Extracting biological age from biomedical data via deep learning: too much of a good thing?
Open accessPublished version of a preprint
Abstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Principal component analysis-based biological age estimators, which involve unsupervised dimensionality reduction to unbiasedly identify ageing signals, seemingly perform even better than clocks that train on chronological age.
“This concept has been demonstrated by principal component analysis-based biological age estimators, which involve unsupervised dimensionality reduction to unbiasedly identify ageing signals, seemingly even better than clocks that train on chronological age173–175.”
From Measuring biological age using omics data (2022) · cites this paper as [174]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
Regression Models and Life-Tables
Cox, D. R. (1992) · Springer Series in Statistics · doi:10.1007/978-1-4612-4380-9_37 · Cited by 26,297 · see citing works
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftPreprint
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 15,273 · see citing works
(2010) · Cited by 14,134 · see citing works
Sudlow, C., Gallacher, J., Allen, N., Beral, V., Burton, P., Danesh, J., Downey, P., Elliott, P., Green, J., Landray, M., et al. (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001779 · Cited by 12,728 · see citing works
Modeling Survival Data: Extending the Cox Model
Therneau, T. M., & Grambsch, P. M. (2000) · Statistics for Biology and Health · doi:10.1007/978-1-4757-3294-8 · Cited by 8,674 · see citing works
Bolstad, B. M., Irizarry, R. A., Åstrand, M., & Speed, T. P. (2003) · Bioinformatics · doi:10.1093/bioinformatics/19.2.185 · Cited by 8,185 · see citing works
DNA methylation age of human tissues and cell types
Horvath, S. (2013) · Genome Biology · doi:10.1186/gb-2013-14-10-r115 · Cited by 7,075 · see citing works
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · see citing works
International Labour Organization
(2022) · Permanent missions to the United Nations · doi:10.18356/9789210018289c229 · Cited by 4,312 · see citing works
Genome-wide methylation profiles reveal quantitative views of human aging rates
Hannum, G., Guinney, J., Zhao, L., Zhang, L., Hughes, G., Sadda, S., Klotzle, B., Bibikova, M., Fan, J.-B., Gao, Y., et al. (2013) · Molecular Cell · doi:10.1016/j.molcel.2012.10.016 · Cited by 4,270 · see citing works
Gompertz, B. (1825) · Philosophical Transactions of the Royal Society of London · doi:10.1098/rstl.1825.0026 · Cited by 3,816 · see citing works
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1× · see citing works
“However, deep CNNs bring the idea to an entirely new level and are particularly useful for automation of the most relevant features engineering from the data in relation to human activity recognition (HAR) [33, 34], spe-”
BackgroundOdamaki, T., Kato, K., Sugahara, H., Hashikura, N., Takahashi, S., Xiao, J.-Z., Abe, F., & Osawa, R. (2016) · BMC Microbiology · doi:10.1186/s12866-016-0708-5 · Cited by 1,521 · see citing works
DNA methylation age of blood predicts all-cause mortality in later life
Marioni, R. E., Shah, S., McRae, A. F., Chen, B. H., Colicino, E., Harris, S. E., Gibson, J., Henders, A. K., Redmond, P., Cox, S. R., et al. (2015) · Genome Biology · doi:10.1186/s13059-015-0584-6 · Cited by 1,261 · see citing works
The Efficiency of Cox's Likelihood Function for Censored Data
Efron, B. (1977) · Journal of the American Statistical Association · doi:10.1080/01621459.1977.10480613 · Cited by 1,240 · see citing works
Levine, M. E. (2012) · The Journals of Gerontology Series A · doi:10.1093/gerona/gls233 · Cited by 897 · see citing works
Obesity accelerates epigenetic aging of human liver
