Publikationsdatenbank

"When two wrongs don't make a right" - examining confirmation bias and the role of time pressure during human-aI collaboration in computational pathology (2025)

Art

Vortrag

Autoren

Rosbach, Emily

Ammeling, Jonas

Krügel, Sebastian

Kießig, Angelika

Fritz, Alexis

Ganz, Jonathan

Puget, Chloé (WE 12)

Donovan, Taryn

Klang, Andrea

Köller, Maximilian C.

Bolfa, Pompei

Tecilla, Marco

Denk, Daniela

Kiupel, Matti

Paraschou, Georgios

Kok, Mun Keong

Haake, Alexander (WE 12)

de Krijger, Ronald R.

Sonnen, Andreas F.-P.

Kasantikul, Tanit

Dorrestein, Gerry M.

Smedley, Rebecca C.

Stathonikos, Nikolas

Uhl, Matthias

Bertram, Christof A.

Riener, Andreas

Aubreville, Marc

Kongress

CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

Yokohama, Japan, 26.04. – 01.05.2025

Quelle

CHI '25: proceedings of the 2025 CHI conference on human factors in computing systems — Naomi Yamashita,Vanessa Evers, Koji Yatani, Xianghua (Sharon) Ding, Bongshin Lee, Marshini Chetty, Phoebe Toups-Dugas (Hrsg.)

New York, NY, United States: Association for Computing Machinery, 2025 — S. 1–18

ISBN: 979-8-4007-1394-1

Sprache

Englisch

Verweise

URL (Volltext): https://dl.acm.org/doi/pdf/10.1145/3706598.3713319

DOI: 10.1145/3706598.3713319

Kontakt

Institut für Tierpathologie

Robert-von-Ostertag-Str. 15
14163 Berlin
+49 30 838 62450
pathologie@vetmed.fu-berlin.de

Abstract / Zusammenfassung

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.