← Back to Skills Marketplace
unisound-llm

unisound-hypertension-missing-bp

by Unisound-LLM · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
55
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install unisound-hypertension-missing-bp
Description
门诊病历内涵质控:高血压未记录血压最高值。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)

高血压未记录血压最高值

概述

本 skill 仅针对**「高血压未记录血压最高值」**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/hypertension-missing-bp/scripts/emr_qc.py \
  --input data/med-emr-qc/record.txt \
  --appkey \x3Cyour-appkey>

# 多格式入口
python3 doctor/emr-qc/hypertension-missing-bp/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/hypertension-missing-bp.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
Install only if you are comfortable sending de-identified outpatient record text to the configured HiVoice MaaS endpoint. Keep the app key private, avoid changing the API base URL to an untrusted service, and do not use --save-prepared with identifiable records unless you intend to leave a local copy.
Capability Analysis
Type: OpenClaw Skill Name: unisound-hypertension-missing-bp Version: 1.0.0 The skill is a medical record quality control tool designed to detect missing blood pressure values in hypertension cases. It processes EMR text and interacts with a legitimate-looking medical LLM API (maas-api.hivoice.cn) using standard Python libraries (urllib). The code is well-structured, lacks obfuscation, and contains no indicators of data exfiltration, unauthorized execution, or malicious prompt injection.
Capability Assessment
Purpose & Capability
The stated purpose and code align: it parses user-provided outpatient record fields and asks a HiVoice-compatible medical LLM to return a defect/no-defect result. The noteworthy point is that clinical record text is sensitive.
Instruction Scope
The workflow is user-directed through --input and --appkey. The optional --save-prepared flag is disclosed, but users should notice it can persist preprocessed record text despite the general privacy wording.
Install Mechanism
There is no install spec and the core text path uses standard Python libraries, but the multi-format run.py path depends on an external _shared/doc-preprocess helper that is not included in the manifest.
Credentials
Use of a HiVoice MaaS endpoint and a bearer app key is proportionate to the described LLM integration, but the registry metadata does not declare a primary credential or capability tags.
Persistence & Privilege
No background service, self-persistence, or privilege escalation is shown. The skill writes the QC result to disk and can optionally save prepared input text when explicitly requested.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install unisound-hypertension-missing-bp
  3. After installation, invoke the skill by name or use /unisound-hypertension-missing-bp
  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 quality control of outpatient medical records regarding hypertension missing maximum blood pressure. - Implements rule: Detects if maximum blood pressure value is not recorded in hypertension cases. - Supports text input as well as PDF, Word, Excel, CSV, and JSON formats. - Calls HiVoice MaaS medical language model for defect detection, returning "无缺陷" or "有缺陷"+reason. - Ensures data privacy with no local persistence and requires de-identified input. - No third-party dependencies needed for base logic.
Metadata
Slug unisound-hypertension-missing-bp
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is unisound-hypertension-missing-bp?

门诊病历内涵质控:高血压未记录血压最高值。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 55 downloads so far.

How do I install unisound-hypertension-missing-bp?

Run "/install unisound-hypertension-missing-bp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is unisound-hypertension-missing-bp free?

Yes, unisound-hypertension-missing-bp is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does unisound-hypertension-missing-bp support?

unisound-hypertension-missing-bp is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created unisound-hypertension-missing-bp?

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

💬 Comments