Skip to main content


Log in

Exploring domains, clinical implications and environmental associations of a deep learning marker of biological ageing

  • Published:
European Journal of Epidemiology Aims and scope Submit manuscript


Deep Neural Networks (DNN) have been recently developed for the estimation of Biological Age (BA), the hypothetical underlying age of an organism, which can differ from its chronological age (CA). Although promising, these population-specific algorithms warrant further characterization and validation, since their biological, clinical and environmental correlates remain largely unexplored. Here, an accurate DNN was trained to compute BA based on 36 circulating biomarkers in an Italian population (N = 23,858; age ≥ 35 years; 51.7% women). This estimate was heavily influenced by markers of metabolic, heart, kidney and liver function. The resulting Δage (BA–CA) significantly predicted mortality and hospitalization risk for all and specific causes. Slowed biological aging (Δage < 0) was associated with higher physical and mental wellbeing, healthy lifestyles (e.g. adherence to Mediterranean diet) and higher socioeconomic status (educational attainment, household income and occupational status), while accelerated aging (Δage > 0) was associated with smoking and obesity. Together, lifestyles and socioeconomic variables explained ~48% of the total variance in Δage, potentially suggesting the existence of a genetic basis. These findings validate blood-based biological aging as a marker of public health in adult Italians and provide a robust body of knowledge on its biological architecture, clinical implications and potential environmental influences.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2

Similar content being viewed by others


  1. Lucia C De, Murphy T, Steves CJ, Dobson RJB. Lifestyle mediates the role of nutrient-sensing pathways in cognitive aging: cellular and epidemiological evidence. Commun Biol [Internet]. Springer US; 2020;1–17. Available from:

  2. Franceschi C, Garagnani P, Parini P, Giuliani C, Santoro A. Inflammaging: a new immune–metabolic viewpoint for age-related diseases. Nat Rev Endocrinol [Internet]. 2018;14:576–90. Available from:

  3. Myint PK, Welch AA. Healthier ageing. London: BMJ. British Medical Journal Publishing Group; 2012.

    Book  Google Scholar 

  4. Cole JH, Franke K. Predicting age using neuroimaging: innovative brain ageing biomarkers. Trends Neurosci Elsevier Ltd. 2017;40:681–90.

    Article  CAS  Google Scholar 

  5. Cole JH, Ritchie SJ, Bastin ME, Valdés Hernández MC, Muñoz Maniega S, Royle N, et al. Brain age predicts mortality. Mol Psychiatry. 2018;23:1385–92.

    Article  CAS  Google Scholar 

  6. Gialluisi A, Di Castelnuovo A, Donati MB, de Gaetano G, Iacoviello L. Machine learning approaches for the estimation of biological aging: the road ahead for population studies. Front Med [Internet]. 2019;6. Available from:

  7. Klemera P, Doubal S. A new approach to the concept and computation of biological age. Mech Ageing Dev. 2006;127:240–8.

    Article  Google Scholar 

  8. Mamoshina P, Kochetov K, Putin E, Cortese F, Aliper A, Lee WS et al. Population specific biomarkers of human aging: a big data study using South Korean, Canadian and Eastern European patient populations. J Gerontol A Biol Sci Med Sci. 2018/01/18. 2018;73:1482–90.

  9. Putin E, Mamoshina P, Aliper A, Korzinkin M, Moskalev A, Kolosov A, et al. Deep biomarkers of human aging: application of deep neural networks to biomarker development. Aging (Albany NY). 2016/05/19. 2016;8:1021–33.

  10. Yamaguchi K, Omori H, Onoue A, Katoh T, Ogata Y, Kawashima H, et al. Novel regression equations predicting lung age from varied spirometric parameters. Respir Physiol Neurobiol [Internet]. Elsevier B.V.; 2012;183:108–14. Available from:

  11. Huan T, Chen G, Liu C, Bhattacharya A, Rong J, Chen BH, et al. Age-associated microRNA expression in human peripheral blood is associated with all-cause mortality and age-related traits. Aging Cell. 2018;17:1–10.

