A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts

David Gomez-Cabrero; on behalf of the FRAILOMIC initiative; Stefan Walter; Imad Abugessaisa; Rebeca Miñambres-Herraiz; Lucia Bernad Palomares; Lee Butcher; Jorge D. Erusalimsky; Francisco Jose Garcia-Garcia; José Carnicero; Timothy C. Hardman; Harald Mischak; Petra Zürbig; Matthias Hackl; Johannes Grillari; Edoardo Fiorillo; Francesco Cucca; Matteo Cesari; Isabelle Carrie; Marco Colpo; Stefania Bandinelli; Catherine Feart; Karine Peres; Jean-François Dartigues; Catherine Helmer; José Viña; Gloria Olaso; Irene García-Palmero; Jorge García Martínez; Pidder Jansen-Dürr; Tilman Grune; Daniela Weber; Giuseppe Lippi; Chiara Bonaguri; Alan J Sinclair; Jesper Tegner; Leocadio Rodriguez-Mañas

doi:10.1007/s11357-021-00334-0

A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts

David Gomez-Cabrero, on behalf of the FRAILOMIC initiative, Stefan Walter, Imad Abugessaisa, Rebeca Miñambres-Herraiz, Lucia Bernad Palomares, Lee Butcher, Jorge D. Erusalimsky, Francisco Jose Garcia-Garcia, José Carnicero, Timothy C. Hardman, Harald Mischak, Petra Zürbig, Matthias Hackl, Johannes Grillari, Edoardo Fiorillo, Francesco Cucca, Matteo Cesari, Isabelle Carrie, Marco ColpoStefania Bandinelli, Catherine Feart, Karine Peres, Jean-François Dartigues, Catherine Helmer, José Viña, Gloria Olaso, Irene García-Palmero, Jorge García Martínez, Pidder Jansen-Dürr, Tilman Grune, Daniela Weber, Giuseppe Lippi, Chiara Bonaguri, Alan J Sinclair, Jesper Tegner, Leocadio Rodriguez-Mañas

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

Abstract

Phenotype-specific omic expression patterns in people with frailty could provide invaluable insight into the underlying multi-systemic pathological processes and targets for intervention. Classical approaches to frailty have not considered the potential for different frailty phenotypes. We characterized associations between frailty (with/without disability) and sets of omic factors (genomic, proteomic, and metabolomic) plus markers measured in routine geriatric care. This study was a prevalent case control using stored biospecimens (urine, whole blood, cells, plasma, and serum) from 1522 individuals (identified as robust (R), pre-frail (P), or frail (F)] from the Toledo Study of Healthy Aging (R=178/P=184/F=109), 3 City Bordeaux (111/269/100), Aging Multidisciplinary Investigation (157/79/54) and InCHIANTI (106/98/77) cohorts. The analysis included over 35,000 omic and routine laboratory variables from robust and frail or pre-frail (with/without disability) individuals using a machine learning framework. We identified three protective biomarkers, vitamin D3 (OR: 0.81 [95% CI: 0.68-0.98]), lutein zeaxanthin (OR: 0.82 [95% CI: 0.70-0.97]), and miRNA125b-5p (OR: 0.73, [95% CI: 0.56-0.97]) and one risk biomarker, cardiac troponin T (OR: 1.25 [95% CI: 1.23-1.27]). Excluding individuals with a disability, one protective biomarker was identified, miR125b-5p (OR: 0.85, [95% CI: 0.81-0.88]). Three risks of frailty biomarkers were detected: pro-BNP (OR: 1.47 [95% CI: 1.27-1.7]), cardiac troponin T (OR: 1.29 [95% CI: 1.21-1.38]), and sRAGE (OR: 1.26 [95% CI: 1.01-1.57]). Three key frailty biomarkers demonstrated a statistical association with frailty (oxidative stress, vitamin D, and cardiovascular system) with relationship patterns differing depending on the presence or absence of a disability.

Original language	English (US)
Journal	GeroScience
DOIs	https://doi.org/10.1007/s11357-021-00334-0
State	Published - Feb 18 2021

Bibliographical note

KAUST Repository Item: Exported on 2021-04-14
Acknowledgements: This work was supported by the European Union’s Seventh Framework Programme (FP7/2007-2013) FRAILOMIC Project (grant number 305483). The Three-City Study was conducted under a partnership agreement between the Institut National de la Santé et de la Recherche Médicale, Victor Segalen – Bordeaux2 University and the Sanofi-Synthélabo company. The Fondation pour la Recherche Médicale funded the preparation and beginning of the study. The 3C-Study was also sponsored by the Caisse Nationale Maladie des Travailleurs Salariés, Direction Générale de la Santé, Conseils Régionaux of Aquitaine and Bourgogne, Fondation de France, Ministry of Research-INSERM Program Cohortes et collections de données biologiques, the Fondation Plan Alzheimer (FCS 2009-2012), and the Caisse Nationale pour la Solidarité et l’Autonomie. The InCHIANTI study baseline (1998–2000) was supported as a ‘targeted project’ (ICS110.1/RF97.71) by the Italian Ministry of Health and in part by the U.S. National Institute on Aging (Contracts: 263 MD 9164 and 263 MD 821336) and by the Intramural Research Program of the National Institute on Aging, National Institutes of Health, Baltimore, Maryland.Data AvailabilityData will be made freely available

