← Back to Home

Documentation

Understand how Syntherx works and how to integrate synthetic data generation into your workflows.

Overview

Syntherx is a synthetic healthcare data platform that enables teams to generate realistic patient datasets on demand via API. It is designed for modeling, validation, and data enrichment without using real patient data.

Core Concepts

  • Blueprints — Predefined dataset templates (e.g., diabetes trials, oncology cohorts).
  • Synthetic Patients — Each dataset simulates patient-level records with structured variables.
  • Dataset Generation — Users specify blueprint + number of patients → system generates dataset.
  • Secure Delivery — Datasets are delivered via signed URLs for secure download.

How It Works

  1. Request sent to /datasets/generate
  2. Simulation engine generates dataset
  3. Dataset stored in S3
  4. Signed download URL returned

Use Cases

  • Clinical trial simulation
  • Machine learning model validation
  • Data augmentation / enrichment
  • Testing analytics pipelines

Why Syntherx

  • Privacy-first (no real patient data)
  • API-first integration
  • Scalable dataset generation
  • Designed for healthcare workflows