TY - GEN
T1 - "When Two Wrongs Don't Make a Right" - Examining Confirmation Bias and the Role of Time Pressure During Human-AI Collaboration in Computational Pathology
AU - Rosbach, Emely
AU - Ammeling, Jonas
AU - Krügel, Sebastian
AU - Kießig, Angelika
AU - Fritz, Alexis
AU - Ganz, Jonathan
AU - Puget, Chloé
AU - Donovan, Taryn
AU - Klang, Andrea
AU - Köller, Maximilian C.
AU - Bolfa, Pompei
AU - Tecilla, Marco
AU - Denk, Daniela
AU - Kiupel, Matti
AU - Paraschou, Georgios
AU - Kok, Mun Keong
AU - Haake, Alexander F.H.
AU - De Krijger, Ronald R.
AU - Sonnen, Andreas F.P.
AU - Kasantikul, Tanit
AU - Dorrestein, Gerry M.
AU - Smedley, Rebecca C.
AU - Stathonikos, Nikolas
AU - Uhl, Matthias
AU - Bertram, Christof A.
AU - Riener, Andreas
AU - Aubreville, Marc
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/4/26
Y1 - 2025/4/26
N2 - 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.
AB - 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.
KW - Artificial Intelligence
KW - Clinical Decision Support Systems
KW - Cognitive Bias
KW - Computational Pathology
KW - Confirmation Bias
KW - Decision Support Systems
KW - Healthcare
KW - Time Pressure
UR - https://www.scopus.com/pages/publications/105005749959
UR - https://www.mendeley.com/catalogue/73824d0d-5bad-3fe9-92ef-a5b7471f6ddb/
U2 - 10.1145/3706598.3713319
DO - 10.1145/3706598.3713319
M3 - Conference contribution
AN - SCOPUS:105005749959
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI 2025 - Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
T2 - 2025 CHI Conference on Human Factors in Computing Systems, CHI 2025
Y2 - 26 April 2025 through 1 May 2025
ER -