Access to Document

10.1007/s11357-021-00334-0

Cite this

Gomez-Cabrero, D., initiative, O. B. O. T. FRAILOMIC., Walter, S., Abugessaisa, I., Miñambres-Herraiz, R., Palomares, L. B., Butcher, L., Erusalimsky, J. D., Garcia-Garcia, F. J., Carnicero, J., Hardman, T. C., Mischak, H., Zürbig, P., Hackl, M., Grillari, J., Fiorillo, E., Cucca, F., Cesari, M., Carrie, I., ... Rodriguez-Mañas, L. (2021). A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts. GeroScience. https://doi.org/10.1007/s11357-021-00334-0

@article{da85d04956cf4a30a44cda42b1582e8e,

title = "A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts",

abstract = "Phenotype-specific omic expression patterns in people with frailty could provide invaluable insight into the underlying multi-systemic pathological processes and targets for intervention. Classical approaches to frailty have not considered the potential for different frailty phenotypes. We characterized associations between frailty (with/without disability) and sets of omic factors (genomic, proteomic, and metabolomic) plus markers measured in routine geriatric care. This study was a prevalent case control using stored biospecimens (urine, whole blood, cells, plasma, and serum) from 1522 individuals (identified as robust (R), pre-frail (P), or frail (F)] from the Toledo Study of Healthy Aging (R=178/P=184/F=109), 3 City Bordeaux (111/269/100), Aging Multidisciplinary Investigation (157/79/54) and InCHIANTI (106/98/77) cohorts. The analysis included over 35,000 omic and routine laboratory variables from robust and frail or pre-frail (with/without disability) individuals using a machine learning framework. We identified three protective biomarkers, vitamin D3 (OR: 0.81 [95% CI: 0.68-0.98]), lutein zeaxanthin (OR: 0.82 [95% CI: 0.70-0.97]), and miRNA125b-5p (OR: 0.73, [95% CI: 0.56-0.97]) and one risk biomarker, cardiac troponin T (OR: 1.25 [95% CI: 1.23-1.27]). Excluding individuals with a disability, one protective biomarker was identified, miR125b-5p (OR: 0.85, [95% CI: 0.81-0.88]). Three risks of frailty biomarkers were detected: pro-BNP (OR: 1.47 [95% CI: 1.27-1.7]), cardiac troponin T (OR: 1.29 [95% CI: 1.21-1.38]), and sRAGE (OR: 1.26 [95% CI: 1.01-1.57]). Three key frailty biomarkers demonstrated a statistical association with frailty (oxidative stress, vitamin D, and cardiovascular system) with relationship patterns differing depending on the presence or absence of a disability.",

author = "David Gomez-Cabrero and initiative, {on behalf of the FRAILOMIC} and Stefan Walter and Imad Abugessaisa and Rebeca Mi{\~n}ambres-Herraiz and Palomares, {Lucia Bernad} and Lee Butcher and Erusalimsky, {Jorge D.} and Garcia-Garcia, {Francisco Jose} and Jos{\'e} Carnicero and Hardman, {Timothy C.} and Harald Mischak and Petra Z{\"u}rbig and Matthias Hackl and Johannes Grillari and Edoardo Fiorillo and Francesco Cucca and Matteo Cesari and Isabelle Carrie and Marco Colpo and Stefania Bandinelli and Catherine Feart and Karine Peres and Jean-Fran{\c c}ois Dartigues and Catherine Helmer and Jos{\'e} Vi{\~n}a and Gloria Olaso and Irene Garc{\'i}a-Palmero and Mart{\'i}nez, {Jorge Garc{\'i}a} and Pidder Jansen-D{\"u}rr and Tilman Grune and Daniela Weber and Giuseppe Lippi and Chiara Bonaguri and Sinclair, {Alan J} and Jesper Tegner and Leocadio Rodriguez-Ma{\~n}as",

