Xpersona
U

unisound-diagnosis-sufficiency-review

CLAWHUB · Unverified

诊断依据充分性审核。输入结构化病案 record 与待审核诊断列表，输出诊断依据充分性审核结果。 Skill: unisound-diagnosis-sufficiency-review Owner: unisound-llm Summary: 诊断依据充分性审核。输入结构化病案 record 与待审核诊断列表，输出诊断依据充分性审核结果。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-07-16T02:35:55.572Z | user - 默认大模型名称由 u1-insuremed 更新为 u2-med。 - 移除 skill-card.md 介绍文件，不影响主要功能与使用说明。 - 其他功能和审核规则未发生变化。 v1.0.1 | 2026-05-28T11:14:04.293Z | user - Removed the file skill-card.md from the skill package. - Updated SKILL.md to reflect

62
Rank
84
Safety
994
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 994 downloads reported by the source. Last updated 10/11/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s1770nyybxj4gn0vk38n6wr6k584x8ea:unisound-diagnosis-sufficiency-review
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-unisound-llm-unisound-diagnosis-sufficiency-review/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

25,150 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: med-diagnosis-sufficiency-review
description: 诊断依据充分性审核。输入结构化病案 record 与待审核诊断列表，输出诊断依据充分性审核结果。
metadata:
  {
    "openclaw":
      {
        "emoji": "🩺"
      }
  }
---

# 诊断依据充分性审核

概述
----
给定结构化病案 `record` 和待审核诊断列表，本技能从诊断依据充分性规则库读取指南，核对病历文书证据，输出诊断依据是否充分。

本技能会：
- 从 `diagnosis_sufficiency_guidelines` 读取诊断依据充分性审核指南。
- 按诊断 `role` 区分主诊断和其他诊断，分别匹配指南适用范围。
- 优先按用户提供的 `diagnoses` 候选列表审核；未提供时，默认审核 `record.diagnosis.primaryDiagnosis` 和 `record.diagnosis.otherDiagnoses` 中的全部诊断。
- 调用 skill 内置的 `review_diagnosis_sufficiency_record` function 完成审核。
- 通过 `scripts/run.py` 提供统一 CLI 入口；不转发、不调用当前项目已有 API 服务，也不导入当前项目 `app.*` 模块。

数据安全、隐私与伦理声明
------------------------
- **最小必要原则**：仅处理审核所需的病案文书、诊断编码和诊断名称。
- **严格脱敏**：调用方应在传入前完成姓名、证件号、手机号、详细地址等可识别身份信息的脱敏。
- **不做本地持久化**：本技能不把请求体、中间结果或审核结果写入本地文件或数据库。
- **规则库服务用途**：规则库 API 仅用于读取诊断依据充分性审核指南。
- **模型调用说明**：默认使用内部医疗大模型生成依据充分性判断；鉴权 `appkey` 必须由调用方传入。如需完全离线规则回退，可传 `use_llm=false`。
- **医疗边界**：输出为医保编码审核辅助信息，不构成医疗诊断或治疗建议。

输入格式
--------
统一入口支持 `pdf/doc/docx/xls/xlsx/csv/txt/json`。JSON 可为结构化病案；其他格式会先预处理为一份完整病历文书。未显式传入 `diagnoses` 时，会自动审核结构化病案中的主诊断和全部其他诊断；普通病历文件需要通过参数传入待审核诊断列表。

```json
{
  "record": {
    "hospitalId": "988",
    "serialNum": "0001092574",
    "docs": [
      {
        "docName": "首次病程记录",
        "fileName": "首次病程记录",
        "docClassName": "首次病程记录",
        "content": "..."
      }
    ],
    "diagnosis": {
      "primaryDiagnosis": {"name": "2型糖尿病", "code": "E11.901"},
      "otherDiagnoses": []
    }
  },
  "diagnoses": [
    {"role": "primary", "code": "E11.901", "name": "2型糖尿病"}
  ],
  "appkey": "由平台分配的鉴权 key",
  "model": "",
  "use_llm": true
}
```

字段说明：
- `record`：**必填**。结构化病案 JSON。
- `diagnoses`：可选。待审核诊断候选数组；每项包含 `role`、`code`、`name`。
- `role`：`primary` 表示主诊断；其他值按其他诊断处理。
- `appkey`：**必填**。内部医疗大模型鉴权 key，由平台分配；调用时使用 Bearer 鉴权。
- `model`：可选。内部医疗大模型名称，默认 `u2-med`。
- `use_llm`：可选，默认 `true`。传 `false` 时不调用模型，仅使用本地回退审核逻辑。

