CertifiedData.io

This page is a synthetic dataset in the CertifiedData AI Artifact Registry — a public index of synthetic datasets, AI models, and certified AI artifacts with cryptographic provenance records. This entry has been registered and its SHA-256 fingerprint recorded. Synthetic data certification has not yet been issued. Once certified, an Ed25519 signature is generated and permanently linked to this record, enabling independent verification. It is categorized under healthcare.

Uncertifieddatasethealthcare

Synthetic EHR Discharge Summary v1

Certified synthetic EHR discharge summary dataset for readmission prediction model training and care pathway analysis.

Hash Algorithm
SHA256
Algorithm
CTGAN
Rows
78,000
Columns
24
Verification count4
Last verifiedApr 10, 2026

Artifact record

Artifact Hash
sha256:6990444286e19b4f1bd5655104174e15e4a4d0d67543e89b0c73573282a931ba
Certificate ID
Not yet certified
Issuer
CertifiedData.io
Schema Version
1.0
File Format
CSV
Use Case
ehr-discharge-analytics
Registered
April 1, 2026

Description

Synthetic EHR Discharge Summary v1 is a synthetic tabular dataset generated with CTGAN and certified by CertifiedData.io for AI testing, model evaluation, and synthetic data workflows.

Machine-readable record

Canonical JSON summary of this artifact for agents, systems, and developers. The certificate_id is the stable reference for verification via POST /api/verify.

Machine-readable summary (for agents and systems)

{
  "term": "Synthetic EHR Discharge Summary v1",
  "slug": "synthetic-ehr-discharge-summary-v1",
  "category": "registry",
  "artifact_type": "dataset",
  "certification_status": "unverified",
  "issuer": "CertifiedData.io",
  "artifact_hash": "sha256:6990444286e19b4f1bd5655104174e15e4a4d0d67543e89b0c73573282a931ba",
  "hash_algorithm": "SHA256",
  "schema_version": "1.0",
  "signing_algorithm": "Ed25519",
  "canonical_url": "https://certifieddata.io/registry/synthetic-ehr-discharge-summary-v1",
  "verification_auth_required": false,
  "openapi_spec": "https://certifieddata.io/openapi.json",
  "generation_algorithm": "CTGAN",
  "rows": 78000,
  "columns": 24,
  "industry": "healthcare"
}

Use cases for this synthetic dataset

This registered synthetic dataset can be used in standard workflows. Add certification to enable independent verification for compliance and audit use cases.

  • Discharge disposition prediction model training
  • 30-day readmission risk model development
  • Care pathway analytics and clinical decision support testing
  • EHR data pipeline validation and integration testing
  • IRB-safe clinical AI benchmarking

What this record proves

This listing has a recorded SHA-256 fingerprint. Certification adds:

  • +A machine-verifiable Ed25519 digital certificate
  • +SHA-256 fingerprint permanently linked to the certificate record
  • +Independent verification — no trust in CertifiedData required
  • +Persistent certificate ID for audit trail and governance documentation
  • +Stronger provenance chain for regulatory filings (GDPR, HIPAA, EU AI Act)

What is a synthetic dataset listing?

A synthetic dataset listing is a registered synthetic dataset in the CertifiedData registry with a recorded SHA-256 fingerprint. Once certified, it receives an Ed25519-signed certificate enabling independent verification by any party.

Learn about AI artifact certification →
Synthetic EHR Discharge Summary v1 — Synthetic Dataset | Healthcare | CertifiedData | CertifiedData