note = "KAUST Repository Item: Exported on 2021-04-14 Acknowledgements: This work was supported by the European Union{\textquoteright}s Seventh Framework Programme (FP7/2007-2013) FRAILOMIC Project (grant number 305483). The Three-City Study was conducted under a partnership agreement between the Institut National de la Sant{\'e} et de la Recherche M{\'e}dicale, Victor Segalen – Bordeaux2 University and the Sanofi-Synth{\'e}labo company. The Fondation pour la Recherche M{\'e}dicale funded the preparation and beginning of the study. The 3C-Study was also sponsored by the Caisse Nationale Maladie des Travailleurs Salari{\'e}s, Direction G{\'e}n{\'e}rale de la Sant{\'e}, Conseils R{\'e}gionaux of Aquitaine and Bourgogne, Fondation de France, Ministry of Research-INSERM Program Cohortes et collections de donn{\'e}es biologiques, the Fondation Plan Alzheimer (FCS 2009-2012), and the Caisse Nationale pour la Solidarit{\'e} et l{\textquoteright}Autonomie. The InCHIANTI study baseline (1998–2000) was supported as a {\textquoteleft}targeted project{\textquoteright} (ICS110.1/RF97.71) by the Italian Ministry of Health and in part by the U.S. National Institute on Aging (Contracts: 263 MD 9164 and 263 MD 821336) and by the Intramural Research Program of the National Institute on Aging, National Institutes of Health, Baltimore, Maryland.Data AvailabilityData will be made freely available",

year = "2021",

month = feb,

day = "18",

doi = "10.1007/s11357-021-00334-0",

language = "English (US)",

journal = "GeroScience",

issn = "2509-2715",

publisher = "Springer International Publishing AG",

}

Gomez-Cabrero, D, initiative, OBOTFRAILOMIC, Walter, S, Abugessaisa, I, Miñambres-Herraiz, R, Palomares, LB, Butcher, L, Erusalimsky, JD, Garcia-Garcia, FJ, Carnicero, J, Hardman, TC, Mischak, H, Zürbig, P, Hackl, M, Grillari, J, Fiorillo, E, Cucca, F, Cesari, M, Carrie, I, Colpo, M, Bandinelli, S, Feart, C, Peres, K, Dartigues, J-F, Helmer, C, Viña, J, Olaso, G, García-Palmero, I, Martínez, JG, Jansen-Dürr, P, Grune, T, Weber, D, Lippi, G, Bonaguri, C, Sinclair, AJ , Tegner, J & Rodriguez-Mañas, L 2021, 'A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts', GeroScience. https://doi.org/10.1007/s11357-021-00334-0

TY - JOUR

T1 - A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts

AU - Gomez-Cabrero, David

AU - initiative, on behalf of the FRAILOMIC

AU - Walter, Stefan

AU - Abugessaisa, Imad

AU - Miñambres-Herraiz, Rebeca

AU - Palomares, Lucia Bernad

AU - Butcher, Lee

AU - Erusalimsky, Jorge D.

AU - Garcia-Garcia, Francisco Jose

AU - Carnicero, José

AU - Hardman, Timothy C.

AU - Mischak, Harald

AU - Zürbig, Petra

AU - Hackl, Matthias

AU - Grillari, Johannes

AU - Fiorillo, Edoardo

AU - Cucca, Francesco

AU - Cesari, Matteo

AU - Carrie, Isabelle

AU - Colpo, Marco

AU - Bandinelli, Stefania

AU - Feart, Catherine

AU - Peres, Karine

AU - Dartigues, Jean-François

AU - Helmer, Catherine

AU - Viña, José

AU - Olaso, Gloria

AU - García-Palmero, Irene

AU - Martínez, Jorge García

AU - Jansen-Dürr, Pidder

AU - Grune, Tilman

AU - Weber, Daniela

AU - Lippi, Giuseppe

AU - Bonaguri, Chiara

AU - Sinclair, Alan J

AU - Tegner, Jesper

AU - Rodriguez-Mañas, Leocadio

N1 - KAUST Repository Item: Exported on 2021-04-14 Acknowledgements: This work was supported by the European Union’s Seventh Framework Programme (FP7/2007-2013) FRAILOMIC Project (grant number 305483). The Three-City Study was conducted under a partnership agreement between the Institut National de la Santé et de la Recherche Médicale, Victor Segalen – Bordeaux2 University and the Sanofi-Synthélabo company. The Fondation pour la Recherche Médicale funded the preparation and beginning of the study. The 3C-Study was also sponsored by the Caisse Nationale Maladie des Travailleurs Salariés, Direction Générale de la Santé, Conseils Régionaux of Aquitaine and Bourgogne, Fondation de France, Ministry of Research-INSERM Program Cohortes et collections de données biologiques, the Fondation Plan Alzheimer (FCS 2009-2012), and the Caisse Nationale pour la Solidarité et l’Autonomie. The InCHIANTI study baseline (1998–2000) was supported as a ‘targeted project’ (ICS110.1/RF97.71) by the Italian Ministry of Health and in part by the U.S. National Institute on Aging (Contracts: 263 MD 9164 and 263 MD 821336) and by the Intramural Research Program of the National Institute on Aging, National Institutes of Health, Baltimore, Maryland.Data AvailabilityData will be made freely available

