Cargando…

Machine learning integration of multimodal data identifies key features of blood pressure regulation

BACKGROUND: Association studies have identified several biomarkers for blood pressure and hypertension, but a thorough understanding of their mutual dependencies is lacking. By integrating two different high-throughput datasets, biochemical and dietary data, we aim to understand the multifactorial c...

Descripción completa

Detalles Bibliográficos
Autores principales: Louca, Panayiotis, Tran, Tran Quoc Bao, Toit, Clea du, Christofidou, Paraskevi, Spector, Tim D., Mangino, Massimo, Suhre, Karsten, Padmanabhan, Sandosh, Menni, Cristina
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9463529/
https://www.ncbi.nlm.nih.gov/pubmed/36084617
http://dx.doi.org/10.1016/j.ebiom.2022.104243
_version_ 1784787410563891200
author Louca, Panayiotis
Tran, Tran Quoc Bao
Toit, Clea du
Christofidou, Paraskevi
Spector, Tim D.
Mangino, Massimo
Suhre, Karsten
Padmanabhan, Sandosh
Menni, Cristina
author_facet Louca, Panayiotis
Tran, Tran Quoc Bao
Toit, Clea du
Christofidou, Paraskevi
Spector, Tim D.
Mangino, Massimo
Suhre, Karsten
Padmanabhan, Sandosh
Menni, Cristina
author_sort Louca, Panayiotis
collection PubMed
description BACKGROUND: Association studies have identified several biomarkers for blood pressure and hypertension, but a thorough understanding of their mutual dependencies is lacking. By integrating two different high-throughput datasets, biochemical and dietary data, we aim to understand the multifactorial contributors of blood pressure (BP). METHODS: We included 4,863 participants from TwinsUK with concurrent BP, metabolomics, genomics, biochemical measures, and dietary data. We used 5-fold cross-validation with the machine learning XGBoost algorithm to identify features of importance in context of one another in TwinsUK (80% training, 20% test). The features tested in TwinsUK were then probed using the same algorithm in an independent dataset of 2,807 individuals from the Qatari Biobank (QBB). FINDINGS: Our model explained 39·2% [4·5%, MAE:11·32 mmHg (95%CI, +/- 0·65)] of the variance in systolic BP (SBP) in TwinsUK. Of the top 50 features, the most influential non-demographic variables were dihomo-linolenate, cis-4-decenoyl carnitine, lactate, chloride, urate, and creatinine along with dietary intakes of total, trans and saturated fat. We also highlight the incremental value of each included dimension. Furthermore, we replicated our model in the QBB [SBP variance explained = 45·2% (13·39%)] cohort and 30 of the top 50 features overlapped between cohorts. INTERPRETATION: We show that an integrated analysis of omics, biochemical and dietary data improves our understanding of their in-between relationships and expands the range of potential biomarkers for blood pressure. Our results point to potentially key biological pathways to be prioritised for mechanistic studies. FUNDING: Chronic Disease Research Foundation, Medical Research Council, Wellcome Trust, Qatar Foundation.
format Online
Article
Text
id pubmed-9463529
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-94635292022-09-11 Machine learning integration of multimodal data identifies key features of blood pressure regulation Louca, Panayiotis Tran, Tran Quoc Bao Toit, Clea du Christofidou, Paraskevi Spector, Tim D. Mangino, Massimo Suhre, Karsten Padmanabhan, Sandosh Menni, Cristina eBioMedicine Articles BACKGROUND: Association studies have identified several biomarkers for blood pressure and hypertension, but a thorough understanding of their mutual dependencies is lacking. By integrating two different high-throughput datasets, biochemical and dietary data, we aim to understand the multifactorial contributors of blood pressure (BP). METHODS: We included 4,863 participants from TwinsUK with concurrent BP, metabolomics, genomics, biochemical measures, and dietary data. We used 5-fold cross-validation with the machine learning XGBoost algorithm to identify features of importance in context of one another in TwinsUK (80% training, 20% test). The features tested in TwinsUK were then probed using the same algorithm in an independent dataset of 2,807 individuals from the Qatari Biobank (QBB). FINDINGS: Our model explained 39·2% [4·5%, MAE:11·32 mmHg (95%CI, +/- 0·65)] of the variance in systolic BP (SBP) in TwinsUK. Of the top 50 features, the most influential non-demographic variables were dihomo-linolenate, cis-4-decenoyl carnitine, lactate, chloride, urate, and creatinine along with dietary intakes of total, trans and saturated fat. We also highlight the incremental value of each included dimension. Furthermore, we replicated our model in the QBB [SBP variance explained = 45·2% (13·39%)] cohort and 30 of the top 50 features overlapped between cohorts. INTERPRETATION: We show that an integrated analysis of omics, biochemical and dietary data improves our understanding of their in-between relationships and expands the range of potential biomarkers for blood pressure. Our results point to potentially key biological pathways to be prioritised for mechanistic studies. FUNDING: Chronic Disease Research Foundation, Medical Research Council, Wellcome Trust, Qatar Foundation. Elsevier 2022-09-06 /pmc/articles/PMC9463529/ /pubmed/36084617 http://dx.doi.org/10.1016/j.ebiom.2022.104243 Text en © 2022 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Articles
Louca, Panayiotis
Tran, Tran Quoc Bao
Toit, Clea du
Christofidou, Paraskevi
Spector, Tim D.
Mangino, Massimo
Suhre, Karsten
Padmanabhan, Sandosh
Menni, Cristina
Machine learning integration of multimodal data identifies key features of blood pressure regulation
title Machine learning integration of multimodal data identifies key features of blood pressure regulation
title_full Machine learning integration of multimodal data identifies key features of blood pressure regulation
title_fullStr Machine learning integration of multimodal data identifies key features of blood pressure regulation
title_full_unstemmed Machine learning integration of multimodal data identifies key features of blood pressure regulation
title_short Machine learning integration of multimodal data identifies key features of blood pressure regulation
title_sort machine learning integration of multimodal data identifies key features of blood pressure regulation
topic Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9463529/
https://www.ncbi.nlm.nih.gov/pubmed/36084617
http://dx.doi.org/10.1016/j.ebiom.2022.104243
work_keys_str_mv AT loucapanayiotis machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT trantranquocbao machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT toitcleadu machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT christofidouparaskevi machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT spectortimd machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT manginomassimo machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT suhrekarsten machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT padmanabhansandosh machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation
AT mennicristina machinelearningintegrationofmultimodaldataidentifieskeyfeaturesofbloodpressureregulation