healthsim-workspace

🥈Silver

HealthSim Workspace generates synthetic healthcare data through natural language conversation. It replaces Python libraries with AI skills, creating realistic patient records and care journeys for testing and training. It benefits operations teams by streamlining data generation for clinical, claims, and pharmacy workflows.

710Updated 2mo ago

Intermediate30min to implementautomation

Saves ~120 min per use

Quick InstallView Source

git clone https://github.com/mark64oswald/healthsim-workspace.git

Works with:

Claude

Overview

About This Skill

HealthSim Workspace generates clinically coherent synthetic healthcare data for testing, training, and development across multiple healthcare domains. The platform includes six integrated products—PatientSim for clinical/EMR data, MemberSim for claims and payer data, RxMemberSim for pharmacy data, TrialSim for clinical trial data, PopulationSim for demographics, and NetworkSim for provider networks. Users generate data through natural language conversation in local development mode (Claude Code with DuckDB) or managed cloud deployment. The specification-driven framework enables profile-driven and template-based generation, producing output in standards including FHIR R4, HL7v2, C-CDA, X12, NCPDP, CDISC SDTM/ADaM, and CSV formats.

How to Use

Start with the Hello HealthSim quick start guide for setup instructions. Choose your product (PatientSim, MemberSim, RxMemberSim, TrialSim, PopulationSim, or NetworkSim) and use the provided examples by product. Describe what data you need in natural language conversation, optionally specify output format (FHIR, HL7, X12, NCPDP, etc.), and execute. For large-scale generation, use the Profile Builder and Journey Builder templates.

Use Cases

Generate realistic patient records with clinical encounters, labs, and medications for EMR testing

Create synthetic claims data (professional, facility, pharmacy) for payer system validation

Build cohort-specific populations (diabetes, heart failure, oncology) with realistic care journeys

Generate clinical trial datasets with adverse events and efficacy endpoints in SDTM format

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/mark64oswald/healthsim-workspace

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Generate synthetic healthcare data for [COMPANY] in the [INDUSTRY] sector. Create 10 patient records with realistic care journeys, including diagnoses, treatments, and outcomes. Ensure the data includes [DATA] such as lab results, medication lists, and provider notes. Format the output as a structured JSON file.

Example Output

```markdown
# Synthetic Healthcare Data for [COMPANY]

## Patient Records

### Patient 1
- **Name**: John Doe
- **Age**: 45
- **Diagnosis**: Type 2 Diabetes
- **Treatment**: Metformin, Dietary Changes
- **Outcome**: Improved HbA1c levels

### Patient 2
- **Name**: Jane Smith
- **Age**: 32
- **Diagnosis**: Hypertension
- **Treatment**: Lisinopril, Exercise Regimen
- **Outcome**: Reduced blood pressure

### Patient 3
- **Name**: Robert Johnson
- **Age**: 60
- **Diagnosis**: Chronic Kidney Disease
- **Treatment**: Dialysis, Low-Protein Diet
- **Outcome**: Stabilized kidney function

## Lab Results
- **Patient 1**: HbA1c: 6.5%, Glucose: 120 mg/dL
- **Patient 2**: Blood Pressure: 120/80 mmHg
- **Patient 3**: Creatinine: 1.5 mg/dL

## Medication Lists
- **Patient 1**: Metformin 500mg twice daily
- **Patient 2**: Lisinopril 10mg daily
- **Patient 3**: Epoetin alfa as needed

## Provider Notes
- **Patient 1**: Adherent to treatment plan, follow-up in 3 months.
- **Patient 2**: Needs to increase exercise frequency.
- **Patient 3**: Monitor for signs of anemia.
```