Horvath, S., Erhart, W., Brosch, M., Ammerpohl, O., Schönfels, W. V., Ahrens, M., Heits, N., Bell, J. T., Tsai, P.-C., Spector, T. D., et al. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1412759111 · Cited by 760 · see citing works
An epigenetic clock analysis of race/ethnicity, sex, and coronary heart disease
Horvath, S., Gurven, M., Levine, M. E., Trumble, B. C., Kaplan, H. S., Allayee, H., Ritz, B. R., Chen, B. H., Lu, A. T.-H., Rickabaugh, T. M., et al. (2016) · Genome biology · doi:10.1186/s13059-016-1030-0 · Cited by 729 · see citing works
The transcriptional landscape of age in human peripheral blood
Peters, M. J., Joehanes, R., Pilling, L. C., Schurmann, C., Conneely, K. N., Powell, J., Reinmaa, E., Sutphin, G. L., Zhernakova, A., Schramm, K., et al. (2015) · Nature Communications · doi:10.1038/ncomms9570 · Cited by 725 · see citing works
Cardiologist-Level Arrhythmia Detection with Convolutional Neural NetworksPreprint
Rajpurkar, P., Hannun, A., Haghpanahi, M., Bourn, C., & Ng, A. Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.01836 · Cited by 611 · see citing works
Kirkwood, T. B. L. (2015) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2014.0379 · Cited by 610 · see citing works
HIV-1 infection accelerates age according to the epigenetic clock
Horvath, S., & Levine, A. J. (2015) · Journal of Infectious Diseases · doi:10.1093/infdis/jiv277 · Cited by 556 · see citing works
Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
Guan, Y., & Plötz, T. (2017) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3090076 · Cited by 511 · see citing works
Accelerated epigenetic aging in Down syndrome
Horvath, S., Garagnani, P., Bacalini, M. G., Pirazzini, C., Salvioli, S., Gentilini, D., Blasio, A. M. D., Giuliani, C., Tung, S., Vinters, H. V., et al. (2015) · Aging Cell · doi:10.1111/acel.12325 · Cited by 488 · see citing works
Glycans Are a Novel Biomarker of Chronological and Biological Ages
Krištić, J., Vučković, F., Menni, C., Klarić, L., Keser, T., Beceheli, I., Pučić-Baković, M., Novokmet, M., Mangino, M., Thaqi, K., et al. (2014) · The Journals of Gerontology: Series A · doi:10.1093/gerona/glt190 · Cited by 400 · see citing works
Franco, O. H., Steyerberg, E. W., Hu, F. B., Mackenbach, J., & Nusselder, W. (2007) · Archives of Internal Medicine · doi:10.1001/archinte.167.11.1145 · Cited by 400 · see citing works
Deep biomarkers of human aging: Application of deep neural networks to biomarker development
Putin, E., Mamoshina, P., Aliper, A. M., Korzinkin, M., Moskalev, A., Kolosov, A., Ostrovskiy, A., Cantor, C. R., Vijg, J., & Zhavoronkov, A. A. (2016) · Aging · doi:10.18632/aging.100968 · Cited by 373 · see citing works
Decreased epigenetic age of PBMCs from Italian semi-supercentenarians and their offspring
Horvath, S., Pirazzini, C., Bacalini, M. G., Gentilini, D., Di Blasio, A. M., Delledonne, M., Mari, D., Arosio, B., Monti, D., Passarino, G., et al. (2015) · Aging · doi:10.18632/aging.100861 · Cited by 316 · see citing works
DNA methylation age is associated with mortality in a longitudinal Danish twin study
Christiansen, L., Lenart, A. G., Tan, Q., Vaupel, J. W., Aviv, A., McGue, M. K., & Christensen, K. (2015) · Aging Cell · doi:10.1111/acel.12421 · Cited by 306 · see citing works
Patients’ views of wearable devices and AI in healthcare: findings from the ComPaRe e-cohort
Tran, V.-T., Riveros, C., & Ravaud, P. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0132-y · Cited by 266 · see citing works
Vidaki, A., Ballard, D., Aliferi, A., Miller, T. H., Barron, L., & Court, D. S. (2017) · Forensic Science International Genetics · doi:10.1016/j.fsigen.2017.02.009 · Cited by 246 · see citing works
The Efficiency of Cox's Likelihood Function for Censored Data
