Related Experiment Video
Updated: Apr 29, 2026
08:51
Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts
Published on: September 20, 2024
2.1K
Refining biomarker-based clustering of cardiovascular inflammatory phenotypes in HIV using Recursive Feature
Rachel Mac Cann1,2,3, Dana Alalwan3, Gurvin Saini3
1School of Medicine, University College Dublin, Belfield, Dublin, Ireland.
Plos Computational Biology
|April 27, 2026
Summary
This study refines biomarker clustering to identify inflammatory patterns linked to cardiovascular disease (CVD) in people with HIV. An individual additive model best revealed these associations, improving CVD risk prediction.
Area of Science:
- Immunology
- Cardiovascular Science
- Biostatistics
Background:
- People with HIV have increased non-communicable disease risk, particularly cardiovascular disease (CVD), due to chronic inflammation.
- Existing biomarker patterns linked to CVD in people with HIV lack clarity on predictive combinations.
- A refined framework is needed to better capture inflammatory patterns associated with cardiovascular phenotype (CVP) in people with HIV.
Purpose of the Study:
- To develop and evaluate a recursive feature addition (RFA) framework for enhancing biomarker-driven clustering.
- To identify optimal biomarker combinations for predicting cardiovascular phenotype (CVP) in people with and without HIV.
- To improve understanding of inflammatory profiles associated with CVD risk in the context of HIV.
Main Methods:
- Three RFA models were developed and compared: cumulative biological relevance, individual biomarker evaluation, and greedy forward-backward selection.
- Models utilized an initial 24-marker panel and 31 exploratory biomarkers.
- Assessment included principal component analysis (PCA), cluster stability, biological coherence, and association with CVP and ASCVD risk.
Main Results:
- All RFA models yielded three distinct biomarker-derived clusters.
- The individual additive model (Model 2) showed the most effective separation of inflammatory profiles, incorporating 11 additional biomarkers.
- Cluster 3 in Model 2 exhibited heightened immune activation, highest CVP prevalence (11%), and strongest CVP association (aOR 2.3).
Conclusions:
- A recursive feature addition (RFA) framework, particularly using a stepwise, individual biomarker additive model, optimizes unsupervised clustering.
- This approach effectively reveals additional associations between inflammatory patterns and cardiovascular phenotype (CVP).
- The findings enhance the ability to identify inflammatory drivers of CVD in people with and without HIV.
