Risk-Calibrated Patient-Facing AI Safety Cards: A UI/UX Design Framework for Rubric-Based Medical Risk Communication
DOI:
https://doi.org/10.51903/ijgd.v3i2.3696Keywords:
patient-facing AI, medical large language models, risk communication, safety card, explainable AI, healthcare UXAbstract
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.References
Agency for Healthcare Research and Quality. (2015). Health literacy universal precautions toolkit (2nd ed.). U.S. Department of Health and Human Services.
American Medical Association. (2016). Code of medical ethics. American Medical Association.
Arora, R. K., Wei, J., Hicks, R. S., Bowman, P., Quinonero-Candela, J., Tsimpourlas, F., Sharman, M., Shah, M., Vallone, A., Beutel, A., Heidecke, J., & Singhal, K. (2025). HealthBench: Evaluating large language models towards improved human health. arXiv. https://arxiv.org/abs/2505.08775
Beauchamp, T. L., & Childress, J. F. (2019). Principles of biomedical ethics (8th ed.). Oxford University Press.
Bickmore, T. W., Pfeifer, L. M., & Jack, B. W. (2009). Taking the time to care: Empowering low health literacy hospital patients with virtual nurse agents. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 1265-1274. https://doi.org/10.1145/1518701.1518891
Carayon, P., Xie, A., & Kianfar, S. (2014). Human factors and ergonomics as a patient safety practice. BMJ Quality & Safety, 23(3), 196-205. https://doi.org/10.1136/bmjqs-2013-001812
Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv. https://arxiv.org/abs/1702.08608
Ehsan, U., Liao, Q. V., Muller, M., Riedl, M. O., & Weisz, J. D. (2021). Expanding explainability: Towards social transparency in AI systems. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, 1-19. https://doi.org/10.1145/3411764.3445188
Gunning, D., & Aha, D. (2019). DARPA's explainable artificial intelligence (XAI) program. AI Magazine, 40(2), 44-58. https://doi.org/10.1609/aimag.v40i2.2850
Han, T., Kumar, A., Agarwal, C., & Lakkaraju, H. (2024). MedSafetyBench: Evaluating and improving the medical safety of large language models. arXiv. https://arxiv.org/abs/2403.03744
Jason Kuhn, Yushan Chen, & Evelyn Chan. (2024). AI-Driven Mobile UI Pattern Recognition and Design Topic Mining on RICO: Semantic Clustering and Screenshot-Based Topic Classification. Journal of Advanced Computing Systems , 4(5), 67-83. https://doi.org/10.69987/JACS.2024.40506
Kaur, H., Nori, H., Jenkins, S., Caruana, R., Wallach, H., & Wortman Vaughan, J. (2020). Interpreting interpretability: Understanding data scientists' use of interpretability tools for machine learning. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 1-14. https://doi.org/10.1145/3313831.3376219
Kutner, M., Greenberg, E., Jin, Y., & Paulsen, C. (2006). The health literacy of America's adults: Results from the 2003 National Assessment of Adult Literacy. National Center for Education Statistics.
Liao, Q. V., Gruen, D., & Miller, S. (2020). Questioning the AI: Informing design practices for explainable AI user experiences. Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, 1-15. https://doi.org/10.1145/3313831.3376590
Mayer, R. E. (2009). Multimedia learning (2nd ed.). Cambridge University Press.
Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1-38. https://doi.org/10.1016/j.artint.2018.07.007
Norman, D. A. (2013). The design of everyday things (Rev. ed.). Basic Books.
Nutbeam, D. (2000). Health literacy as a public health goal: A challenge for contemporary health education and communication strategies. Health Promotion International, 15(3), 259-267. https://doi.org/10.1093/heapro/15.3.259
Rottger, P., Kirk, H. R., Vidgen, B., Attanasio, G., Bianchi, F., & Hovy, D. (2024). XSTest: A test suite for identifying exaggerated safety behaviours in large language models. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 5377-5400.
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., Payne, P., Seneviratne, M., Gamble, P., Kelly, C., Scharli, N., Chowdhery, A., Mansfield, P., Demner-Fushman, D., Aguera y Arcas, B., ... Natarajan, V. (2023). Large language models encode clinical knowledge. Nature, 620, 172-180. https://doi.org/10.1038/s41586-023-06291-2
Singhal, K., Tu, T., Gottweis, J., Sayres, R., Wulczyn, E., Amin, M., Hou, L., Clark, K., Pfohl, S., Cole-Lewis, H., Neal, D., Schaekermann, M., Wang, A., Mahmoud, M., McDermott, M., Freyberg, J., Liu, R., Kornblith, S., Fleet, D., ... Natarajan, V. (2024). Toward expert-level medical question answering with large language models. Nature Medicine, 30, 943-950. https://doi.org/10.1038/s41591-024-02817-8
Slovic, P. (1987). Perception of risk. Science, 236(4799), 280-285. https://doi.org/10.1126/science.3563507
Sokol, K., & Flach, P. (2020). Explainability fact sheets: A framework for systematic assessment of explainable approaches. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 56-67. https://doi.org/10.1145/3351095.3372870
Tufte, E. R. (2001). The visual display of quantitative information (2nd ed.). Graphics Press.
Ware, C. (2013). Information visualization: Perception for design (3rd ed.). Morgan Kaufmann.
World Wide Web Consortium. (2023). Web content accessibility guidelines (WCAG) 2.2. W3C Recommendation.
Yushan Chen, & Evelyn Chan. (2023). Multimodal UI Representation Learning: Ablation of Screenshot, Wireframe, and View-Hierarchy Proxies on an Uploaded 168-Screen Dataset. Journal of Advanced Computing Systems , 3(1), 1-15. https://doi.org/10.69987/JACS.2023.30101
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Binghua Zhou, Chenyu Li, Lily Liu
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
5.png)
