Explainability in context: calibrating appropriate trust and reliance in artificial intelligence
Journal of the American Medical Informatics Association · 01.08.2026 · 33 (8) · 1554-1563
DOI: 10.1093/jamia/ocag082 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 26.05.2026. Verfasst von Sharon E Davis und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States. Hauptthemen laut MEDLINE: Artificial Intelligence, Decision Support Systems, Clinical. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: AHRQ HHS, Agency for Healthcare Research and Quality (AHRQ).
Abstract (Originalsprache)
Background and Significance Predictive artificial intelligence (AI) promises to transform care delivery, enhance patient safety, and improve health outcomes. Realizing these benefits will require careful design, implementation, and monitoring strategies to avoid unintended consequences, including automation bias (i.e., erroneously favoring recommendations from automated systems). Automation bias is particularly concerning due to the variability of AI performance across time and populations, leading to predictions that may be variably incorrect, uncertain, or unfair. Approach We advocate for an expanded view of explainable AI that uses contextual information to help end users calibrate appropriate levels of trust and reliance. We propose multiple levels of contextualization—model, setting, subpopulation, and patient—that together provide insight for clinicians to evaluate the reliability of individual predictions. This includes information about historical and in-the-moment AI performance, algorithmic fairness, and prediction uncertainty. Conclusion We outline an approach to integrate context-based explanations into decision support workflows to aid clinician interpretation without adding cognitive burden.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN 37203, United States.
- Department of Anesthesiology, Center for Research and Innovation in Systems Safety, Vanderbilt University Medical Center, Nashville, TN 37232, United States.
ORCID-Profile: Sharon E Davis, Megan E Salwei
Förderung
- AHRQ HHS
- Agency for Healthcare Research and Quality (AHRQ)
Zitieren
APA
Davis, S. E., & Salwei, M. E. (2026). Explainability in context: calibrating appropriate trust and reliance in artificial intelligence. Journal of the American Medical Informatics Association, 33(8), 1554-1563. https://doi.org/10.1093/jamia/ocag082
Vancouver
Davis SE, Salwei ME. Explainability in context: calibrating appropriate trust and reliance in artificial intelligence. Journal of the American Medical Informatics Association. 2026;33(8):1554-1563. doi:10.1093/jamia/ocag082
BibTeX
@article{Davis2026,
author = {Davis, Sharon E and Salwei, Megan E},
title = {Explainability in context: calibrating appropriate trust and reliance in artificial intelligence},
journal = {Journal of the American Medical Informatics Association},
year = {2026},
volume = {33},
number = {8},
pages = {1554--1563},
doi = {10.1093/jamia/ocag082}
}
EUVIMED