Cluster analysis of angiotensin biomarkers to identify antihypertensive drug treatment in population studies.
Aldosterone
Angiotensin
Antihypertensive drugs
Cluster analysis
Lasso regression
CHRIS study
Journal
BMC medical research methodology
ISSN: 1471-2288
Titre abrégé: BMC Med Res Methodol
Pays: England
ID NLM: 100968545
Informations de publication
Date de publication:
27 05 2023
27 05 2023
Historique:
received:
20
01
2023
accepted:
23
04
2023
medline:
29
5
2023
pubmed:
28
5
2023
entrez:
27
5
2023
Statut:
epublish
Résumé
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. 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. 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 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.
Sections du résumé
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
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.
Identifiants
pubmed: 37245005
doi: 10.1186/s12874-023-01930-8
pii: 10.1186/s12874-023-01930-8
pmc: PMC10224304
doi:
Substances chimiques
Antihypertensive Agents
0
Angiotensins
0
Angiotensin-Converting Enzyme Inhibitors
0
Angiotensin Receptor Antagonists
0
Biomarkers
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
131Informations de copyright
© 2023. The Author(s).
Références
J Transl Med. 2015 Nov 05;13:348
pubmed: 26541195
J Stat Softw. 2010;33(1):1-22
pubmed: 20808728
J Hypertens. 2006 Feb;24(2):243-56
pubmed: 16508564
J Clin Epidemiol. 1996 Dec;49(12):1447-52
pubmed: 8970496
Hum Genet. 2017 Jun;136(6):743-757
pubmed: 28374192
Hypertension. 2022 Jan;79(1):12-23
pubmed: 34739765
Eur Heart J. 2018 Sep 1;39(33):3021-3104
pubmed: 30165516
Am J Kidney Dis. 2018 Dec;72(6):873-884
pubmed: 30201547
Psychol Bull. 1968 Oct;70(4):213-20
pubmed: 19673146
JAMA. 2017 Jan 10;317(2):165-182
pubmed: 28097354
J Clin Epidemiol. 2001 May;54(5):482-7
pubmed: 11337211
Int J Prev Med. 2013 Sep;4(9):1025-9
pubmed: 24130943
J Transl Med. 2020 Apr 1;18(1):150
pubmed: 32238168
Can J Cardiol. 2006 May 15;22(7):553-5
pubmed: 16755308
Nat Biotechnol. 2021 Jun;39(6):705-716
pubmed: 33361824
J Clin Epidemiol. 2014 Aug;67(8):921-31
pubmed: 24794575
Am J Hypertens. 1999 May;12(5):451-9
pubmed: 10342782
Hypertension. 2020 Jan;75(1):163-172
pubmed: 31760886
J Hypertens. 2018 Apr;36(4):939-946
pubmed: 29303829
Nephron Clin Pract. 2013;123(1-2):102-11
pubmed: 23797027