Home > Research > Publications & Outputs > Interpretable brain age prediction using linear...

Research

Associated organisational unit

Links

Text available via DOI:

View graph of relations

Interpretable brain age prediction using linear latent variable models of functional connectivity

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Interpretable brain age prediction using linear latent variable models of functional connectivity. / Monti, Ricardo Pio; Gibberd, Alex; Roy, Sandipan et al.
In: PLoS ONE, Vol. 15, No. 6, e0232296, 10.06.2020.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Monti, RP, Gibberd, A, Roy, S, Nunes, M, Lorenz, R, Leech, R, Ogawa, T, Kawanabe, M & Hyvärinen, A 2020, 'Interpretable brain age prediction using linear latent variable models of functional connectivity', PLoS ONE, vol. 15, no. 6, e0232296. https://doi.org/10.1371/journal.pone.0232296

APA

Monti, R. P., Gibberd, A., Roy, S., Nunes, M., Lorenz, R., Leech, R., Ogawa, T., Kawanabe, M., & Hyvärinen, A. (2020). Interpretable brain age prediction using linear latent variable models of functional connectivity. PLoS ONE, 15(6), Article e0232296. https://doi.org/10.1371/journal.pone.0232296

Vancouver

Monti RP, Gibberd A, Roy S, Nunes M, Lorenz R, Leech R et al. Interpretable brain age prediction using linear latent variable models of functional connectivity. PLoS ONE. 2020 Jun 10;15(6):e0232296. doi: 10.1371/journal.pone.0232296

Author

Monti, Ricardo Pio ; Gibberd, Alex ; Roy, Sandipan et al. / Interpretable brain age prediction using linear latent variable models of functional connectivity. In: PLoS ONE. 2020 ; Vol. 15, No. 6.

Bibtex

@article{3135f6b260ce48b2b30201050be41b3f,
title = "Interpretable brain age prediction using linear latent variable models of functional connectivity",
abstract = "Neuroimaging-driven prediction of brain age, defined as the predicted biological age of a subject using only brain imaging data, is an exciting avenue of research. In this work we seek to build models of brain age based on functional connectivity while prioritizing model interpretability and understanding. This way, the models serve to both provide accurate estimates of brain age as well as allow us to investigate changes in functional connectivity which occur during the ageing process. The methods proposed in this work consist of a two-step procedure: first, linear latent variable models, such as PCA and its extensions, are employed to learn reproducible functional connectivity networks present across a cohort of subjects. The activity within each network is subsequently employed as a feature in a linear regression model to predict brain age. The proposed framework is employed on the data from the CamCAN repository and the inferred brain age models are further demonstrated to generalize using data from two open-access repositories: the Human Connectome Project and the ATR Wide-Age-Range.",
author = "Monti, {Ricardo Pio} and Alex Gibberd and Sandipan Roy and Matthew Nunes and Romy Lorenz and Robert Leech and Takeshi Ogawa and Motoaki Kawanabe and Aapo Hyv{\"a}rinen",
year = "2020",
month = jun,
day = "10",
doi = "10.1371/journal.pone.0232296",
language = "English",
volume = "15",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "6",

}

RIS

TY - JOUR

T1 - Interpretable brain age prediction using linear latent variable models of functional connectivity

AU - Monti, Ricardo Pio

AU - Gibberd, Alex

AU - Roy, Sandipan

AU - Nunes, Matthew

AU - Lorenz, Romy

AU - Leech, Robert

AU - Ogawa, Takeshi

AU - Kawanabe, Motoaki

AU - Hyvärinen, Aapo

PY - 2020/6/10

Y1 - 2020/6/10

N2 - Neuroimaging-driven prediction of brain age, defined as the predicted biological age of a subject using only brain imaging data, is an exciting avenue of research. In this work we seek to build models of brain age based on functional connectivity while prioritizing model interpretability and understanding. This way, the models serve to both provide accurate estimates of brain age as well as allow us to investigate changes in functional connectivity which occur during the ageing process. The methods proposed in this work consist of a two-step procedure: first, linear latent variable models, such as PCA and its extensions, are employed to learn reproducible functional connectivity networks present across a cohort of subjects. The activity within each network is subsequently employed as a feature in a linear regression model to predict brain age. The proposed framework is employed on the data from the CamCAN repository and the inferred brain age models are further demonstrated to generalize using data from two open-access repositories: the Human Connectome Project and the ATR Wide-Age-Range.

AB - Neuroimaging-driven prediction of brain age, defined as the predicted biological age of a subject using only brain imaging data, is an exciting avenue of research. In this work we seek to build models of brain age based on functional connectivity while prioritizing model interpretability and understanding. This way, the models serve to both provide accurate estimates of brain age as well as allow us to investigate changes in functional connectivity which occur during the ageing process. The methods proposed in this work consist of a two-step procedure: first, linear latent variable models, such as PCA and its extensions, are employed to learn reproducible functional connectivity networks present across a cohort of subjects. The activity within each network is subsequently employed as a feature in a linear regression model to predict brain age. The proposed framework is employed on the data from the CamCAN repository and the inferred brain age models are further demonstrated to generalize using data from two open-access repositories: the Human Connectome Project and the ATR Wide-Age-Range.

U2 - 10.1371/journal.pone.0232296

DO - 10.1371/journal.pone.0232296

M3 - Journal article

C2 - 32520931

VL - 15

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 6

M1 - e0232296

ER -