Machine learning for classification of hypertension subtypes using multi-omics: a multi-centre, retrospective, data-driven study.
Name:
Publisher version
View Source
Access full-text PDFOpen Access
View Source
Check access options
Check access options
Author
Reel, Parminder SReel, Smarti
van Kralingen, Josie C
Langton, Katharina
Lang, Katharina
Erlic, Zoran
Larsen, Casper K
Amar, Laurence
Pamporaki, Christina
Mulatero, Paolo
Blanchard, Anne
Kabat, Marek
Robertson, Stacy
MacKenzie, Scott M
Taylor, Angela E
Peitzsch, Mirko
Ceccato, Filippo
Scaroni, Carla
Reincke, Martin
Kroiss, Matthias
Dennedy, Michael C
Pecori, Alessio
Monticone, Silvia
Deinum, Jaap
Rossi, Gian Paolo
Lenzini, Livia
McClure, John D
Nind, Thomas
Riddell, Alexandra
Stell, Anthony
Cole, Christian
Sudano, Isabella
Prehn, Cornelia
Adamski, Jerzy
Gimenez-Roqueplo, Anne-Paule
Assié, Guillaume
Arlt, Wiebke
Beuschlein, Felix
Eisenhofer, Graeme
Davies, Eleanor
Zennaro, Maria-Christina
Jefferson, Emily
Publication date
2022-09-27Subject
Public health. Health statistics. Occupational health. Health educationDiseases & disorders of systemic, metabolic or environmental origin
Clinical pathology
Endocrinology
Pharmacology
Metadata
Show full item recordAbstract
Background: Arterial hypertension is a major cardiovascular risk factor. Identification of secondary hypertension in its various forms is key to preventing and targeting treatment of cardiovascular complications. Simplified diagnostic tests are urgently required to distinguish primary and secondary hypertension to address the current underdiagnosis of the latter. Methods: This study uses Machine Learning (ML) to classify subtypes of endocrine hypertension (EHT) in a large cohort of hypertensive patients using multidimensional omics analysis of plasma and urine samples. We measured 409 multi-omics (MOmics) features including plasma miRNAs (PmiRNA: 173), plasma catechol O-methylated metabolites (PMetas: 4), plasma steroids (PSteroids: 16), urinary steroid metabolites (USteroids: 27), and plasma small metabolites (PSmallMB: 189) in primary hypertension (PHT) patients, EHT patients with either primary aldosteronism (PA), pheochromocytoma/functional paraganglioma (PPGL) or Cushing syndrome (CS) and normotensive volunteers (NV). Biomarker discovery involved selection of disease combination, outlier handling, feature reduction, 8 ML classifiers, class balancing and consideration of different age- and sex-based scenarios. Classifications were evaluated using balanced accuracy, sensitivity, specificity, AUC, F1, and Kappa score. Findings: Complete clinical and biological datasets were generated from 307 subjects (PA=113, PPGL=88, CS=41 and PHT=112). The random forest classifier provided ∼92% balanced accuracy (∼11% improvement on the best mono-omics classifier), with 96% specificity and 0.95 AUC to distinguish one of the four conditions in multi-class ALL-ALL comparisons (PPGL vs PA vs CS vs PHT) on an unseen test set, using 57 MOmics features. For discrimination of EHT (PA + PPGL + CS) vs PHT, the simple logistic classifier achieved 0.96 AUC with 90% sensitivity, and ∼86% specificity, using 37 MOmics features. One PmiRNA (hsa-miR-15a-5p) and two PSmallMB (C9 and PC ae C38:1) features were found to be most discriminating for all disease combinations. Overall, the MOmics-based classifiers were able to provide better classification performance in comparison to mono-omics classifiers. Interpretation: We have developed a ML pipeline to distinguish different EHT subtypes from PHT using multi-omics data. This innovative approach to stratification is an advancement towards the development of a diagnostic tool for EHT patients, significantly increasing testing throughput and accelerating administration of appropriate treatment. Funding: European Union's Horizon 2020 Research and Innovation Programme under Grant Agreement No. 633983, Clinical Research Priority Program of the University of Zurich for the CRPP HYRENE (to Z.E. and F.B.), and Deutsche Forschungsgemeinschaft (CRC/Transregio 205/1).Citation
Reel PS, Reel S, van Kralingen JC, Langton K, Lang K, Erlic Z, Larsen CK, Amar L, Pamporaki C, Mulatero P, Blanchard A, Kabat M, Robertson S, MacKenzie SM, Taylor AE, Peitzsch M, Ceccato F, Scaroni C, Reincke M, Kroiss M, Dennedy MC, Pecori A, Monticone S, Deinum J, Rossi GP, Lenzini L, McClure JD, Nind T, Riddell A, Stell A, Cole C, Sudano I, Prehn C, Adamski J, Gimenez-Roqueplo AP, Assié G, Arlt W, Beuschlein F, Eisenhofer G, Davies E, Zennaro MC, Jefferson E. Machine learning for classification of hypertension subtypes using multi-omics: A multi-centre, retrospective, data-driven study. EBioMedicine. 2022 Oct;84:104276. doi: 10.1016/j.ebiom.2022.104276. Epub 2022 Sep 27Type
ArticleAdditional Links
http://www.sciencedirect.com/science/journal/23523964https://www.ncbi.nlm.nih.gov/pmc/journals/2749/
PMID
36179553Journal
EBioMedicinePublisher
Elsevierae974a485f413a2113503eed53cd6c53
10.1016/j.ebiom.2022.104276