PY - 2021/2/18

Y1 - 2021/2/18

N2 - Phenotype-specific omic expression patterns in people with frailty could provide invaluable insight into the underlying multi-systemic pathological processes and targets for intervention. Classical approaches to frailty have not considered the potential for different frailty phenotypes. We characterized associations between frailty (with/without disability) and sets of omic factors (genomic, proteomic, and metabolomic) plus markers measured in routine geriatric care. This study was a prevalent case control using stored biospecimens (urine, whole blood, cells, plasma, and serum) from 1522 individuals (identified as robust (R), pre-frail (P), or frail (F)] from the Toledo Study of Healthy Aging (R=178/P=184/F=109), 3 City Bordeaux (111/269/100), Aging Multidisciplinary Investigation (157/79/54) and InCHIANTI (106/98/77) cohorts. The analysis included over 35,000 omic and routine laboratory variables from robust and frail or pre-frail (with/without disability) individuals using a machine learning framework. We identified three protective biomarkers, vitamin D3 (OR: 0.81 [95% CI: 0.68-0.98]), lutein zeaxanthin (OR: 0.82 [95% CI: 0.70-0.97]), and miRNA125b-5p (OR: 0.73, [95% CI: 0.56-0.97]) and one risk biomarker, cardiac troponin T (OR: 1.25 [95% CI: 1.23-1.27]). Excluding individuals with a disability, one protective biomarker was identified, miR125b-5p (OR: 0.85, [95% CI: 0.81-0.88]). Three risks of frailty biomarkers were detected: pro-BNP (OR: 1.47 [95% CI: 1.27-1.7]), cardiac troponin T (OR: 1.29 [95% CI: 1.21-1.38]), and sRAGE (OR: 1.26 [95% CI: 1.01-1.57]). Three key frailty biomarkers demonstrated a statistical association with frailty (oxidative stress, vitamin D, and cardiovascular system) with relationship patterns differing depending on the presence or absence of a disability.

AB - Phenotype-specific omic expression patterns in people with frailty could provide invaluable insight into the underlying multi-systemic pathological processes and targets for intervention. Classical approaches to frailty have not considered the potential for different frailty phenotypes. We characterized associations between frailty (with/without disability) and sets of omic factors (genomic, proteomic, and metabolomic) plus markers measured in routine geriatric care. This study was a prevalent case control using stored biospecimens (urine, whole blood, cells, plasma, and serum) from 1522 individuals (identified as robust (R), pre-frail (P), or frail (F)] from the Toledo Study of Healthy Aging (R=178/P=184/F=109), 3 City Bordeaux (111/269/100), Aging Multidisciplinary Investigation (157/79/54) and InCHIANTI (106/98/77) cohorts. The analysis included over 35,000 omic and routine laboratory variables from robust and frail or pre-frail (with/without disability) individuals using a machine learning framework. We identified three protective biomarkers, vitamin D3 (OR: 0.81 [95% CI: 0.68-0.98]), lutein zeaxanthin (OR: 0.82 [95% CI: 0.70-0.97]), and miRNA125b-5p (OR: 0.73, [95% CI: 0.56-0.97]) and one risk biomarker, cardiac troponin T (OR: 1.25 [95% CI: 1.23-1.27]). Excluding individuals with a disability, one protective biomarker was identified, miR125b-5p (OR: 0.85, [95% CI: 0.81-0.88]). Three risks of frailty biomarkers were detected: pro-BNP (OR: 1.47 [95% CI: 1.27-1.7]), cardiac troponin T (OR: 1.29 [95% CI: 1.21-1.38]), and sRAGE (OR: 1.26 [95% CI: 1.01-1.57]). Three key frailty biomarkers demonstrated a statistical association with frailty (oxidative stress, vitamin D, and cardiovascular system) with relationship patterns differing depending on the presence or absence of a disability.

UR - http://hdl.handle.net/10754/667522

UR - http://link.springer.com/10.1007/s11357-021-00334-0

UR - http://www.scopus.com/inward/record.url?scp=85101234843&partnerID=8YFLogxK

U2 - 10.1007/s11357-021-00334-0

DO - 10.1007/s11357-021-00334-0

M3 - Article

C2 - 33599920

SN - 2509-2715

JO - GeroScience

JF - GeroScience

ER -

A robust machine learning framework to identify signatures for frailty: a nested case-control study in four aging European cohorts

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this