EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Refining biomarker-based clustering of cardiovascular inflammatory phenotypes in HIV using Recursive Feature Addition: A comparative evaluation approach

Rachel Mac Cann iD, Dana Alalwan, Gurvin Saini, Alejandro Abner Garcia Leon, Neeltje A Kootstra, Padraig McGettrick, Aoife G Cotter, Alan Winston iD, Peter Reiss iD, Caroline Sabin iD, Patrick W Mallon, UPBEAT-CAD, AIID and COBRA cohorts

PLOS Computational Biology · 27.04.2026 · 22 (4) · e1014209

DOI: 10.1371/journal.pcbi.1014209 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS Computational Biology, online erschienen am 27.04.2026. Verfasst von Rachel Mac Cann und 11 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, University College Dublin, Belfield, Dublin, Ireland. Hauptthemen laut MEDLINE: Biomarkers, HIV Infections, Cardiovascular Diseases, Inflammation. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Health Research Board, Wellcome Trust, British HIV Association.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

People living with HIV remain at elevated risk for a number of non-communicable diseases, including cardiovascular disease (CVD), driven in part by chronic inflammation. While prior studies have identified inflammatory biomarker patterns linked to CVD in people with HIV, it remains unclear which combinations of biomarkers most effectively predict clinical outcomes. We aimed to develop and evaluate a framework for refining biomarker-based clustering approaches to better capture inflammatory patterns associated with a cardiovascular phenotype (CVP) in people with HIV.

Methods

We developed and evaluated three recursive feature addition (RFA) models to enhance biomarker-driven clustering of people with and without HIV. Using a 24-marker initial panel of biomarkers chosen for their links to clinical CVP in people with HIV, we compared three models for selective inclusion of 31 additional, exploratory biomarkers: (1) a stepwise additive model evaluating biomarkers cumulatively based on biological relevance; (2) a stepwise additive model evaluating biomarkers individually; and (3) a greedy forward-backward selection model. Each model was assessed using principal component analysis (PCA), cluster stability, biological coherence and association with a CVP and 10-year Atherosclerotic Cardiovascular Disease (ASCVD) risk.

Results

All three RFA models generated three, biomarker-derived clusters. Post RFA cluster biomarker composition, model stability and clinical associations of these clusters differed across models. The individual additive model (Model 2) produced the most distinct separation of inflammatory profiles, incorporating 11 additional biomarkers, including, GDF-15, IFN-λ2 and Thrombopoietin). In this model, Cluster 3 was characterised by heightened innate and adaptive immune activation, the highest CVP prevalence (11%) and the strongest association with CVP (adjusted odds ratio (aOR) 2.3, 95% CI 1.04–5.09).

Conclusion

We demonstrate that an RFA framework using a stepwise, additive model evaluating biomarkers individually to enhance clustering profiles provides optimal unsupervised clustering of exploratory biomarkers to reveal additional associations between inflammatory patterns and CVP in people with and without HIV.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BiomarkersHIV InfectionsCardiovascular DiseasesInflammationHumansClustering AlgorithmsCluster AnalysisPhenotypeFemaleComputational BiologyMalePrincipal Component Analysis

Substanzen

Biomarkers

Autor:innen und Institutionen

  • School of Medicine, University College Dublin, Belfield, Dublin, Ireland.
  • Department of Infectious Diseases, St Vincent's University Hospital, Elm Park, Dublin, Ireland.
  • Centre for Experimental Pathogen Host Research (CEPHR), University College Dublin, Belfield, Dublin, Ireland.
  • Amsterdam Institute for Immunology and Infectious Diseases, Amsterdam, The Netherlands.
  • Department of Experimental Immunology, Amsterdam University Medical Centers, University of Amsterdam, Amsterdam, The Netherlands.
  • Department of Infectious Diseases, Mater Misericordiae University Hospital, Dublin, Ireland.

ORCID-Profile: Rachel Mac Cann, Alan Winston, Peter Reiss, Caroline Sabin

Förderung

  • Health Research Board
  • Wellcome Trust
  • British HIV Association
  • FP7 Coordination of Research Activities

Zitieren

APA

Mac Cann, R., Alalwan, D., Saini, G., Garcia Leon, A. A., Kootstra, N. A., McGettrick, P., Cotter, A. G., Winston, A., Reiss, P., Sabin, C., Mallon, P. W., & UPBEAT-CAD, AIID and COBRA cohorts (2026). Refining biomarker-based clustering of cardiovascular inflammatory phenotypes in HIV using Recursive Feature Addition: A comparative evaluation approach. PLOS Computational Biology, 22(4), e1014209. https://doi.org/10.1371/journal.pcbi.1014209

Vancouver

Mac Cann R, Alalwan D, Saini G, Garcia Leon AA, Kootstra NA, McGettrick P, et al. Refining biomarker-based clustering of cardiovascular inflammatory phenotypes in HIV using Recursive Feature Addition: A comparative evaluation approach. PLOS Computational Biology. 2026;22(4):e1014209. doi:10.1371/journal.pcbi.1014209

BibTeX
@article{MacCann2026,
  author = {Mac Cann, Rachel and Alalwan, Dana and Saini, Gurvin and Garcia Leon, Alejandro Abner and Kootstra, Neeltje A and McGettrick, Padraig and Cotter, Aoife G and Winston, Alan and Reiss, Peter and Sabin, Caroline and Mallon, Patrick W and UPBEAT-CAD, AIID and COBRA cohorts, UPBEAT-CAD, AIID and COBRA cohorts},
  title = {Refining biomarker-based clustering of cardiovascular inflammatory phenotypes in HIV using Recursive Feature Addition: A comparative evaluation approach},
  journal = {PLOS Computational Biology},
  year = {2026},
  volume = {22},
  number = {4},
  pages = {e1014209},
  doi = {10.1371/journal.pcbi.1014209}
}
Kostenlos starten →