审核规则
--------
- **候选优先**：只审核输入候选或病案首页中已有诊断，不自由生成候选列表外的诊断名称或编码。
- **证据优先**：依据充分必须来自病程、出院记录、检查检验、治疗经过等病历文书明确支持；不能把病案首页诊断列表本身当作充分临床依据。
- **主诊断边界**：主诊断应体现本次住院主要诊疗原因、主要资源消耗或核心治疗目标；仅有既往史、伴随疾病或偶然检出，不能自动视为主诊断依据充分。
- **其他诊断边界**：其他诊断应有明确并存、影响检查治疗、用药、护理、病情评估或资源消耗的证据；仅名称出现时需保守。
- **父类/子类边界**：父类诊断证据不能自动证明子类分型、并发症、部位、病因成立；缺少细分证据时输出 `待人工复核` 或 `依据不充分`。
- **同义词/简称边界**：仅当简称、同义词与候选诊断在医学内涵和编码归类上明确一致时可作为证据。
- **模糊保守**：疑似、待排、排除、术前诊断未证实、既往史、家族史、患者自述未被医生确认等，不应直接判为依据充分。
- **DRG/CC 边界**：严重合并症或并发症、一般合并症或并发症、无合并症或并发症的边界必须由病历明确支持；不能用模型常识或编码父类自动升级。

快速开始
--------

```bash
# JSON 结构化病历；未显式传入候选时审核主诊断和全部其他诊断
python3 doctor/icd-drg/diagnosis-sufficiency-review/scripts/run.py \
  --input doctor/icd-drg/diagnosis-sufficiency-review/example/10109_A5204171_1.json \
  --appkey <your-appkey> \
  --no-llm

# TXT/PDF 等普通病历文件；必须传入待审核诊断，可重复传入主诊断和其他诊断
python3 doctor/icd-drg/diagnosis-sufficiency-review/scripts/run.py \
  --input /path/to/record.txt \
  --appkey <your-appkey> \
  --diagnosis 'primary|E11.901|2型糖尿病' \
  --diagnosis 'other|I10.x00|高血压' \
  --save-prepared
```

参数说明
--------
- `--input PATH`：**必填**。结构化病案 JSON，或包含

_meta.json

{
  "ownerId": "kn7ft98qwhxyrgcy7b7rzdhrrd8366k6",
  "slug": "unisound-diagnosis-sufficiency-review",
  "version": "1.0.2",
  "publishedAt": 1784169355572
}

skill-card.md

## Description:

诊断依据充分性审核。输入结构化病案 record 与待审核诊断列表，输出诊断依据充分性审核结果。

This skill is ready for commercial/non-commercial use.

## Publisher:

[unisound-llm](https://clawhub.ai/user/unisound-llm)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and healthcare operations teams use this skill to review whether structured medical-record evidence sufficiently supports listed primary and other diagnoses for ICD/DRG audit workflows. It returns concise auxiliary review results and is not medical diagnosis or treatment advice.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Sensitive medical-record excerpts may be sent to guideline and model services.

Mitigation: Use only de-identified inputs, restrict outbound network access to approved endpoints, and prefer offline review with --no-llm when external transmission is not appropriate.

Risk: Bearer credentials may be sent to configurable network endpoints.

Mitigation: Provide credentials through managed secret handling and avoid arbitrary --base values unless the endpoint is approved.

Risk: Record-derived data can be written to disk when prepared-text or output-file options are used.

Mitigation: Avoid --save-prepared and output-file options unless the destination is access-controlled and retention is managed.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/unisound-llm/skills/unisound-diagnosis-sufficiency-review)
- [Publisher profile](https://clawhub.ai/user/unisound-llm)
- [Internal medical LLM API endpoint](https://maas-api.hivoice.cn/v1/chat/completions)

## Skill Output:

**Output Type(s):** [text, JSON, guidance]

**Output Format:** [JSON object with final_decision and reasoning fields]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [final_decision is one of 依据充分, 依据不充分, or 待人工复核; reasoning is concise and does not expose chain-of-thought.]

## Skill Version(s):

1.0.2 (source: evidence.release.version)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to unisound-diagnosis-sufficiency-review and adjacent AI workflows.