A 2019 synthetic cardiovascular registry dataset developed by Radjamin, Farozan Erdian Talab for academic research training. It simulates anonymized patient-level data representing common clinical presentations in tertiary healthcare and cardiology practice. The dataset includes demographic variables, risk factors, laboratory parameters, imaging findings, diagnoses, treatments, hospitalization metrics, and clinical outcomes.
Use Cases
- Training in epidemiological analysis based on simulated patient-level cardiovascular data.
- Developing machine learning applications in cardiology based on diagnosis categories and clinical outcomes.
- Practicing predictive modeling based on cardiovascular risk factors and laboratory parameters.
- Conducting survival analysis based on treatment interventions and hospitalization metrics.
- Creating healthcare data visualizations based on demographic variables and imaging findings.
Strengths
- Dataset is explicitly designed for research training, statistical practice, and educational purposes.
- Covers multiple data categories including demographics, risk factors, lab parameters, imaging, diagnoses, treatments, and outcomes.
- Simulates data from tertiary healthcare and cardiology practice during a specific year (2019).
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count and file formats are unknown, which may limit suitability assessment.
Provenance
- Source
- Harvard Dataverse
- Collection Method
- Synthetically generated for training purposes.
- Time Range
- 2019
- Freshness
- Last updated 2026-05-22 13:26:38; freshness should be verified.
- Geography
- null