Cluster analysis of angiotensin biomarkers to identify antihypertensive drug treatment in population studies

BMC Medical Research Methodology · 14 authors, 9 centres

AI SUMMARY

FIDELITY 100%

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

This study used unsupervised machine learning to cluster participants based on blood biomarkers of the renin-angiotensin system.

Full summary

832 CHARS

THE ANALYSIS IDENTIFIED THREE CLUSTERS

one for individuals not on RAAS-targeting drugs, one for angiotensin type 1 receptor blocker (ARB) users, and one for angiotensin-converting enzyme inhibitor (ACEi) users. The ARB cluster had a weighted kappa of 74% and sensitivity of 73% for identifying users. The ACEi cluster had a weighted kappa of 81% and specificity of 90% but lower sensitivity of 55%. Additional analyses showed that clusters 2 and 3 (drug users) had higher frequencies of diabetes and cardiometabolic issues compared to cluster 1. Limitations include the cross-sectional design, potential unaccounted treatment non-adherence, and a sample size that prevented independent validation. The findings suggest RAAS biomarker clustering could be a viable tool to identify antihypertensive treatments in real-world settings.

STUDY TYPE

cohort

SPECIALTY

cardiology

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10224304

Cluster analysis of angiotensin biomarkers to identify antihypertensive drug treatment in population studies

BMC Medical Research Methodology

READ THE FULL PAPER

ABSTRACT

Abstract Background The recent progress in molecular biology generates an increasing interest in investigating molecular biomarkers as markers of response to treatments. The present work is motivated by a study, where the objective was to explore the potential of the molecular biomarkers of renin-angiotensin-aldosterone system (RAAS) to identify the undertaken antihypertensive treatments in the general population. Population-based studies offer an opportunity to assess the effectiveness of treatments in real-world scenarios. However, lack of quality documentation, especially when electronic health record linkage is unavailable, leads to inaccurate reporting and classification bias. Method We present a machine learning clustering technique to determine the potential of measured RAAS biomarkers for the identification of undertaken treatments in the general population. The biomarkers were simultaneously determined through a novel mass-spectrometry analysis in 800 participants of the Cooperative Health Research In South Tyrol (CHRIS) study with documented antihypertensive treatments. We assessed the agreement, sensitivity and specificity of the resulting clusters against known treatment types. Through the lasso penalized regression, we identified clinical characteristics associated with the biomarkers, accounting for the effects of cluster and treatment classifications. Results We identified three well-separated clusters: cluster 1 (n = 444) preferentially including individuals not receiving RAAS-targeting drugs; cluster 2 (n = 235) identifying angiotensin type 1 receptor blockers (ARB) users (weighted kappa κ w = 74%; sensitivity = 73%; specificity = 83%); and cluster 3 (n = 121) well discriminating angiotensin-converting enzyme inhibitors (ACEi) users (κ w = 81%; sensitivity = 55%; specificity = 90%). Individuals in clusters 2 and 3 had higher frequency of diabetes as well as higher fasting glucose and BMI levels. Age, sex and kidney function were strong predictors of the RAAS biomarkers independently of the cluster structure. Conclusions Unsupervised clustering of angiotensin-based biomarkers is a viable technique to identify individuals on specific antihypertensive treatments, pointing to a potential application of the biomarkers as useful clinical diagnostic tools even outside of a controlled clinical setting. Supplementary Information The online version contains supplementary material available at 10.1186/s12874-023-01930-8. Keywords: Angiotensin , Aldosterone, Antihypertensive drugs, Cluster analysis, Lasso regression, CHRIS study

CITATION EXPORT

Maeregu Woldeyes Arisido, Luisa Foco, Robin Shoemaker et al.. Cluster analysis of angiotensin biomarkers to identify antihypertensive drug treatment in population studies. BMC Medical Research Methodology. (2023). https://doi.org/10.1186/s12874-023-01930-8

AUTHORS

14 · 9 CENTRES

Maeregu Woldeyes Arisido, Luisa Foco, Robin Shoemaker, Roberto Melotti, Christian Delles, Martin Gögele, Stefano Barolo, Stephanie Baron, Michel Azizi, Anna F Dominiczak, Maria-Christina Zennaro, Peter P Pramstaller, Marko Poglitsch, Cristian Pattaro

1Institute for Biomedicine (affiliated to the University of Lübeck), Eurac Research, Via Volta 21, 39100 Bolzano, Italy
2Department of Dietetics and Human Nutrition, University of Kentucky, Lexington, USA
3School of Cardiovascular and Metabolic Health , University of Glasgow, Glasgow, UK
4Hospital of Schlanders/Silandro, Schlanders/Silandro, Italy
5National Institute of Health and Medical Research (Inserm), Paris, France
6Hypertension Department and DMU CARTE, AP-HP, Hôpital Européen Georges-Pompidou, Paris, France
7Attoquant Diagnostics, Vienna, Austria
8Health Data Science Center, Human Technopole, Viale Rita Levi Montalcini, 1, 20157 Milan, Italy
9Université Paris Cité, Paris, France