Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
15
0

Year Published

2016
2016
2019
2019

Publication Types

Select...
3
1

Relationship

1
3

Authors

Journals

citations
Cited by 17 publications
(26 citation statements)
references
References 21 publications
(26 reference statements)
0
15
0
Order By: Relevance
“…Based on information in the section above, developing a proxy measure of biological aging for humans still requires work but is a very dynamic and promising area of investigation with strong potential for translation. Some of the measures described-namely mitochondrial function, DNA methylation, and, to a lesser extent, cellular senescence and autophagy-are ready to be implemented based on several epidemiological studies, although refinements are always possible Choi et al, 2016;Cohen, Morissette-Thomas, Ferrucci, & Fried, 2016;Jylhävä, Pedersen, & Hägg, 2017;Jylhävä et al, 2014;Kananen et al, 2016;Kent & Fitzgerald, 2016;Kim & Jazwinski, 2015;Levine et al, 2018;Li et al, 2018;Marioni et al, 2019;Marttila et al, 2015;Putin et al, 2017;Sillanpää et al, 2018). Measures of telomere length are hampered by noise and wide longitudinal variations that cannot be explained by health events and at this stage are not useful for measuring biological age (Arai et al, 2015;Jodczyk, Fergusson, Horwood, Pearson, & Kennedy, 2014;Tomaska & Nosek, 2009).…”
Section: Connec Ting the B I Ology Of Ag Ing With Ag E-a Sso Ciatedmentioning
confidence: 99%
“…Based on information in the section above, developing a proxy measure of biological aging for humans still requires work but is a very dynamic and promising area of investigation with strong potential for translation. Some of the measures described-namely mitochondrial function, DNA methylation, and, to a lesser extent, cellular senescence and autophagy-are ready to be implemented based on several epidemiological studies, although refinements are always possible Choi et al, 2016;Cohen, Morissette-Thomas, Ferrucci, & Fried, 2016;Jylhävä, Pedersen, & Hägg, 2017;Jylhävä et al, 2014;Kananen et al, 2016;Kent & Fitzgerald, 2016;Kim & Jazwinski, 2015;Levine et al, 2018;Li et al, 2018;Marioni et al, 2019;Marttila et al, 2015;Putin et al, 2017;Sillanpää et al, 2018). Measures of telomere length are hampered by noise and wide longitudinal variations that cannot be explained by health events and at this stage are not useful for measuring biological age (Arai et al, 2015;Jodczyk, Fergusson, Horwood, Pearson, & Kennedy, 2014;Tomaska & Nosek, 2009).…”
Section: Connec Ting the B I Ology Of Ag Ing With Ag E-a Sso Ciatedmentioning
confidence: 99%
“…Like other biomarkers discussed in the Introduction, biomarkers of aging can have three uses: to estimate lifespan remaining (prognosis), to identify the mechanisms that cause aging (33), and, most ambitiously and usually late in their development, to distinguish classes of individuals for whom different treatments are appropriate. In cross-sectional studies, epigenetic biomarkers of aging have been selected for their ability to predict age at the time of sampling (21).…”
Section: Discussionmentioning
confidence: 99%
“…The "biological age" or "bioage" is a quantitative measure of aging -and thus an expected lifespan -based on biological data. State-of-the-art approaches for biological age evaluation take advantage of the strong association of physiological variables with age and thus rely on linear (see, e.g., DNA methylation age [1,18]) or non-linear regressions [7,8,10] to estimate the chronological age of a patient directly from the biological data. Following these examples, we started by building a deep convolution neural network (CNN) trained to predict the chronological age of the same NHANES participants from the raw one-week long physical activity records.…”
Section: Deep Learning Chronological Age From Physical Activity Recordsmentioning
confidence: 99%
“…Deep learning is a powerful tool in pattern recognition and has demonstrated outstanding performance in visual object identification, speech recognition, and other fields requiring hierarchical analysis of input data. Recent promising examples in the field of biomedical signal analysis include convolution neural networks (CNNs) trained to process electrocardiograms showing cardiologist-level performance in detection of arrhythmia [6], biomarkers of age from clinical blood biochemistry [7,8] or electronic medical records [9], or mortality prediction [10]. Inspired by these examples, we explored deep learning architectures for Health Risks Assessment (HRA) applications, to use human physical activity streams from wearable devices for continuous health risks evaluation.…”
Section: Introductionmentioning
confidence: 99%