All skills

healthcare-cdss-patterns

Official
by Api.AirforcePrepends a system promptAI & Agent Building000 uses202,700

临床决策支持系统(CDSS)开发模式。药物相互作用检查、剂量验证、临床评分(NEWS2、qSOFA)、警报严重性分类以及集成到电子病历工作流程中。

open-sourceclaude-codeai-agent-buildingaffaan-m
Share

What this skill does

When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.

---
name: healthcare-cdss-patterns
description: 临床决策支持系统(CDSS)开发模式。药物相互作用检查、剂量验证、临床评分(NEWS2、qSOFA)、警报严重性分类以及集成到电子病历工作流程中。
origin: Health1 Super Speciality Hospitals — contributed by Dr. Keyur Patel
version: "1.0.0"
---

# 医疗CDSS开发模式

构建可集成至EMR工作流的临床决策支持系统的模式。CDSS模块关乎患者安全——对假阴性零容忍。

## 适用场景

* 实现药物相互作用检查
* 构建剂量验证引擎
* 实现临床评分系统(NEWS2、qSOFA、APACHE、GCS)
* 设计异常临床值警报系统
* 构建带安全校验的用药医嘱录入
* 结合临床上下文解读检验结果

## 工作原理

CDSS引擎是一个**无副作用的纯函数库**。输入临床数据,输出警报。这使得它完全可测试。

三个核心模块:

1. **`checkInteractions(newDrug, currentMeds, allergies)`** — 检查新药物与现有用药及已知过敏的冲突。返回按严重程度排序的`InteractionAlert[]`。使用`DrugInteractionPair`数据模型。
2. **`validateDose(drug, dose, route, weight, age, renalFunction)`** — 根据体重、年龄和肾功能调整规则验证处方剂量。返回`DoseValidationResult`。
3. **`calculateNEWS2(vitals)`** — 基于`NEWS2Input`计算国家早期预警评分2。返回包含总分、风险等级和升级指导的`NEWS2Result`。

```
EMR UI
  ↓ (用户输入数据)
CDSS 引擎(纯函数,无副作用)
  ├── 药物相互作用检查器
  ├── 剂量验证器
  ├── 临床评分(NEWS2、qSOFA 等)
  └── 警报分类器
  ↓ (返回警报)
EMR UI(内联显示警报,严重时阻止操作)
```

### 药物相互作用检查

```typescript
interface DrugInteractionPair {
  drugA: string;           // generic name
  drugB: string;           // generic name
  severity: 'critical' | 'major' | 'minor';
  mechanism: string;
  clinicalEffect: string;
  recommendation: string;
}

function checkInteractions(
  newDrug: string,
  currentMedications: string[],
  allergyList: string[]
): InteractionAlert[] {
  if (!newDrug) return [];
  const alerts: InteractionAlert[] = [];
  for (const current of currentMedications) {
    const interaction = findInteraction(newDrug, current);
    if (interaction) {
      alerts.push({ severity: interaction.severity, pair: [newDrug, current],
        message: interaction.clinicalEffect, recommendation: interaction.recommendation });
    }
  }
  for (const allergy of allergyList) {
    if (isCrossReactive(newDrug, allergy)) {
      alerts.push({ severity: 'critical', pair: [newDrug, allergy],
        message: `Cross-reactivity with documented allergy: ${allergy}`,
        recommendation: 'Do not prescribe 

Use this skill

Per request

Add a "skill" field with the skill’s ID to your chat completion request. It is applied server-side before your prompt is sent — no extra calls.

{
  "model": "gpt-4o-mini",
  "skill": "imp-5af0ef53-8a01-4679-8e20-3232cd43f887",
  "messages": [{ "role": "user", "content": "…" }]
}
Always on — no field to send

Install the skill, enable it in your dashboard and (optionally) limit it to specific models. It then applies automatically to every matching request — with no "skill" field to send each time.

Set it up in your dashboard