Repeated Decisions, Stable Care: Evaluating Medical AI Beyond Average Accuracy

This evidence synthesis examines longitudinal stability in repeat encounters and deterministic clinical tasks. It argues that the appropriate object of evaluation is the complete chain from incoming signal or prompt to evidence retrieval, model reasoning, confidence, and human action, not a model score in isolation. The review brings together the assigned studies with established work on uncertainty, robustness, provenance, and governance. Across these literatures, a common problem emerges: an error can be fluent, repeatable, and clinically consequential even when aggregate benchmark accuracy is high. The proposed framework separates evidence quality, model behavior, decision policy, and operational monitoring, then asks how each layer changes under distribution shift, adversarial pressure, or incomplete information. It recommends evaluation by slices and repeated trials, explicit reject and escalation policies, preservation of data and reasoning lineage, and prospective monitoring tied to defined actions. The result is a research agenda for systems that are efficient enough to use but also bounded enough to audit. No new experiment is claimed; the article develops a comparative conceptual model and identifies tests that would make future empirical claims more credible.

1. Hu, Saisai. "Research on Security Enhancement Methods for Adversarial Robust Large Language Model Intelligent Agents for Medical Decision-Making Tasks." *arXiv preprint arXiv:2605.08257* (2026).
2. Li, Yuanhao, et al. "DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs." *Proceedings of the AAAI Conference on Artificial Intelligence* 40.35 (2026): 29530-29537.
3. Sang, Yinghao. "Adaptive Quantization Strategies for Robust ML Inference Under Distribution Shift." *Proceedings of the 2026 5th International Conference on Cyber Security, Artificial Intelligence and Digital Economy* (2026): 362-368.
4. Su, Tongli, et al. "Cross-Modal Generative Framework for Signal Translation from Fetal-Maternal Electrocardiograms to Fetal Doppler Waveforms." *arXiv preprint arXiv:2607.08073* (2026).
5. Zhou, Yongxi, et al. "Accuracy, Stability, and Repeated-Run Reliability of Large Language Models on Deterministic Programming Tasks." *arXiv preprint arXiv:2606.00920* (2026).
6. Wiens, Jenna, et al. "Do No Harm: A Roadmap for Responsible Machine Learning for Health Care." *Nature Medicine*, vol. 25, 2019, pp. 1337-1340.
7. Rajkomar, Alvin, Jeffrey Dean, and Isaac Kohane. "Machine Learning in Medicine." *New England Journal of Medicine*, vol. 380, 2019, pp. 1347-1358.
8. World Health Organization. *Ethics and Governance of Artificial Intelligence for Health*. World Health Organization, 2021.
9. National Institute of Standards and Technology. *Artificial Intelligence Risk Management Framework (AI RMF 1.0)*. U.S. Department of Commerce, 2023.
10. Sculley, D., et al. "Hidden Technical Debt in Machine Learning Systems." *Advances in Neural Information Processing Systems*, vol. 28, 2015.
11. Hendrycks, Dan, and Thomas Dietterich. "Benchmarking Neural Network Robustness to Common Corruptions and Perturbations." *International Conference on Learning Representations*, 2019.
12. Goodfellow, Ian J., Jonathon Shlens, and Christian Szegedy. "Explaining and Harnessing Adversarial Examples." *International Conference on Learning Representations*, 2015.
13. Guo, Chuan, et al. "On Calibration of Modern Neural Networks." *Proceedings of the 34th International Conference on Machine Learning*, 2017, pp. 1321-1330.
14. Ovadia, Yaniv, et al. "Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty under Dataset Shift." *Advances in Neural Information Processing Systems*, vol. 32, 2019.
15. Geifman, Yonatan, and Ran El-Yaniv. "Selective Classification for Deep Neural Networks." *Advances in Neural Information Processing Systems*, vol. 30, 2017.