Healthcare AI faces an ethical dilemma between selective and equitable deployment, exacerbated by flawed performance metrics. These metrics inadequately capture real-world complexities and biases, leading to premature assertions of effectiveness. Improved evaluation practices, including continuous monitoring and silent evaluation periods, are crucial. To address these fundamental shortcomings, a paradigm shift in AI assessment is needed, prioritizing actual patient outcomes over conventional benchmarking.

中文翻译：

---

有缺陷的医疗保健人工智能指标中的道德辩论


医疗保健 AI 在选择性部署和公平部署之间面临道德困境，有缺陷的性能指标加剧了这一困境。这些指标没有充分捕捉现实世界的复杂性和偏见，导致过早地断言有效性。改进的评估实践，包括持续监测和静默评估期，至关重要。为了解决这些基本缺陷，需要转变 AI 评估的范式，优先考虑实际的患者结果而不是传统的基准测试。