Biomarker Selection Criteria Scores Model 1 for HIV and Cardiovascular Disease

Biomarker selection criteria scores model 1 contains results from a study evaluating three recursive feature addition (RFA) models for clustering inflammatory biomarker patterns associated with cardiovascular disease in people with HIV. The dataset, authored by Rachel Mac Cann and shared on figshare, is a 5.5 KB Excel file last updated on 2026-04-27. It compares models using a 24-marker initial panel and 31 exploratory biomarkers to identify clusters linked to a cardiovascular phenotype.

Use Cases

• Evaluating recursive feature addition (RFA) frameworks for biomarker selection based on the described stepwise additive and greedy selection models.
• Analyzing inflammatory biomarker patterns associated with cardiovascular disease risk in people with HIV based on the 24-marker panel and exploratory biomarkers.
• Comparing cluster stability and biological coherence of biomarker-derived groups as described in the study results.
• Investigating associations between specific biomarkers (e.g., GDF-15, IFN-λ2, Thrombopoietin) and clinical outcomes like 10-year ASCVD risk.

Strengths

• Dataset is based on a structured study comparing three distinct RFA models (stepwise additive, individual additive, greedy forward-backward).
• Focuses on a specific 24-marker initial panel of biomarkers linked to cardiovascular phenotype in people with HIV.
• Results include specific metrics like adjusted odds ratios (aOR 2.3) for cluster associations with clinical outcomes.
• Released under a permissive CC-BY-4.0 license, facilitating reuse and redistribution.

Limitations

• Row count is unknown, which may limit suitability assessment for machine learning tasks.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (5.5 KB), indicating limited scope, likely containing model scores or summary results rather than raw patient-level data.

Provenance

Source

figshare

Collection Method

Likely derived from a research study applying recursive feature addition (RFA) models to biomarker data.

Time Range

null

Freshness

Last updated 2026-04-27 17:33:27; freshness should be verified.

Geography

null