    Article  Google Scholar 

  12. Horvath S. DNA methylation age of human tissues and cell types. Genome Biol [Internet]. BioMed Central; 2013 [cited 2018 Nov 6];14:R115. Available from:

  13. Hannum G, Guinney J, Zhao L, Zhang L, Hughes G, Sadda S, et al. Genome-wide methylation profiles reveal quantitative views of human aging rates. Mol Cell [Internet]. 2013 [cited 2018 Nov 6];49:359–67. Available from:

  14. Marioni RE, Shah S, McRae AF, Chen BH, Colicino E, Harris SE, et al. DNA methylation age of blood predicts all-cause mortality in later life. Genome Biol [Internet]. BioMed Central; 2015 [cited 2018 Nov 26];16:25. Available from:

  15. Chen BH, Marioni RE, Colicino E, Peters MJ, Ward-Caviness CK, Tsai PC, et al. DNA methylation-based measures of biological age: meta-analysis predicting time to death Aging. (Albany NY) Impact J LLC. 2016;8:1844–65.

    CAS  Google Scholar 

  16. Lu AT, Quach A, Wilson JG, Reiner AP, Aviv A, Raj K, et al. DNA methylation GrimAge strongly predicts lifespan and healthspan. Aging (Albany NY). 2019;11:303–27.

    Article  CAS  Google Scholar 

  17. Levine ME, Lu AT, Quach A, Chen BH, Assimes TL, Bandinelli S, et al. An epigenetic biomarker of aging for lifespan and healthspan. Aging (Albany NY). 2018;10:573–91.

    Article  Google Scholar 

  18. Cole JH, Poudel RPK, Tsagkrasoulis D, Caan MWA, Steves C, Spector TD, et al. Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. Neuroimage Elsevier Ltd. 2017;163:115–24.

    Article  Google Scholar 

  19. Mamoshina P, Koche K, Cortese F, Kova A. Blood Biochemistry Analysis to Detect Smoking Status and Quantify Accelerated Aging in Smokers. Sci Rep. 2019;142.

  20. Wood T, Kelly C, Roberts M, Walsh B. An interpretable machine learning model of biological age [version 1; peer review: 2 approved with reservations]. F1000Research. 2019;8:1–16.

    Google Scholar 

  21. Waziry R, Gras L, Sedaghat S, Tiemeier H, Weverling GJ, Ghanbari M, et al. Quantification of biological age as a determinant of age-related diseases in the Rotterdam Study: a structural equation modeling approach. Eur J Epidemiol [Internet]. Springer Netherlands; 2019;34:793–9. Available from:

  22. Pyrkov TV, Fedichev PO. Biological age is a universal marker of aging, stress, and frailty. bioRxiv [Internet]. 2019;578245. Available from:

  23. Hughes A, Smart M, Gorrie-Stone T, Hannon E, Mill J, Bao Y, et al. Socioeconomic position and DNA methylation age acceleration across the life course. Am J Epidemiol. 2018;187:2346–54.

    Article  Google Scholar 

  24. Fiorito G, Polidoro S, Dugué P-A, Kivimaki M, Ponzi E, Matullo G, et al. Social adversity and epigenetic aging: a multi-cohort study on socioeconomic differences in peripheral blood DNA methylation. Sci Rep [Internet]. Nature Publishing Group; 2017 [cited 2018 Nov 26];7:16266. Available from:

  25. Bonaccio M, Di Castelnuovo A, Costanzo S, De Curtis A, Persichillo M, Cerletti C, et al. Socioeconomic trajectories across the life course and risk of total and cause-specific mortality: prospective findings from the Moli-sani Study. J Epidemiol Community Health [Internet]. 2019;73:516 LP – 528. Available from:

  26. Zenin A, Tsepilov Y, Sharapov S, Getmantsev E, Menshikov LI, Fedichev PO, et al. Identification of 12 genetic loci associated with human healthspan. Commun Biol [Internet]. Springer US; 2019;2. Available from:

  27. Joshi PK, Pirastu N, Kentistou KA, Fischer K, Hofer E, Schraut KE, et al. Genome-wide meta-analysis associates HLA-DQA1/DRB1 and LPA and lifestyle factors with human longevity. Nat Commun [Internet]. 2017; Available from:

  28. Mamoshina P, Kochetov K, Putin E, Cortese F, Aliper A, Lee W-S, et al. Population specific biomarkers of human aging: a big data study using South Korean, Canadian and Eastern European patient populations. J Gerontol Ser A [Internet]. 2018;73:1482–90. Available from:

  29. R Core Team. R: A Language and environment for statistical computing [Internet]. Vienna, Austria.: R Foundation for Statistical Computing; 2019. Available from:

  30. Kowarik A, Templ M. Imputation with the R package VIM. J Stat Softw Am Stat Assoc. 2016;74:1–16.

    Google Scholar 

  31. Agnes A, #1 L, Sagayaraj Francis F. Adagrad-An optimizer for stochastic gradient descent [Internet]. Available from:

  32. Biecek P. DALEX: Explainers for complex predictive models in R. J Mach Learn Res [Internet]. 2018 [cited 2020 Apr 10];19:1–5. Available from:

  33. Liu Z, Kuo P-L, Horvath S, Crimmins E, Ferrucci L, Levine M. A new aging measure captures morbidity and mortality risk across diverse subpopulations from NHANES IV: A cohort study. Basu S, editor. PLOS Med [Internet]. Public Library of Science; 2018 [cited 2021 Apr 23];15:e1002718. Available from:

  34. Di Castelnuovo A, Costanzo S, Persichillo M, Olivieri M, De Curtis A, Zito F, et al. Distribution of short and lifetime risks for cardiovascular disease in Italians. Eur J Prev Cardiol [Internet]. 2012 [cited 2020 May 4];19:723–30. Available from:

  35. Bonaccio M, Di Castelnuovo A, Pounis G, De Curtis A, Costanzo S, Persichillo M, et al. Relative contribution of health-related behaviours and chronic diseases to the socioeconomic patterning of low-grade inflammation. Int J Public Health. Springer International Publishing; 2017;62:551–62.

  36. Bonaccio M, Di Castelnuovo A, Costanzo S, Gialluisi A, Persichillo M, Cerletti C, et al. Mediterranean diet and mortality in the elderly: a prospective cohort study and a meta-analysis. Br J Nutr [Internet]. 2018;1–14. Available from:

  37. Costanzo S, Mukamal KJ, Di Castelnuovo A, Bonaccio M, Olivieri M, Persichillo M, et al. Alcohol consumption and hospitalization burden in an adult Italian population: prospective results from the Moli-sani study. Addiction. 2019;114:636–50.

    Article  Google Scholar 

  38. Bonaccio M, Di Castelnuovo A, Costanzo S, De Curtis A, Persichillo M, Cerletti C, et al. Impact of combined healthy lifestyle factors on survival in an adult general population and in high‐risk groups: prospective results from the Moli‐sani Study. J Intern Med [Internet]. 2019;joim.12907. Available from:

  39. Bonaccio M, Di Castelnuovo A, Bonanni A, Costanzo S, De Lucia F, Pounis G, et al. Adherence to a Mediterranean diet is associated with a better health-related quality of life: a possible role of high dietary antioxidant content. BMJ Open. 2013;3.

  40. Bonaccio M, Di Castelnuovo A, Costanzo S, Persichillo M, Donati MB, de Gaetano G, et al. Interaction between education and income on the risk of all-cause mortality: prospective results from the MOLI-SANI study. Int J Public Health. 2016;61:765–76.

    Article  Google Scholar 

  41. Bonaccio M, Di Castelnuovo A, Pounis G, Costanzo S, Persichillo M, Cerletti C, et al. High adherence to the Mediterranean diet is associated with cardiovascular protection in higher but not in lower socioeconomic groups: prospective findings from the Moli-sani study. Int J Epidemiol. 2017;46:1478–87.

    Article  Google Scholar 

  42. Crotti G, Gianfagna F, Bonaccio M, Di Castelnuovo A, Costanzo S, Persichillo M, et al. Body mass index and mortality in elderly subjects from the Moli-Sani study: a possible mediation by low-grade inflammation? Immunol Invest [Internet]. Taylor & Francis; 2018;47:774–89. Available from:

  43. Apolone G, Mosconi P. The Italian SF-36 health survey: translation, validation and norming. J Clin Epidemiol United States. 1998;51:1025–36.

    Article  CAS  Google Scholar 

  44. Ware JEJ, Gandek B. Overview of the SF-36 health survey and the international quality of life assessment (IQOLA) Project. J Clin Epidemiol United States. 1998;51:903–12.

    Article  Google Scholar 

  45. Trichopoulou A, Costacou T, Bamia C, Trichopoulos D. Adherence to a Mediterranean Diet and Survival in a Greek Population. N Engl J Med [Internet]. 2003 [cited 2018 Sep 8];348:2599–608. Available from:

  46. Ainsworth BE, Haskell WL, Whitt MC, Irwin ML, Swartz AM, Strath SJ, et al. Compendium of physical activities: an update of activity codes and MET intensities. Med Sci Sports Exerc [Internet]. 2000 [cited 2018 Sep 8];32:S498–504. Available from:

  47. Woolcott OO, Bergman RN. Relative fat mass (RFM) as a new estimator of whole-body fat percentage—a cross-sectional study in American adult individuals. Sci Rep. 2018;8:1–11.

