Systems in Psychiatric Services Increases Staff Trust in These Systems: A Randomized Survey Experiment
Der Erhalt von Informationen zu ML-basierten klinischen Entscheidungshilfesystemen in psychiatrischen Diensten erhöht das Vertrauen des Personals in diese Systeme: randomisiertes Survey-Experiment
Acta Psychiatrica Scandinavica · 2025-07 · 152 (1) · 39-48
DOI: 10.1111/acps.13791 ↗Auf einen Blick
Bei 780 Teilnehmenden erhöhte Information zu ML-basierten klinischen Entscheidungshilfesystemen das Vertrauen und verringerte das Misstrauen gegenüber diesen Systemen.
Fragestellung
Erhöht Basisinformation zu ML-basierten klinischen Entscheidungshilfesystemen das Vertrauen von Mitarbeitenden in psychiatrischen Diensten?
Methode
Randomisiertes Survey-Experiment unter Mitarbeitenden der Psychiatric Services der Central Denmark Region; 3 Studienarme mit unterschiedlicher Information; Auswertung über paarweise Vergleiche der Summenscores.
Ergebnisse
2838 Eingeladene, 780 Teilnehmende. Gegenüber dem aktiven Kontrollarm: Vertrauen +5 % (95 %-KI 2 % bis 9 %), Misstrauen −4 % (95 %-KI −7 % bis −1 %). Gegenüber dem blanken Kontrollarm: Vertrauen +5 % (95 %-KI 2 % bis 11 %), Misstrauen −3 % (95 %-KI −6 % bis −1 %).
Schlussfolgerung der Autor:innen
Die Bereitstellung von Informationen zu ML-basierten klinischen Entscheidungshilfesystemen in der Krankenhauspsychiatrie kann das Vertrauen des Gesundheitspersonals in solche Systeme erhöhen.
Kernaussagen
- Information erhöhte das Vertrauen in ML-basierte Entscheidungshilfesysteme.
- Misstrauen nahm in beiden Vergleichen ab.
- Studie als randomisiertes Survey-Experiment mit 780 Teilnehmenden.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Randomisierte kontrollierte Studie in der Zeitschrift Acta Psychiatrica Scandinavica, online erschienen am 11.02.2025. Verfasst von Erik Perfalk und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Affective Disorders, Aarhus University Hospital - Psychiatry, Aarhus, Denmark. Hauptthemen laut MEDLINE: Trust, Decision Support Systems, Clinical, Machine Learning, Mental Health Services. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Danish Agency for Digital Government National Uptake Fund for New Technologies, Danish Cancer Society, Central Denmark Region Fund for Strengthening of Health Science.
Abstract (Originalsprache)
Background
Clinical decision support systems based on machine learning (ML) models are emerging within psychiatry. To ensure their successful implementation, healthcare staff needs to trust these systems. Here, we investigated if providing staff with basic information about ML‐based clinical decision support systems enhances their trust in them.
Methods
We conducted a randomised survey experiment among staff in the Psychiatric Services of the Central Denmark Region. The participants were allocated to one of three arms, receiving different types of information: An intervention arm (receiving information on clinical decision‐making supported by an ML model); an active control arm (receiving information on standard clinical decision process without ML support); and a blank control arm (no information). Subsequently, participants responded to various questions regarding their trust/distrust in ML‐based clinical decision support systems. The effect of the intervention was assessed by pairwise comparisons between all randomization arms on sum scores of trust and distrust.
Results
Among 2838 invitees, 780 completed the survey experiment. The intervention enhanced trust and diminished distrust in ML‐based clinical decision support systems compared with the active control arm (Trust: mean difference = 5% [95% confidence interval (CI): 2%; 9%], p value < 0.001; Distrust: mean difference = −4% [−7%; −1%], p value = 0.042) and the blank control arm (Trust: mean difference = 5% [2%; 11%], p value = 0.003; Distrust: mean difference = −3% [−6%; −1%], p value = 0.021).
Conclusion
Providing information on ML‐based clinical decision support systems in hospital psychiatry may increase healthcare staff trust in such systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Affective Disorders, Aarhus University Hospital - Psychiatry, Aarhus, Denmark.
- Department of Clinical Medicine, Aarhus University, Aarhus, Denmark.
ORCID-Profile: Erik Perfalk, Martin Bernstorff, Andreas Aalkjær Danielsen, Søren Dinesen Østergaard
Förderung
- Danish Agency for Digital Government National Uptake Fund for New Technologies
- Danish Cancer Society
- Central Denmark Region Fund for Strengthening of Health Science
- Lundbeck Foundation
- Kræftens Bekæmpelse
Zitieren
APA
Perfalk, E., Bernstorff, M., Danielsen, A. A., & Østergaard, S. D. (2025). Receiving Information on Machine Learning‐Based Clinical Decision Support Systems in Psychiatric Services Increases Staff Trust in These Systems: A Randomized Survey Experiment. Acta Psychiatrica Scandinavica, 152(1), 39-48. https://doi.org/10.1111/acps.13791
Vancouver
Perfalk E, Bernstorff M, Danielsen AA, Østergaard SD. Receiving Information on Machine Learning‐Based Clinical Decision Support Systems in Psychiatric Services Increases Staff Trust in These Systems: A Randomized Survey Experiment. Acta Psychiatrica Scandinavica. 2025;152(1):39-48. doi:10.1111/acps.13791
BibTeX
@article{Perfalk2025,
author = {Perfalk, Erik and Bernstorff, Martin and Danielsen, Andreas Aalkjær and Østergaard, Søren Dinesen},
title = {Receiving Information on Machine Learning‐Based Clinical Decision Support Systems in Psychiatric Services Increases Staff Trust in These Systems: A Randomized Survey Experiment},
journal = {Acta Psychiatrica Scandinavica},
year = {2025},
volume = {152},
number = {1},
pages = {39--48},
doi = {10.1111/acps.13791}
}
EUVIMED