EUVIMEDEUVIMED entdecken
Open Access

The Impact of Information Relevancy and Interactivity on Intensivists’ Trust in a Machine Learning–Based Bacteremia Prediction System: Simulation Study

Omer Katzburg iD, Michael Roimi iD, Amit Frenkel iD, Roy Ilan iD, Yuval Bitan iD

JMIR Human Factors · 01.08.2024 · 11 · e56924-e56924

DOI: 10.2196/56924 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Human Factors, online erschienen am 01.08.2024. Verfasst von Omer Katzburg und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Policy and Management, Ben-Gurion University of the Negev, Be'er Sheva, Israel. Hauptthemen laut MEDLINE: Machine Learning, Trust, Bacteremia, Decision Support Systems, Clinical. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The exponential growth in computing power and the increasing digitization of information have substantially advanced the machine learning (ML) research field. However, ML algorithms are often considered “black boxes,” and this fosters distrust. In medical domains, in which mistakes can result in fatal outcomes, practitioners may be especially reluctant to trust ML algorithms.

Objective

The aim of this study is to explore the effect of user-interface design features on intensivists’ trust in an ML-based clinical decision support system.

Methods

A total of 47 physicians from critical care specialties were presented with 3 patient cases of bacteremia in the setting of an ML-based simulation system. Three conditions of the simulation were tested according to combinations of information relevancy and interactivity. Participants’ trust in the system was assessed by their agreement with the system’s prediction and a postexperiment questionnaire. Linear regression models were applied to measure the effects.

Results

Participants’ agreement with the system’s prediction did not differ according to the experimental conditions. However, in the postexperiment questionnaire, higher information relevancy ratings and interactivity ratings were associated with higher perceived trust in the system ( P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTrustBacteremiaDecision Support Systems, ClinicalHumansMaleFemaleAdultMiddle AgedSurveys and QuestionnairesUser-Computer Interface

Stichwörter der Autor:innen

AIMLartificial intelligenceautomationclinical decision supportdecision makingdecision supportdecision support systemdecision support systemsdigitizationdigitization of informationhuman-MLhuman-ML interactionhuman-ML interactionshuman-automation interaction

Autor:innen und Institutionen

  • Department of Health Policy and Management, Ben-Gurion University of the Negev, Be'er Sheva, Israel.
  • General Intensive Care Unit, Rambam Medical Center, Haifa, Israel.
  • General Intensive Care Unit, Soroka Medical Center, Be'er Sheva, Israel.

ORCID-Profile: Omer Katzburg, Michael Roimi, Amit Frenkel, Roy Ilan, Yuval Bitan

Zitieren

APA

Katzburg, O., Roimi, M., Frenkel, A., Ilan, R., & Bitan, Y. (2024). The Impact of Information Relevancy and Interactivity on Intensivists’ Trust in a Machine Learning–Based Bacteremia Prediction System: Simulation Study. JMIR Human Factors, 11, e56924-e56924. https://doi.org/10.2196/56924

Vancouver

Katzburg O, Roimi M, Frenkel A, Ilan R, Bitan Y. The Impact of Information Relevancy and Interactivity on Intensivists’ Trust in a Machine Learning–Based Bacteremia Prediction System: Simulation Study. JMIR Human Factors. 2024;11:e56924-e56924. doi:10.2196/56924

BibTeX
@article{Katzburg2024,
  author = {Katzburg, Omer and Roimi, Michael and Frenkel, Amit and Ilan, Roy and Bitan, Yuval},
  title = {The Impact of Information Relevancy and Interactivity on Intensivists’ Trust in a Machine Learning–Based Bacteremia Prediction System: Simulation Study},
  journal = {JMIR Human Factors},
  year = {2024},
  volume = {11},
  pages = {e56924--e56924},
  doi = {10.2196/56924}
}
Kostenlos starten →