    Article  CAS  Google Scholar 

  48. Venables WN, Ripley BD. Modern Applied Statistics with R [Internet]. New York: Elsevier; 2002 [cited 2020 Sep 30]. Available from:

  49. Kresovich JK, Taylor JARE. Socioeconomic position and DNA methylation age acceleration across the life course. Am J Epidemiol. 2019;188:487–8.

    Article  Google Scholar 

  50. Inker LA, Schmid CH, Tighiouart H, Eckfeldt JH, Feldman HI, Greene T, et al. Estimating glomerular filtration rate from serum creatinine and cystatin C. N Engl J Med [Internet]. Massachussetts Medical Society; 2012 [cited 2020 Apr 9];367:20–9. Available from:

  51. Sarnak MJ, Katz R, Fried LF, Siscovick D, Kestenbaum B, Seliger S, et al. Cystatin C and aging success. Arch Intern Med Am Med Assoc. 2008;168:147–53.

    Article  CAS  Google Scholar 

  52. Di Castelnuovo A, Veronesi G, Costanzo S, Zeller T, Schnabel RB, de Curtis A, et al. NT-proBNP (N-Terminal Pro-B-Type Natriuretic Peptide) and the Risk of Stroke. Stroke United States. 2019;50:610–7.

    Article  Google Scholar 

  53. Samani NJ, Van Der Harst P. Biological ageing and cardiovascular disease. Heart. BMJ Publishing Group Ltd; 2008. p. 537–9.

  54. Stephan Y, Sutin AR, Terracciano A. Feeling older and risk of hospitalization: Evidence from three longitudinal cohorts. Heal Psychol. American Psychological Association Inc.; 2016;35:634–7.

  55. Hägg S, Jylhävä J. Should we invest in biological age predictors to treat colorectal cancer in older adults? Eur J Surg Oncol. W.B. Saunders Ltd; 2020;46:316–20.

  56. Kresovich JK, Xu Z, O’Brien KM, Weinberg CR, Sandler DP, Taylor JA. Methylation-based biological age and breast cancer risk. J Natl Cancer Inst. 2019;111:1051–8.

    Article  CAS  Google Scholar 

  57. Chen M, Wong EM, Nguyen TL, Dite GS, Stone J, Dugué PA, et al. DNA methylation-based biological age, genome-wide average DNA methylation, and conventional breast cancer risk factors. Sci Rep. 2019;9:1–10.

    Google Scholar 

  58. Christensen K, Thinggaard M, McGue M, Rexbye H, Hjelmborg JVB, Aviv A, et al. Perceived age as clinically useful biomarker of ageing: Cohort study. BMJ. British Medical Journal Publishing Group; 2009;339:1433.

  59. Crocker TF, Brown L, Clegg A, Farley K, Franklin M, Simpkins S, et al. Quality of life is substantially worse for community-dwelling older people living with frailty: systematic review and meta-analysis. Qual Life Res. Springer International Publishing; 2019. p. 2041–56.

  60. Belsky DW, Caspi A, Houts R, Cohen HJ, Corcoran DL, Danese A, et al. Quantification of biological aging in young adults. Proc Natl Acad Sci U S A. National Academy of Sciences; 2015;112:E4104–10.

  61. Quach A, Levine ME, Tanaka T, Lu AT, Chen BH, Ferrucci L, et al. Epigenetic clock analysis of diet, exercise, education, and lifestyle factors. Aging (Albany NY). 2017;9:419–46.

    Article  CAS  Google Scholar 

  62. Gensous N, Garagnani P, Santoro A, Giuliani C, Ostan R, Fabbri C, et al. One-year Mediterranean diet promotes epigenetic rejuvenation with country- and sex-specific effects: a pilot study from the NU-AGE project. GeroScience. GeroScience; 2020.

  63. Steffener J, Habeck C, O’Shea D, Razlighi Q, Bherer L, Stern Y. Differences between chronological and brain age are related to education and self-reported physical activity. Neurobiol Aging. Elsevier Inc; 2016;40:138–44.

  64. Di Castelnuovo A, Costanzo S, Bagnardi V, Donati MB, Iacoviello L, de Gaetano G. Alcohol dosing and total mortality in men and women: an updated meta-analysis of 34 prospective studies. Arch Intern Med United States. 2006;166:2437–45.

