"When Two Wrongs Don't Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology

要旨

Artificial intelligence (AI)-based decision support systems hold promise for enhancing diagnostic accuracy and efficiency in computational pathology. However, human-AI collaboration can introduce and amplify cognitive biases, like confirmation bias caused by false confirmation when erroneous human opinions are reinforced by inaccurate AI output. This bias may increase under time pressure, a ubiquitous factor in routine pathology, as it strains practitioners' cognitive resources. We quantified confirmation bias triggered by AI-induced false confirmation and examined the role of time constraints in a web-based experiment, where trained pathology experts (n=28) estimated tumor cell percentages. Our results suggest that AI integration fuels confirmation bias, evidenced by a statistically significant positive linear-mixed-effects model coefficient linking AI recommendations mirroring flawed human judgment and alignment with system advice. Conversely, time pressure appeared to weaken this relationship. These findings highlight potential risks of AI in healthcare and aim to support the safe integration of clinical decision support systems.

受賞
Honorable Mention
著者
Emely Rosbach
Technische Hochschule Ingolstadt, Ingolstadt, Germany
Jonas Ammeling
Technische Hochschule Ingolstadt, Ingolstadt, Germany
Sebastian Krügel
University of Hohenheim, Stuttgart, Germany
Angelika Kießig
Katholische Universität Eichstätt, Eichstätt, Germany
Alexis Fritz
Albert-Ludwigs-Universität Freiburg, Freiburg im Breisgau, Germany
Jonathan Ganz
Technische Hochschule Ingolstadt, Ingolstadt, Germany
Chloé Puget
Freie Universität Berlin, Berlin, Germany
Taryn Donovan
Animal Medical Center, New York, New York, United States
Andrea Klang
University of Veterinary Medicine Vienna, Vienna, Austria
Maximilian C. Köller
Medical University of Vienna, Vienna, Germany
Pompei Bolfa
Ross University School of Veterinary Medicine, Basseterre, Saint Kitts and Nevis
Marco Tecilla
University of Milan, Milan, Italy
Daniela Denk
Ludwig-Maximilians-University of Munich, Munich, Germany
Matti Kiupel
Michigan State University, East Lansing, Michigan, United States
Georgios Paraschou
Ross University School of Veterinary Medicine, Basseterre, Saint Kitts and Nevis
Mun Keong Kok
Faculty of Veterinary Medicine, Universiti Putra Malaysia, Serdang, Malaysia
Alexander F. H.. Haake
Freie Universität Berlin, Berlin, Germany
Ronald R. de Krijger
UMC Utrecht, Utrecht, Netherlands
Andreas F.-P. Sonnen
UMC Utrecht, Utrecht, Netherlands
Tanit Kasantikul
Michigan State University, East Lansing, Michigan, United States
Gerry M. Dorrestein
NOIVBD, Vessem, Netherlands
Rebecca C. Smedley
Michigan State University, East Lansing, Michigan, United States
Nikolas Stathonikos
UMC Utrecht, Utrecht, Netherlands
Matthias Uhl
University of Hohenheim, Stuttgart, Germany
Christof A. Bertram
University of Veterinary Medicine Vienna, Vienna, Austria
Andreas Riener
Technische Hochschule Ingolstadt, Ingolstadt, Bavaria, Germany
Marc Aubreville
Flensburg University of Applied Sciences, Flensburg, Germany
DOI

10.1145/3706598.3713319

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713319

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Human-AI Collaboration

G304
7 件の発表
2025-05-01 01:20:00
2025-05-01 02:50:00
日本語まとめ
読み込み中…