Appealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making
Ammeling J, Manger C, Kwaka E, Krügel S, Uhl M, Kießig A, Fritz A, Ganz J, Riener A, Bertram CA, Breininger K, Aubreville M (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Association for Computing Machinery
Pages Range: 330-335
Conference Proceedings Title: ACM International Conference Proceeding Series
Event location: Rapperswil, CHE
ISBN: 9798400707711
Abstract
Artificial intelligence (AI)-based recommender systems can help to improve efficiency and accuracy in medical decision making. Yet, it has been shown that a recommendation given by an algorithm can influence the human expert responsible for the decision. The strength and direction of this bias, induced by a computer-aided diagnosis workflow, can be influenced by the visual representation of the results. This study focuses on evaluating four frequently used visualization types (bounding box, segmentation mask, segmentation contour, and heatmap) for displaying segmentation results of medical data. A group of 24 medical experts specializing in pathology and radiology participated in the evaluation, assessing the subjective appeal of these visualizations. The study evaluated the pragmatic and hedonic quality of the visualizations based on a standardized questionnaire and specific criteria relevant to medical decision making. The findings indicate that the heatmap received the highest ratings for non-task-oriented aspects of the user experience. However, it exhibited significant inconsistencies among experts concerning task-oriented aspects and was perceived as the most biasing visualization type. On the other hand, the segmentation contour consistently received high ratings across various subscales. The results of the study contribute to better alignment between visualization techniques and user requirements for the development of future AI-based recommender systems.
Authors with CRIS profile
Involved external institutions
Katholische Universität Eichstätt-Ingolstadt
Germany (DE)
Veterinärmedizinische Universität Wien (Vetmeduni Vienna) / University of Veterinary Medicine, Vienna
Austria (AT)
Technische Hochschule Ingolstadt
Germany (DE)
Germany (DE)
Veterinärmedizinische Universität Wien (Vetmeduni Vienna) / University of Veterinary Medicine, Vienna
Austria (AT)
Technische Hochschule Ingolstadt
Germany (DE)
How to cite
APA:
Ammeling, J., Manger, C., Kwaka, E., Krügel, S., Uhl, M., Kießig, A.,... Aubreville, M. (2023). Appealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making. In Markus Stolze, Frieder Loch, Matthias Baldauf, Florian Alt, Christina Schneegass, Thomas Kosch, Teresa Hirzle, Shadan Sadeghian, Fiona Draxler, Kenan Bektas, Katrin Lohan, Pascal Knierim (Eds.), ACM International Conference Proceeding Series (pp. 330-335). Rapperswil, CHE: Association for Computing Machinery.
MLA:
Ammeling, Jonas, et al. "Appealing but Potentially Biasing - Investigation of the Visual Representation of Segmentation Predictions by AI Recommender Systems for Medical Decision Making." Proceedings of the 2023 Mensch und Computer Conference, MuC 2023, Rapperswil, CHE Ed. Markus Stolze, Frieder Loch, Matthias Baldauf, Florian Alt, Christina Schneegass, Thomas Kosch, Teresa Hirzle, Shadan Sadeghian, Fiona Draxler, Kenan Bektas, Katrin Lohan, Pascal Knierim, Association for Computing Machinery, 2023. 330-335.
BibTeX: Download