Efron, B. (1977) · Journal of the American Statistical Association · doi:10.2307/2286217 · Cited by 218 · see citing works
Brown, A. E., Yemini, E., Grundy, L. J., Jucikas, T., & Schafer, W. R. (2012) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1211447110 · Cited by 186 · see citing works
Daily step goal of 10,000 steps: A literature review
Choi, B. C. K., Pak, A. W. P., Choi, J. C. L., & Choi, E. C. L. (2007) · Clinical and investigative medicine · doi:10.25011/cim.v30i3.1083 · Cited by 167 · see citing works
Oakden-Rayner, L., Carneiro, G., Bessen, T., Nascimento, J. C., Bradley, A. P., & Palmer, L. J. (2017) · Scientific Reports · doi:10.1038/s41598-017-01931-w · Cited by 154 · see citing works
Tedesco, S. A., Barton, J. J., & O’Flynn, B. (2017) · Sensors · doi:10.3390/s17061277 · Cited by 126 · see citing works
Age-Dependent Changes in the Cerebrospinal Fluid Proteome by Slow Off-Rate Modified Aptamer Array
Baird, G. S., Nelson, S. K., Keeney, T. R., Stewart, A., Williams, S., Kraemer, S., Peskind, E. R., & Montine, T. J. (2012) · The American Journal of Pathology · doi:10.1016/j.ajpath.2011.10.024 · Cited by 110 · see citing works
Deep Learning using Convolutional LSTM estimates Biological Age from Physical Activity
Rahman, S. A., & Adjeroh, D. (2019) · Scientific Reports · doi:10.1038/s41598-019-46850-0 · Cited by 92 · see citing works
Deep Survival: A Deep Cox Proportional Hazards Network.Preprint
Katzman, J., Shaham, U., Cloninger, A., Bates, J., Jiang, T., & Kluger, Y. (2016) · arXiv (Cornell University) · Cited by 81 · see citing works
Tarkhov, A. E., Alla, R., Ayyadevara, S., Pyatnitskiy, M. A., Men’shikov, L. I., Reis, R. J. S., & Fedichev, P. O. (2019) · Scientific Reports · doi:10.1038/s41598-019-43075-z · Cited by 67 · see citing works
Self-citationGao, X., Zhang, Y., Saum, K.-U., Schöttker, B., Breitling, L. P., & Brenner, H. (2016) · Epigenetics · doi:10.1080/15592294.2016.1271855 · Cited by 64 · see citing works
Quantitative characterization of biological age and frailty based on locomotor activity records
Pyrkov, T. V., Getmantsev, E., Zhurov, B., Avchaciov, K., Pyatnitskiy, M., Menshikov, L., Khodova, K., Gudkov, A. V., & Fedichev, P. O. (2018) · Aging · doi:10.18632/aging.101603 · Cited by 55 · see citing works
Self-citationProtein profiling reveals consequences of lifestyle choices on predicted biological aging
Enroth, S., Enroth, S. B., Johansson, Å., & Gyllensten, U. B. (2015) · Scientific Reports · doi:10.1038/srep17282 · Cited by 52 · see citing works
Di, J., Spira, A. P., Bai, J., Urbanek, J. K., Leroux, A., Wu, M. N., Resnick, S. M., Simonsick, E. M., Ferrucci, L., Schrack, J. A., et al. (2019) · Statistics in Biosciences · doi:10.1007/s12561-019-09236-4 · Cited by 52 · see citing works
Wang, Z., Li, L., Glicksberg, B. S., Israel, A., Dudley, J. T., & Ma’ayan, A. (2017) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2017.11.003 · Cited by 51 · see citing works
Strehler-Mildvan correlation is a degenerate manifold of Gompertz fit
Tarkhov, A. E., Men’shikov, L. I., & Fedichev, P. O. (2017) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2017.01.017 · Cited by 39 · see citing works
Self-citationThe Law of Mortality Revisited: Interspecies Comparisons of Mortality
Olshansky, S. J. (2009) · Journal of Comparative Pathology · doi:10.1016/j.jcpa.2009.10.016 · Cited by 28 · see citing works
Development of Tissue-Specific Age Predictors Using DNA Methylation Data
Choi, H., Joe, S., & Nam, H. (2019) · Genes · doi:10.3390/genes10110888 · Cited by 28 · see citing works
Deep biomarkers of aging are population-dependent
Cohen, A. A., Morissette-Thomas, V., Ferrucci, L., & Fried, L. P. (2016) · Aging · doi:10.18632/aging.101034 · Cited by 21 · see citing works
Critical dynamics of gene networks is a mechanism behind ageing and Gompertz lawPreprint
