Contingency Table: Hypertensive Patient Data for CVD Risk Prediction

Enrique Rodilla's dataset contains a contingency table from a retrospective study of 3,588 hypertensive patients followed for a mean of 8.3 years to predict new-onset cardiovascular disease. The 155-variable dataset was enriched using statistical measures, PCA, and LCA to train an XGBoost model. The data was last updated on 2026-05-21.

Use Cases

• Training machine learning models for CVD risk prediction based on clinical variables from hypertensive patients.
• Comparing the performance of AI-based risk models (like XGBoost) against traditional clinical scores (like SCORE2).
• Identifying key predictive clinical features, such as the number of antihypertensive drugs, for cardiovascular outcomes.

Strengths

• Contains data from 3,588 patients with a mean follow-up of 8.3 years, providing longitudinal clinical insight.
• The derived XGBoost model achieved 86% ROC AUC, 81% sensitivity, and 78% specificity, indicating predictive utility.
• Dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is from a single-center study, which may limit generalizability to other populations.

Provenance

Source

Enrique Rodilla via figshare.

Collection Method

Single-center retrospective study of consecutive hypertensive subjects.

Time Range

Mean follow-up period of 8.3 years (specific start/end years not provided).

Freshness

Last updated 2026-05-21 17:23:18; freshness should be verified.