Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Design Framework for Rubric-Based Medical Risk Communication
International Journal of Graphic Design · 29.10.2025 · 3 (2) · 365-380
DOI: 10.51903/ijgd.v3i2.3696 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Graphic Design, online erschienen am 29.10.2025. Verfasst von Binghua Zhou und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
Patient-facing medical AI systems can provide valuable health information; however, safety-sensitive queries require responses that establish clear boundaries while remaining informative, respectful, and actionable. This paper presents the Risk-Calibrated Safety Card, a UI/UX framework for communicating medical AI responses in high-risk situations. The framework transforms safety-sensitive outputs into a structured card containing five elements: risk level, explanation of why an unrestricted response may be unsafe, bounded safe information, professional-help guidance, and a bias-sensitive language note. The evaluation uses HealthBench, a benchmark of realistic health conversations with physician-authored rubrics, including the HealthBench Full evaluation split and robustness analyses on the Consensus and Hard subsets. Four response formats were compared: unstructured answer, refusal-only answer, refusal with explanation, and the proposed safety card. Across 4,597 HealthBench Full records, the safety card achieved the lowest rubric-based safety-communication risk score (1.27), the highest weighted positive-rubric coverage (0.664), and complete coverage of predefined card components (1.00). Refusal-only responses reduced unsafe personalization but showed limited helpfulness (1.55) and negligible positive-rubric coverage (0.001). Refusal with explanation improved boundary communication but lacked the structured presentation provided by the card. Although the safety card produced longer responses and a slightly lower readability score than the refusal-with-explanation condition (Flesch-Kincaid grade 14.39 vs. 14.72), the results suggest that structured safety cards can improve the visibility of risk, guidance, and support cues. These findings represent rubric-based interface evidence and should not be interpreted as validation of patient outcomes, clinical safety, or real-world deployment effectiveness.
Zitieren
APA
Zhou, B., Li, C., & Liu, L. (2025). Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Design Framework for Rubric-Based Medical Risk Communication. International Journal of Graphic Design, 3(2), 365-380. https://doi.org/10.51903/ijgd.v3i2.3696
Vancouver
Zhou B, Li C, Liu L. Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Design Framework for Rubric-Based Medical Risk Communication. International Journal of Graphic Design. 2025;3(2):365-380. doi:10.51903/ijgd.v3i2.3696
BibTeX
@article{Zhou2025,
author = {Zhou, Binghua and Li, Chenyu and Liu, Lily},
title = {Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Design Framework for Rubric-Based Medical Risk Communication},
journal = {International Journal of Graphic Design},
year = {2025},
volume = {3},
number = {2},
pages = {365--380},
doi = {10.51903/ijgd.v3i2.3696}
}
EUVIMED