EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Samuele Pe, Laura Bergomi, Giovanna Nicora, Camilla A. Simonelli, Prabhjot Kour, Esperanza Diaz, Guttorm Alendal, Ana I. Hernáiz Ferrer, Valeria Corso, Chandra Bortolotto, Valentina Zuccaro, Francesco Salinaro und 2 weitere

Machine Learning and Knowledge Extraction · 22.07.2026 · 8 (7) · 216

DOI: 10.3390/make8070216 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 22.07.2026. Verfasst von Samuele Pe und 13 weiteren Autor:innen. Die Arbeit nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Italian Ministry of Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Italian Ministry of Research

Zitieren

APA

Pe, S., Bergomi, L., Nicora, G., Simonelli, C. A., Kour, P., Diaz, E., Alendal, G., Ferrer, A. I. H., Corso, V., Bortolotto, C., Zuccaro, V., Salinaro, F., Preda, L., & Parimbelli, E. (2026). Cognitive Friction in Clinical Decision Support: A Comparative Study of Judicial and Adjunct Human–AI Interaction Protocols. Machine Learning and Knowledge Extraction, 8(7), 216. https://doi.org/10.3390/make8070216

Vancouver

Pe S, Bergomi L, Nicora G, Simonelli CA, Kour P, Diaz E, et al. Cognitive Friction in Clinical Decision Support: A Comparative Study of Judicial and Adjunct Human–AI Interaction Protocols. Machine Learning and Knowledge Extraction. 2026;8(7):216. doi:10.3390/make8070216

BibTeX
@article{Pe2026,
  author = {Pe, Samuele and Bergomi, Laura and Nicora, Giovanna and Simonelli, Camilla A. and Kour, Prabhjot and Diaz, Esperanza and Alendal, Guttorm and Ferrer, Ana I. Hernáiz and Corso, Valeria and Bortolotto, Chandra and Zuccaro, Valentina and Salinaro, Francesco and Preda, Lorenzo and Parimbelli, Enea},
  title = {Cognitive Friction in Clinical Decision Support: A Comparative Study of Judicial and Adjunct Human–AI Interaction Protocols},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {7},
  pages = {216},
  doi = {10.3390/make8070216}
}
Kostenlos starten →