    Article  Google Scholar 

  65. D’innocenzo S, Biagi C, Lanari M. Obesity and the mediterranean diet: A review of evidence of the role and sustainability of the mediterranean diet [Internet]. Nutrients. MDPI AG; 2019 [cited 2020 Oct 2]. Available from: /pmc/articles/PMC6627690/?report=abstract

  66. Bonaccio M, Di Castelnuovo A, Costanzo S, Persichillo M, Cerletti C, Donati MB, et al. Socioeconomic trajectories across the life course and risk of all-cause and cardiovascular mortality: Prospective findings from the moli-sani study. Circulation [Internet]. 2018;137:1–13. Available from:

  67. Kaufmann T, van der Meer D, Doan NT, Schwarz E, Lund MJ, Agartz I, et al. Common brain disorders are associated with heritable patterns of apparent aging of the brain. Nat Neurosci. 2019;22:1617–23.

    Article  CAS  Google Scholar 

  68. Jonsson BA, Bjornsdottir G, Thorgeirsson TE, Ellingsen LM, Walters GB, Gudbjartsson DF, et al. Brain age prediction using deep learning uncovers associated sequence variants. Nat Commun [Internet]. Springer US; 2019;10:1–10. Available from:

  69. Song M, Emilsson L, Bozorg SR, Nguyen LH, Joshi AD, Staller K, et al. Risk of colorectal cancer incidence and mortality after polypectomy: a Swedish record-linkage study. Lancet Gastroenterol Hepatol. Elsevier BV; 2020;0.


  1. R:

  2. VIM package:

  3. Keras package:

  4. DALEX package:

  5. MASS package:

  6. BioAge package:

Download references


We thank the BiomarCaRE Investigators for testing some of the markers used in this study and Dr Nina Tirozzi for the refinement of artwork.


Funders had no role in this study design, collection, analysis, and interpretation of data, nor in the writing and submission phase of the manuscript. This study was partially supported by the Italian Ministry of Economic Development (PLATONE project, bando “Agenda Digitale” PON I&C 2014-2020; Prog. n. F/080032/01-03/X35), by the Italian Ministry of Health (grant RF-2018-12367074 to GdG and SC); by the Hypercan Study AIRC “5xMILLE” (n.12237 to LI); and by POR FESR 2014-2020: DD n. 459 27/11/2018. SATIN: Sviluppo di Approcci Terapeutici INnovativi per patologie neoplastiche resistenti ai trattamenti). AG, MB and SC were supported by Fondazione Umberto Veronesi. The Moli-sani Study Investigators thank the Associazione Cuore Sano Onlus (Campobasso, Italy) for its cultural and financial support. The enrolment phase of the Moli-sani Study was supported by research grants from Pfizer Foundation (Rome, Italy), the Italian Ministry of University and Research (MIUR, Rome, Italy) – Programma Triennale di Ricerca, Decreto no. 1588 and Instrumentation Laboratory, Milan, Italy.

Author information

Authors and Affiliations




LI, MBD, ADiC, CC and GdG originally inspired the Moli-sani Study. AG and LI contributed to the conception and design of this study. MP, ADeC and SM carried out biological sample management and measurements, while SC and ADiC performed statistical data elaboration and curation in the Moli-sani Study. EC, MB, SC and ADiC provided technical and theoretical support for statistical analyses. AG analyzed the data and wrote the first draft of the manuscript, with contributions and critical review from all the co-authors.

Corresponding author

Correspondence to Alessandro Gialluisi.

Ethics declarations

Conflict of interest

All Authors were and are independent from funders and declare no conflicts of interest.

Data and Code Availability

The codes supporting the findings of this study are available from the corresponding author ( and/or from the senior author of the manuscript ( upon request. Raw data and the model for validation of the DNN algorithm in independent cohorts (based on top 15 features) are available at the institutional repository

Ethics approval

The Moli-sani Study was approved by the ethical committee of the Catholic University of Rome (on March 8, 2004; approval nr: A-931/03-138-04/CE 2004).

Consent to participate

All the participants provided written informed consent.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

A complete list of the Moli-sani Study Investigators is reported in the Supplementary File.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 1275 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gialluisi, A., Di Castelnuovo, A., Costanzo, S. et al. Exploring domains, clinical implications and environmental associations of a deep learning marker of biological ageing. Eur J Epidemiol 37, 35–48 (2022).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: