Symptom Checker Triage

Analyzes symptom descriptions and suggests triage levels (Emergency / Urgent / Outpatient) based on red flag identification. Provides rationale and recommended next steps. For AI-assisted decision support only.

Quick Check

CODEBLOCK0

Audit-Ready Commands

CODEBLOCK1

When to Use

- Triage a patient symptom description to Emergency, Urgent, or Outpatient level
Identify red flag symptoms in a clinical or research context
Generate structured triage output for documentation or downstream processing

Workflow

1. Confirm the symptom description is provided as natural language text.
Validate that the request is a symptom triage task; stop early if not.
Run scripts/main.py with the symptom string or use --interactive mode.
Return a structured result with triage level, red flags, rationale, and disclaimer.
If execution fails or inputs are incomplete, switch to the Fallback Template below.

Fallback Template

If scripts/main.py fails or required fields are missing, respond with:

CODEBLOCK2

Stress-Case Output Checklist

For complex multi-constraint requests, always include these sections explicitly:

- Assumptions: symptom keywords matched, confidence threshold applied
Constraints: rule-based engine only; no differential diagnosis
Risks: false positives and false negatives are possible; always defer to clinician
Unresolved Items: ambiguous symptoms requiring clarification

CLI Usage

CODEBLOCK3

Output Format

CODEBLOCK4

Triage Levels

Level	Description	Action
emergency	Life-threatening red flags present	Call emergency services or go to ED immediately
urgent

Red Flag Categories

→ Full red flags reference: references/red_flags.md

Key categories: Cardiovascular, Respiratory, Neurological, Gastrointestinal, Trauma/Poisoning, Obstetric.

Disclaimer

Important: This tool provides AI-assisted triage suggestions only. It cannot replace professional medical diagnosis. If in doubt, seek medical care immediately. Call emergency services in life-threatening situations.

Input Validation

This skill accepts: natural language symptom descriptions in English or Chinese for triage level suggestion.

If the request does not involve symptom triage — for example, asking to diagnose a specific disease, prescribe medication, interpret lab results, or perform general medical Q&A — do not proceed. Instead respond:

"symptom-checker-triage is designed to suggest triage levels based on symptom red flags. Your request appears to be outside this scope. Please provide a symptom description, or use a more appropriate tool. This tool does not provide diagnoses or treatment recommendations."

Error Handling

- If no symptom description is provided, request it explicitly.
If the task goes outside documented scope (diagnosis, prescription), stop immediately.
If scripts/main.py fails, use the Fallback Template above.
Do not fabricate triage levels, red flag matches, or medical advice.

Output Requirements

Every final response must include:

1. Objective — what symptom set was triaged
Inputs Received — symptom description used
Assumptions — keyword matching applied, confidence threshold
Triage Result — level, red flags identified, rationale
Risks and Limits — AI-only, not a diagnosis, false positive/negative risk
Next Checks — always recommend professional medical evaluation

Dependencies

- Python 3.8+
No third-party dependencies (rule-based engine, standard library only)

症状检查分诊

分析症状描述，并根据危险信号识别建议分诊级别（急诊/紧急/门诊）。提供理由和推荐后续步骤。仅用于AI辅助决策支持。

快速检查

bash
python -m py_compile scripts/main.py

审计就绪命令

bash
python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py 胸痛、呼吸困难、持续30分钟
python scripts/main.py 头痛、发烧38.5度、呕吐 --verbose

使用场景

- 将患者症状描述分诊至急诊、紧急或门诊级别
在临床或研究环境中识别危险信号症状
生成结构化分诊输出，用于文档记录或下游处理

工作流程

1. 确认症状描述以自然语言文本形式提供。
验证请求是否为症状分诊任务；如果不是则提前停止。
使用症状字符串运行scripts/main.py，或使用--interactive模式。
返回包含分诊级别、危险信号、理由和免责声明的结构化结果。
如果执行失败或输入不完整，切换到下面的备用模板。

备用模板

如果scripts/main.py执行失败或缺少必填字段，请回复：

备用报告
───────────────────────────────────────
目标 : <分诊目标>
可用输入 : <提供的症状描述>
缺失输入 : <准确列出缺失内容>
部分结果 : <任何可以安全做出的分诊评估>
受阻步骤 : <无法完成的内容及原因>
免责声明 : 此为AI辅助建议，请寻求专业医疗护理。
后续步骤 : <完成所需的最少信息>
───────────────────────────────────────

压力测试输出检查清单

对于复杂的多约束请求，务必明确包含以下部分：

- 假设：症状关键词已匹配，置信度阈值已应用
约束：仅基于规则引擎；不提供鉴别诊断
风险：可能出现假阳性和假阴性；始终以临床医生意见为准
未解决事项：需要澄清的模糊症状

CLI使用

bash

直接输入症状

python scripts/main.py 胸痛，放射至左臂，出汗

交互模式

python scripts/main.py --interactive

详细输出

python scripts/main.py 头痛、发烧 --verbose

JSON输出

python scripts/main.py 腹痛，右下腹压痛 --json

输出格式

json
{
triage_level: emergency|urgent|outpatient,
confidence: 0.85,
red_flags: [胸痛, 呼吸困难],
reason: 胸痛伴呼吸困难可能提示心肌梗死或肺栓塞,
recommendation: 立即前往急诊科,
department: 急诊/心内科,
warning: 此为AI辅助建议，不能替代专业医疗诊断
}

分诊级别

级别	描述	行动
急诊	存在危及生命的危险信号	立即呼叫急救服务或前往急诊科
紧急

危险信号类别

→ 完整危险信号参考：references/red_flags.md

主要类别：心血管、呼吸系统、神经系统、消化系统、创伤/中毒、产科。

免责声明

重要提示：此工具仅提供AI辅助分诊建议。不能替代专业医疗诊断。如有疑问，请立即就医。在危及生命的情况下请呼叫急救服务。

输入验证

此技能接受：英文或中文的自然语言症状描述，用于分诊级别建议。

如果请求不涉及症状分诊——例如要求诊断特定疾病、开具处方、解读化验结果或进行一般性医疗问答——请勿继续。应回复：

symptom-checker-triage 旨在根据症状危险信号建议分诊级别。您的请求似乎超出此范围。请提供症状描述，或使用更合适的工具。此工具不提供诊断或治疗建议。

错误处理

- 如果未提供症状描述，明确要求提供。
如果任务超出文档范围（诊断、处方），立即停止。
如果scripts/main.py执行失败，使用上述备用模板。
不得编造分诊级别、危险信号匹配或医疗建议。

输出要求

每个最终回复必须包含：

1. 目标——对哪组症状进行了分诊
接收的输入——使用的症状描述
假设——已应用关键词匹配、置信度阈值
分诊结果——级别、识别的危险信号、理由
风险与限制——仅AI辅助，非诊断，假阳性/假阴性风险
后续检查——始终建议进行专业医疗评估

依赖项

- Python 3.8+
无第三方依赖（仅基于规则引擎，标准库）

symptom-checker-triage症状检查分诊