healthcare-cdss-patterns

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: 臨床意思決定支援システム（CDSS）パターン、医学的推論、およびエビデンスベースの実装。
origin: Health1 Super Speciality Hospitals — contributed by Dr. Keyur Patel
version: "1.0.0"
---

# Healthcare CDSS Development Patterns

Patterns for building Clinical Decision Support Systems that integrate into EMR workflows. CDSS modules are patient safety critical — zero tolerance for false negatives.

## When to Use

- Implementing drug interaction checking
- Building dose validation engines
- Implementing clinical scoring systems (NEWS2, qSOFA, APACHE, GCS)
- Designing alert systems for abnormal clinical values
- Building medication order entry with safety checks
- Integrating lab result interpretation with clinical context

## How It Works

The CDSS engine is a **pure function library with zero side effects**. Input clinical data, output alerts. This makes it fully testable.

Three primary modules:

1. **`checkInteractions(newDrug, currentMeds, allergies)`** — Checks a new drug against current medications and known allergies. Returns severity-sorted `InteractionAlert[]`. Uses `DrugInteractionPair` data model.
2. **`validateDose(drug, dose, route, weight, age, renalFunction)`** — Validates a prescribed dose against weight-based, age-adjusted, and renal-adjusted rules. Returns `DoseValidationResult`.
3. **`calculateNEWS2(vitals)`** — National Early Warning Score 2 from `NEWS2Input`. Returns `NEWS2Result` with total score, risk level, and escalation guidance.

```
EMR UI
  ↓ (user enters data)
CDSS Engine (pure functions, no side effects)
  ├── Drug Interaction Checker
  ├── Dose Validator
  ├── Clinical Scoring (NEWS2, qSOFA, etc.)
  └── Alert Classifier
  ↓ (returns alerts)
EMR UI (displays alerts inline, blocks if critical)
```

### Drug Interaction Checking

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

Use this skill

{
  "model": "gpt-4o-mini",
  "skill": "imp-9b88c021-9451-461d-8d1b-4de85bb1ab3f",
  "messages": [{ "role": "user", "content": "…" }]
}

More skills