Extracting biological age from biomedical data via deep learning: too much of a good thing?

Abstract Age-related physiological changes in humans are linearly associated with age. Naturally, linear combinations of physiological measures trained to estimate chronological age have recently emerged as a practical way to quantify aging in the form of biological age. In this work, we used one-we...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Timothy V. Pyrkov, Konstantin Slipensky, Mikhail Barg, Alexey Kondrashin, Boris Zhurov, Alexander Zenin, Mikhail Pyatnitskiy, Leonid Menshikov, Sergei Markov, Peter O. Fedichev
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/b81dc284f30544e6a57682636f29adbf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b81dc284f30544e6a57682636f29adbf
record_format	dspace
spelling	oai:doaj.org-article:b81dc284f30544e6a57682636f29adbf2021-12-02T15:08:57ZExtracting biological age from biomedical data via deep learning: too much of a good thing?10.1038/s41598-018-23534-92045-2322https://doaj.org/article/b81dc284f30544e6a57682636f29adbf2018-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-23534-9https://doaj.org/toc/2045-2322Abstract Age-related physiological changes in humans are linearly associated with age. Naturally, linear combinations of physiological measures trained to estimate chronological age have recently emerged as a practical way to quantify aging in the form of biological age. In this work, we used one-week long physical activity records from a 2003–2006 National Health and Nutrition Examination Survey (NHANES) to compare three increasingly accurate biological age models: the unsupervised Principal Components Analysis (PCA) score, a multivariate linear regression, and a state-of-the-art deep convolutional neural network (CNN). We found that the supervised approaches produce better chronological age estimations at the expense of a loss of the association between the aging acceleration and all-cause mortality. Consequently, we turned to the NHANES death register directly and introduced a novel way to train parametric proportional hazards models suitable for out-of-the-box implementation with any modern machine learning software. As a demonstration, we produced a separate deep CNN for mortality risks prediction that outperformed any of the biological age or a simple linear proportional hazards model. Altogether, our findings demonstrate the emerging potential of combined wearable sensors and deep learning technologies for applications involving continuous health risk monitoring and real-time feedback to patients and care providers.Timothy V. PyrkovKonstantin SlipenskyMikhail BargAlexey KondrashinBoris ZhurovAlexander ZeninMikhail PyatnitskiyLeonid MenshikovSergei MarkovPeter O. FedichevNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-11 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Timothy V. Pyrkov Konstantin Slipensky Mikhail Barg Alexey Kondrashin Boris Zhurov Alexander Zenin Mikhail Pyatnitskiy Leonid Menshikov Sergei Markov Peter O. Fedichev Extracting biological age from biomedical data via deep learning: too much of a good thing?
description	Abstract Age-related physiological changes in humans are linearly associated with age. Naturally, linear combinations of physiological measures trained to estimate chronological age have recently emerged as a practical way to quantify aging in the form of biological age. In this work, we used one-week long physical activity records from a 2003–2006 National Health and Nutrition Examination Survey (NHANES) to compare three increasingly accurate biological age models: the unsupervised Principal Components Analysis (PCA) score, a multivariate linear regression, and a state-of-the-art deep convolutional neural network (CNN). We found that the supervised approaches produce better chronological age estimations at the expense of a loss of the association between the aging acceleration and all-cause mortality. Consequently, we turned to the NHANES death register directly and introduced a novel way to train parametric proportional hazards models suitable for out-of-the-box implementation with any modern machine learning software. As a demonstration, we produced a separate deep CNN for mortality risks prediction that outperformed any of the biological age or a simple linear proportional hazards model. Altogether, our findings demonstrate the emerging potential of combined wearable sensors and deep learning technologies for applications involving continuous health risk monitoring and real-time feedback to patients and care providers.
format	article
author	Timothy V. Pyrkov Konstantin Slipensky Mikhail Barg Alexey Kondrashin Boris Zhurov Alexander Zenin Mikhail Pyatnitskiy Leonid Menshikov Sergei Markov Peter O. Fedichev
author_facet	Timothy V. Pyrkov Konstantin Slipensky Mikhail Barg Alexey Kondrashin Boris Zhurov Alexander Zenin Mikhail Pyatnitskiy Leonid Menshikov Sergei Markov Peter O. Fedichev
author_sort	Timothy V. Pyrkov
title	Extracting biological age from biomedical data via deep learning: too much of a good thing?
title_short	Extracting biological age from biomedical data via deep learning: too much of a good thing?
title_full	Extracting biological age from biomedical data via deep learning: too much of a good thing?
title_fullStr	Extracting biological age from biomedical data via deep learning: too much of a good thing?
title_full_unstemmed	Extracting biological age from biomedical data via deep learning: too much of a good thing?
title_sort	extracting biological age from biomedical data via deep learning: too much of a good thing?
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/b81dc284f30544e6a57682636f29adbf
work_keys_str_mv	AT timothyvpyrkov extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT konstantinslipensky extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT mikhailbarg extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT alexeykondrashin extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT boriszhurov extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT alexanderzenin extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT mikhailpyatnitskiy extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT leonidmenshikov extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT sergeimarkov extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing AT peterofedichev extractingbiologicalagefrombiomedicaldataviadeeplearningtoomuchofagoodthing
_version_	1718387960986992640

Extracting biological age from biomedical data via deep learning: too much of a good thing?

Ejemplares similares