VeriDx：以疾病为中心的验证赢得诊断权
VeriDx: Earning the Right to Diagnose with Disease-Centric Verification
- Heidelberg University（海德堡大学）
- University of International Business and Economics（对外经济贸易大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对医学大语言模型评估忽视推理过程义务的问题，提出以疾病为中心的VeriDx验证框架，通过跟踪假设满足状态暴露诊断错误，实验表明错误多为早期承诺的破坏。
AI中文摘要：
正确的诊断仍可能因错误的原因而得出。在临床推理中，每个疾病假设都会产生义务：必须检查关键证据，必须排除替代方案，必须解决矛盾，必须考虑有用的检验，并且必须证明结论的合理性。当前对医学大语言模型的评估大多关注最终答案、局部步骤或孤立事实，因此忽略了这些由假设引发的承诺。我们引入了VeriDx，一个以疾病为中心的验证框架，将自由形式的诊断推理与结构化的疾病档案联系起来。VeriDx跟踪每个假设是否满足、未解决或违反了其临床义务，从而暴露诸如缺失关键检验、未解决的鉴别诊断、被忽略的矛盾、无根据的主张和过早结束等失败。我们使用指南衍生的疾病档案和专家标注的纵向病例，针对复杂的呼吸系统诊断实例化了VeriDx。我们的结果表明，许多诊断错误并非孤立的失误，而是推理过程中早期做出的被打破的承诺。
英文摘要：
A correct diagnosis can still be reached for the wrong reasons. In clinical reasoning, every disease hypothesis creates obligations: key evidence must be checked, alternatives must be ruled out, contradictions must be resolved, useful tests must be considered, and closure must be justified. Current evaluations of medical LLMs mostly focus on final answers, local steps, or isolated facts, and therefore miss these hypothesis-induced commitments. We introduce \textbf{VeriDx}, a disease-centric verification framework that links free-form diagnostic reasoning to structured disease profiles. VeriDx tracks whether each hypothesis is satisfied, unresolved, or violated its clinical obligations, exposing failures such as missing critical tests, unresolved differentials, ignored contradictions, unsupported claims, and premature closure. We instantiate VeriDx for complex respiratory diagnosis using guideline-derived disease profiles and expert-annotated longitudinal cases. Our results show that many diagnostic errors are not isolated mistakes, but broken commitments made earlier in the reasoning process.