Podolsky, D., Molodtcov, I., Zenin, A., Kogan, V., Men’shikov, L. I., Gladyshev, V. N., Reis, R. J. S., & Fedichev, P. O. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04307 · Cited by 17 · see citing works
Self-citationLevy, G., & Levin, B. L. (2014) · Wiley eBooks · doi:10.1002/9781118645840 · Cited by 11 · see citing works
The Biostatistics of Aging: From Gompertzian Mortality to an Index of Aging-Relatedness
Levy, G., & Levin, B. (2014) · Medical Entomology and Zoology · Cited by 7 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [25]Levine ME Modeling the rate of senescence: can estimated biological age predict mortality more accurately than chronological age? J. Gerontol. A Biol. Sci. Med. Sci 2013 68 667 674 10.1093/gerona/gls233 23213031 PMC3660119 · DOI
Cited by
Sorted by citations
Measuring biological age using omics data
Rutledge, J., Oh, H., & Wyss-Coray, T. (2022) · Nature Reviews Genetics · doi:10.1038/s41576-022-00511-7 · Cited by 570 · see citing works
Human gut microbiome aging clock based on taxonomic profiling and deep learning
Galkin, F., Mamoshina, P., Aliper, A., Lane, E., Moskalev, V., Gladyshev, V. N., & Zhavoronkov, A. (2020) · iScience · doi:10.1016/j.isci.2020.101199 · Cited by 292 · see citing works
Artificial intelligence for aging and longevity research: Recent advances and perspectives
Zhavoronkov, A., Mamoshina, P., Vanhaelen, Q., Scheibye-Knudsen, M., Moskalev, A., & Aliper, A. (2019) · Ageing Research Reviews · doi:10.1016/j.arr.2018.11.003 · Cited by 246 · see citing works
Identification of 12 genetic loci associated with human healthspan
Zenin, A., Tsepilov, Y., Sharapov, S., Getmantsev, E., Menshikov, L. I., Fedichev, P. O., & Aulchenko, Y. (2019) · Communications Biology · doi:10.1038/s42003-019-0290-0 · Cited by 170 · see citing works
Self-citationPyrkov, T. V., Avchaciov, K., Tarkhov, A. E., Menshikov, L. I., Gudkov, A. V., & Fedichev, P. O. (2021) · Nature Communications · doi:10.1038/s41467-021-23014-1 · Cited by 139 · see citing works
Self-citationQuantitative characterization of biological age and frailty based on locomotor activity records
Pyrkov, T. V., Getmantsev, E., Zhurov, B., Avchaciov, K., Pyatnitskiy, M., Menshikov, L., Khodova, K., Gudkov, A. V., & Fedichev, P. O. (2018) · Aging · doi:10.18632/aging.101603 · Cited by 55 · see citing works
Self-citation
- Authors
- Pyrkov, T. V., Slipensky, K., Barg, M., Kondrashin, A., Zhurov, B., Zenin, A., Pyatnitskiy, M., Menshikov, L., Markov, S., & Fedichev, P. O.
- Affiliations
- Moscow Institute of Physics and Technology (RU)
- Corresponding author
- Pyrkov, Timothy V.
- Fedichev, Peter O.
- Venue
- Scientific Reports
- Published
- 2018-03-26
- Volume
- 8
- Issue
- 1
- Pages
- 5210-5210
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC5980076
- OpenAlex
- W2949288398
- Cited by
- 111
- References
- 54
- Citations by year
- 2026: 3 · 2025: 11 · 2024: 14 · 2023: 11 · 2022: 11 · 2021: 24 · 2020: 9 · 2019: 21 · 2018: 7
- FWCI
- 8.47
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Physiology › Physical Activity and Health
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- biological age, chronological age estimation, physical activity, accelerated aging, all-cause mortality, proportional hazards model, mortality prediction, convolutional neural networks, principal component analysis, wearable sensors, health risk monitoring, NHANES
- MeSH terms
- Machine Learning, Deep Learning, Adolescent, Adult, Age Factors, Aged, Aged, 80 and over, Aging, Algorithms, Female, Follow-Up Studies, Humans, Male, Middle Aged, Nutrition Surveys, Software, Exercise, Neural Networks, Computer, Principal Component Analysis, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
