Proteomic machine-learning signatures associated with carotid plaque: A population-based hypothesis-generating study
5 affiliations
- 1Department of Cardiology and Internal Medicine with Cardiac Intensive Care Unit, Medical University of Białystok, Białystok, Poland
- 2Faculty of Computer Science, University of Białystok, Białystok, Poland
- 3Department of Population Medicine and Lifestyle Diseases Prevention, Medical University of Białystok, Białystok, Poland
- 4Population Research Centre, Medical University of Białystok, Białystok, Poland
- 5Computing Centre, University of Białystok, Białystok, Poland
Abstract
Carotid plaque (CP) is a surrogate marker of cardiovascular disease, and high-risk morphology significantly increases the risk of stroke. The aim of this study was to develop advanced machine learning (ML) models to predict the presence of CP in the general population. The study involved 693 participants from the Polish Longitudinal University Study – Bialystok PLUS, a representative sample of the local population. The analysis used 460 OLINK protein biomarkers. The data were analysed using the BORUTA algorithm based on the random forest classifier method. We identified 42 significant biomarkers associated with CP, the most important of which were GDF-15, CDCP1, CHIT1, FLT3LG, CDH2 and CRTAC1. Interestingly, the top 6 biomarkers had a highly speculative or unresolved association with atherosclerosis. Next, we developed an ML-based CP fingerprint comprising 25 biomarkers, which showed good internal cross-validated discrimination in subjects aged 30–70 years. We also generated a network of interactions for the 42 biomarkers using STRING database modules, and performed a functional analysis to assess the biological significance of the interactions detected. These results are hypothesis-generating and require external, prospective validation to identify cause-and-effect relationships.
Related
- Age-Associated Plasma Protein Signatures and Proteomic Age Estimation by Data-Independent Acquisition Mass Spectrometry in a Russian Cross-Sectional Cohort
- Tissue-resolved transcriptomic and proteomic profiling reveals organ-specific molecular signatures associated with inter-animal variation in glycemic response to metformin in obese diabetic Mongolian gerbils
- Targeting the Gut Vascular Axis in Atherosclerosis: Probiotic and Phytoantioxidant Crosstalk as a Hypothesis-Generating Framework for Residual Cardiovascular Risk
- Does the mouth seed the small bowel? Mechanisms and hypothesis-generating framework via the oral–gut axis
- Subtype-Conditioned NRF2-KEAP1 Signaling in Breast Cancer: A Narrative Review and Hypothesis-Generating Framework from Chemoprevention to Therapy Resistance.
BibTeX
@article{szpakowicz2026proteomic,
title = {{Proteomic machine-learning signatures associated with carotid plaque: A population-based hypothesis-generating study}},
author = {Anna Szpakowicz and Wojciech Lesiński and Jakub K. Tuchliński and Urszula Roszkowska and Marlena Dubatówka and Zofia Stachurska and Marcin Kondraciuk and Witold R. Rudnicki and Karol A. Kamiński},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0358765},
url = {https://doi.org/10.1371/journal.pone.0358765},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Proteomic machine-learning signatures associated with carotid plaque: A population-based hypothesis-generating study
AU - Anna Szpakowicz
AU - Wojciech Lesiński
AU - Jakub K. Tuchliński
AU - Urszula Roszkowska
AU - Marlena Dubatówka
AU - Zofia Stachurska
AU - Marcin Kondraciuk
AU - Witold R. Rudnicki
AU - Karol A. Kamiński
PY - 2026
DA - 2026/09/24
JO - PLOS One
DO - 10.1371/journal.pone.0358765
UR - https://doi.org/10.1371/journal.pone.0358765
AB - Carotid plaque (CP) is a surrogate marker of cardiovascular disease, and high-risk morphology significantly increases the risk of stroke. The aim of this study was to develop advanced machine learning (ML) models to predict the presence of CP in the general population. The study involved 693 participants from the Polish Longitudinal University Study – Bialystok PLUS, a representative sample of the local population. The analysis used 460 OLINK protein biomarkers. The data were analysed using the BORUTA algorithm based on the random forest classifier method. We identified 42 significant biomarkers associated with CP, the most important of which were GDF-15, CDCP1, CHIT1, FLT3LG, CDH2 and CRTAC1. Interestingly, the top 6 biomarkers had a highly speculative or unresolved association with atherosclerosis. Next, we developed an ML-based CP fingerprint comprising 25 biomarkers, which showed good internal cross-validated discrimination in subjects aged 30–70 years. We also generated a network of interactions for the 42 biomarkers using STRING database modules, and performed a functional analysis to assess the biological significance of the interactions detected. These results are hypothesis-generating and require external, prospective validation to identify cause-and-effect relationships.
SN - 1932-6203
ER -