healthcare-cdss-patterns
OfficialClinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows.
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: Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows.
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 {
drUse this skill
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-faf5ead7-d0de-4ac7-b9c0-163629543696",
"messages": [{ "role": "user", "content": "…" }]
}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 dashboardMore skills
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
Create, view, edit, delete, search, move, or export Apple Notes via the memo CLI on macOS.
List, add, edit, complete, or delete Apple Reminders and reminder lists via remindctl.
Create, search, and manage Bear notes via grizzly CLI.
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Capture frames or clips from RTSP/ONVIF cameras.
Search, install, update, sync, or publish agent skills with the ClawHub CLI and registry.