CoChat

The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.

Cognitive Friction in Clinical Decision Support: A Comparative Study of Judicial and Adjunct Human-AI Interaction Protocols

Open access

Abstract

Artificial intelligence is increasingly used to support clinical decision making, yet concerns remain regarding algorithmic aversion, automation bias and the preservation of meaningful human oversight; while explainable AI aims to improve transparency, less attention has been devoted to the design of human–AI interaction protocols. This study investigates Frictional AI, an interaction paradigm that introduces cognitive friction to encourage critical engagement with AI recommendations. First, semi-structured interviews were conducted with a legal expert and a psychologist and analyzed through thematic analysis to identify legal, ethical, and cognitive requirements for AI-assisted decision support. Second, a user study involving 96 medical residents compared three interaction protocols: a conventional explainable AI-first design (XAI) and two friction-based protocols, namely a judicial protocol based on juxtaposed explanations (Judicial AI, JAI) and an adjunct protocol requiring an initial unsupported decision before AI exposure (AAI). Diagnostic accuracy and confidence, perceived usefulness, completion time, and reliance patterns were evaluated. The interviews highlighted the importance of human-centered explanations, contrastive reasoning, preservation of professional responsibility, and the role of user studies in evaluating human–AI interaction. The quantitative results showed that none of the AI-assisted conditions improved diagnostic accuracy relative to the no-support baseline. However, JAI achieved performance comparable to the baseline, outperforming XAI and AAI, and exhibited the lowest level of over-reliance. Overall findings suggest that the effectiveness of decision-support systems depends not only on model performance and explanation quality but also on interaction design. In conclusion, while preserving diagnostic performance, judicial protocols showed promise in mitigating automation bias and promoting active cognitive engagement in clinical decision support.

Overview

Integrity signals

Registry

Crossref · 10.3390/make8070216

Cites

46 of 46 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Citations

Cites

Research works printed but not linked: 5

  1. IEEE Global Initiative on Ethics of Autonomous and Intelligent Systems (2019). Ethically Aligned Design: A Vision for Prioritizing Human Well-Being with Autonomous and Intelligent Systems, IEEE Standards Association.
  2. Natali, C. (2023). Per Aspera ad Astra, or Flourishing via Friction: Stimulating Cognitive Activation by Design through Frictional Decision Support Systems. CHItaly-DC 2023 CHItaly 2023 Doctoral Consortium CHItaly 2023 Proceedings of the Doctoral Consortium of the 15th Biannual Conference of the Italian SIGCHI Chapter (CHItaly 2023), CEUR-WS.
  3. Norman, D.A. (2011). Living with Complexity, MIT Press.
  4. Nicora, G., Tito, A.L., Donatelli, A., Callea, G., Biasibetti, C., Galli, M.V., Comotto, F., Bortolotto, C., Perlini, S., and Preda, L. (2021, January 29). ALFABETO: Supporting COVID-19 hospital admissions with Bayesian Networks. Proceedings of the Workshop on Towards Smarter Health Care: Can Artificial Intelligence Help? co-located with 20th International Conference of the Italian Association for Artificial Intelligence (AIxIA2021), Online Event.
  5. Moens, M.F., Huang, X., Specia, L., and Yih, S.W.T. (2021). Contrastive Explanations for Model Interpretability. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics.

Metadata

Authors
Pe, S., Bergomi, L., Nicora, G., Simonelli, C. A., Kour, P., Diaz, E., Alendal, G., Hernáiz Ferrer, A. I., Corso, V., Bortolotto, C., Zuccaro, V., Salinaro, F., Preda, L., & Parimbelli, E.
Affiliations
  • University of Pavia (IT)
  • University of Bergen (NO)
  • Department of Global Public Health and Primary Care, Faculty of Medicine, University of Bergen, 5009 Bergen, Norway
  • Department of Radiology, IRCCS Policlinic San Matteo Foundation, 27100 Pavia, Italy
  • University of Ottawa (CA)
Corresponding author
  • Pe, Samuele
  • Parimbelli, Enea
Venue
Machine Learning and Knowledge Extraction
Publisher
MDPI AG
Published
2026-07-22
Volume
8
Issue
7
Pages
216
ISSN
2504-4990 (ISSN-L)
OpenAlex
W7170090355
Cited by
0
References
42
FWCI
0.00
Type
journal article
Language
en
Open access
Locations
  • Machine Learning and Knowledge Extraction (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
Italian Ministry of Research (PNC0000007)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
Keywords
clinical decision support, human-AI interaction, cognitive friction, explainable AI, automation bias, algorithmic aversion, overreliance on AI, diagnostic accuracy, medical residents, interaction design, contrastive reasoning, professional responsibility

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.