← Back to Skills Marketplace
unisound-llm

unisound-chief-complaint-diagnosis-inconsistent

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
76
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-chief-complaint-diagnosis-inconsistent
Description
门诊病历内涵质控:主诉和诊断部位不一致。给定门诊病历文本,调用内部医疗大模型,输出无缺陷或有缺陷及原因。
README (SKILL.md)

主诉和诊断部位不一致

概述

本 skill 仅针对**「主诉和诊断部位不一致」**这一条内涵质控规则。将字段解析、多步 LLM 推理与条件分支实现在本目录 scripts/emr_qc_impl.py 中;scripts/emr_qc.pyscripts/run.py 为入口,本 skill 可单独打包发布。调用 HiVoice MaaS 医疗大模型(OpenAI 兼容 chat/completions),输出 无缺陷有缺陷 + 原因。

数据安全、隐私与伦理声明

  • 最小必要原则:仅处理质控所必需的病历文本内容;不要求提供姓名、证件号等身份信息。
  • 严格脱敏:在发送至任何接口前,请确保病历文本已完成脱敏/去标识化处理。
  • 不做本地持久化:不将输入与中间结果写入本地持久化存储;本次调用结束即销毁
  • 医疗边界:本技能为辅助质控工具,不构成医疗诊断或治疗建议;最终结论请由执业医生审核。

输入格式

纯文本门诊病历(UTF-8),各字段用中文标签开头,例如:

主诉:发热3天
现病史:患者3天前无明显诱因出现发热,体温最高38.5℃...
既往史:高血压病史5年,规律服用氨氯地平,血压控制可...
体格检查:T 38.2℃,BP 150/90mmHg,双肺呼吸音清...
初步诊断:上呼吸道感染
处理意见:对症治疗

支持的字段标签:主诉现病史既往史体格检查辅助检查初步诊断/诊断处理意见/处理(中英文冒号均可)。

也支持通过 scripts/run.py 直接输入 pdf/doc/docx/xls/xlsx/csv/txt/json

快速开始

# 文本入口(在仓库 skills 根目录运行)
python3 doctor/emr-qc/chief-complaint-diagnosis-inconsistent/scripts/emr_qc.py \
  --input data/med-emr-qc/record.txt \
  --appkey \x3Cyour-appkey>

# 多格式入口
python3 doctor/emr-qc/chief-complaint-diagnosis-inconsistent/scripts/run.py \
  --input data/med-emr-qc/record.xlsx \
  --appkey \x3Cyour-appkey>

参数说明

scripts/emr_qc.py

  • --input PATH必填。门诊病历文本文件路径(UTF-8)。
  • --appkey STRING必填。调用内部医疗大模型的鉴权 key,由平台分配;不得写入仓库
  • --base URL:大模型 base URL(默认:https://maas-api.hivoice.cn/v1)。
  • --model STRING:模型名称(默认:u1-insuremed)。
  • --timeout SECONDS:HTTP 超时秒数;0 表示一直等待(默认:0)。
  • --output PATH:输出文件路径(默认:../runs/med-emr-qc/chief-complaint-diagnosis-inconsistent.txt)。

scripts/run.py 附加参数:

  • --input-type auto|pdf|doc|docx|xls|xlsx|csv|txt|json:输入类型;默认 auto
  • --sheet STRING:读取 Excel 时指定 sheet(可选)。
  • --encoding STRINGtxt/csv 编码(默认:utf-8)。
  • --save-prepared:保存预处理后的文本,便于调试。

输出约定

  • 输出为 UTF-8 文本:
    • 无缺陷:输出 无缺陷
    • 有缺陷:输出 有缺陷 + 换行 + 原因说明

依赖

自包含实现

质控与 LLM 调用逻辑均在 scripts/emr_qc_impl.py(与同 skill 一并发布)。

预处理(仅 run.py

scripts/run.py 依赖 _shared/doc-preprocesspreprocess.py),须位于仓库 skills/ 根下。

运行环境

  • Python 3.7+
  • 无需第三方包(仅标准库;多格式输入时可选 openpyxlpypdf

外部 API

  • 医疗大模型:https://maas-api.hivoice.cn/v1/chat/completions(POST,OpenAI 兼容格式)
Usage Guidance
Use this skill only if HiVoice MaaS is approved for your medical-record workflow. De-identify records before running it, protect the app key, verify the base URL, avoid `--save-prepared` unless you intentionally want a local debug copy, and make sure a qualified clinician reviews the result.
Capability Analysis
Type: OpenClaw Skill Name: unisound-chief-complaint-diagnosis-inconsistent Version: 1.0.0 The skill bundle is a legitimate tool for medical record quality control, specifically checking for anatomical inconsistencies between chief complaints and diagnoses. It functions by parsing medical text and making authorized API calls to a medical LLM (HiVoice MaaS at maas-api.hivoice.cn). The implementation in scripts/emr_qc_impl.py and scripts/run.py is transparent, lacks obfuscation, and contains no evidence of data exfiltration, unauthorized execution, or malicious prompt injection.
Capability Assessment
Purpose & Capability
The code and documentation align with the stated purpose: parse outpatient EMR fields and check one specific complaint-vs-diagnosis consistency rule. The main sensitivity is that medical text is sent to an external LLM provider.
Instruction Scope
The instructions are narrow and include privacy and physician-review warnings. Record text is inserted into LLM prompts, so crafted input could influence the model’s QC wording or result.
Install Mechanism
There is no install spec. The core text entry is included, but the multi-format runner imports a shared document-preprocessing module outside this skill’s file manifest.
Credentials
Network access and an app key are proportionate to the HiVoice MaaS integration. Users should verify the configured base URL and avoid exposing the app key through command history or logs.
Persistence & Privilege
There is no background service or privilege escalation. The skill writes a QC result file by default, and an explicitly documented --save-prepared flag can also persist preprocessed input text for debugging.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-chief-complaint-diagnosis-inconsistent
  3. After installation, invoke the skill by name or use /unisound-chief-complaint-diagnosis-inconsistent
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the skill for outpatient EMR quality control: checks if the chief complaint and diagnosis site are inconsistent. - Supports UTF-8 plain text input with field tags (e.g., 主诉, 现病史, 初步诊断) and multi-format files (pdf, doc, docx, xls, xlsx, csv, txt, json). - Leverages HiVoice MaaS medical LLM via OpenAI-compatible API; outputs “无缺陷” (No Defect) or “有缺陷” (Defect) plus reason. - Strictly enforces data privacy and security by requiring de-identified input, not storing data locally, and not requiring personal identifiers. - No third-party dependencies required for basic usage; optional packages for multi-format input. - Includes clear CLI usage instructions and parameters for both text and multi-format EMR input.
Metadata
Slug unisound-chief-complaint-diagnosis-inconsistent
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-chief-complaint-diagnosis-inconsistent?

门诊病历内涵质控:主诉和诊断部位不一致。给定门诊病历文本,调用内部医疗大模型,输出无缺陷或有缺陷及原因。 It is an AI Agent Skill for Claude Code / OpenClaw, with 76 downloads so far.

How do I install unisound-chief-complaint-diagnosis-inconsistent?

Run "/install unisound-chief-complaint-diagnosis-inconsistent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is unisound-chief-complaint-diagnosis-inconsistent free?

Yes, unisound-chief-complaint-diagnosis-inconsistent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does unisound-chief-complaint-diagnosis-inconsistent support?

unisound-chief-complaint-diagnosis-inconsistent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created unisound-chief-complaint-diagnosis-inconsistent?

It is built and maintained by Unisound-LLM (@unisound-llm); the current version is v1.0.0.

💬 Comments