← Back to Home

Synthetic Healthcare Datasets

Synthetic datasets for machine learning, research, and healthcare data experimentation. All datasets are privacy-safe and designed for reproducible analysis.

Generate from blueprints

Diabetes HbA1c Trial
diabetes

Synthetic type 2 diabetes trial with HbA1c as primary endpoint. Includes baseline demographics, visit schedule at weeks 0/12/24/52, and biomarker progression.

Oncology Survival Trial
oncology

Synthetic oncology trial with overall survival and progression-free survival endpoints. Designed for cancer treatment efficacy simulation.

Hospital Readmission
healthcare_utilization

Synthetic dataset for 30-day hospital readmission prediction. Includes admission characteristics, discharge disposition, and readmission outcomes.

Cardiology Outcomes
cardiology

Synthetic cardiovascular outcomes trial. Includes MACE (major adverse cardiovascular events), LDL, blood pressure, and cardiac biomarkers.

Survival Analysis
survival

Synthetic survival analysis dataset with time-to-event endpoints. Includes treatment groups, tumor staging, survival time, and event indicators for Kaplan-Meier and Cox regression.

Clinical Trial
clinical_trial

Generic synthetic clinical trial with baseline and outcome measures. Designed for treatment efficacy comparison and primary endpoint analysis.

EHR Longitudinal
ehr

Synthetic longitudinal electronic health record cohort. Includes encounter types, diagnosis codes, and lab values over time for temporal analysis.

Claims Utilization
healthcare_utilization

Synthetic healthcare claims and utilization dataset. Includes encounter types, admission diagnoses, ICD codes, and discharge dispositions for utilization analysis.

Metabolic Disease
metabolic

Synthetic metabolic disease cohort with HbA1c, LDL, and lab biomarkers. Designed for diabetes, dyslipidemia, and metabolic syndrome research.

Browse by Category