跳到正文

D009 问题与诊断归并

归并患者问题与诊断的多次记录,保留否定、疑似、既往状态和明确变化,形成具有来源依据的问题对象。

个人 Skill知识加工17 个文件浏览次数 0
开始使用

下载前阅读 SKILL.md 中的使用条件,并确认所用工具支持对应能力。

输入资料
Required: D006 context_resolution_manifest.json with overall_status=ready_for_domain_normalization; D006 contextualized_facts.jsonl; D006 state_transitions.jsonl when present. D009 reads only fact_type=condition facts. S… 阅读本节完整说明
交付内容
Each canonical problem contains:Read references/problem-semantics.md before changing disposition rules. 阅读本节完整说明
  1. 获取完整包,保留配套文件的目录结构。
  2. 按照原文准备所需工具、依赖与输入资料。
  3. 阅读对应使用步骤与输入输出说明,在自己的环境中验证结果。

使用提示摘自原文,配套文件保留来源版本;实际运行条件以各包说明为准。

正文

获取原文件

references/problem-semantics.md

Disposition meanings

  • active: supported as a current positive patient problem.
  • resolved: explicit evidence says the problem resolved.
  • inactive: explicit inactive status.
  • remission: explicit remission state.
  • recurrence: explicit recurrence state.
  • historical_known: positive patient history exists but current activity is not established.
  • uncertain: only suspected/possible/probable evidence remains unresolved.
  • refuted: the candidate problem was explicitly refuted or only negative/refuted evidence remains.
  • unknown: evidence conflicts or ordering is insufficient.

Historical wording never implies resolved. A later timestamp is useful only when the timestamp is trustworthy and the semantic state is explicit enough to compare.

include_in_active_problem_list is true only for active or recurrence.

CONTACT HAONAN

联系haonan

医疗 AI · 产品与独立开发

刘浩南

关注医疗 AI 从 demo 到真实落地,聚焦产品化、商业化与院内工作流效率提升。

12年医疗产研经验,大湾区头部医疗AI公司前产品总监,独立开发者

医疗 AI 产品化医疗 AI 商业化院内工作流效率
刘浩南的微信联系二维码
微信扫一扫,联系 haonan