Predicting age by mining electronic medical records with deep learning characterizes differences between chronological and physiological age

Journal of Biomedical Informatics

Volumn 76, Issue , 2017, Pages 59-68

  Wang, Zichen ^a   Li, Li ^a   Glicksberg, Benjamin S ^a   Israel, Ariel ^b   Dudley, Joel T ^a   Ma'ayan, Avi ^a  

^a MOUNT SINAI SCHOOL OF MEDICINE   (United States)

^b CLALIT HEALTH SERVICES   (Israel)

Author keywords

Age prediction; Aging; Deep learning; Machine learning; Medical records

Indexed keywords

AGING OF MATERIALS; BLOOD PRESSURE; E-LEARNING; FORECASTING; GENES; LEARNING SYSTEMS; MEDICAL COMPUTING;

AGE PREDICTIONS; CHRONOLOGICAL AGE; ELECTRONIC MEDICAL RECORD; GENOME-WIDE ASSOCIATION STUDIES; MEDICAL RECORD; PHYSIOLOGICAL STATE; STANDARD DEVIATION; SYSTOLIC BLOOD PRESSURE;

DEEP LEARNING;

CHOLESTEROL;

ACCURACY; ADOLESCENT; AGE; AGE DETERMINATION; AGED; ANEMIA; ARTICLE; BODY BUILD; BODY WEIGHT; CHOLESTEROL BLOOD LEVEL; COHORT ANALYSIS; ELECTRONIC MEDICAL RECORD; FEMALE; GENE IDENTIFICATION; GENE MAPPING; GENETIC ASSOCIATION; GENETIC VARIABILITY; GENOME-WIDE ASSOCIATION STUDY; HUMAN; HYPERTENSION; INFLAMMATION; LABORATORY TEST; LIFESPAN; LIPID METABOLISM; LIVER INJURY; MALE; MISSENSE MUTATION; PHYSIOLOGICAL AGE; PRIORITY JOURNAL; SINGLE NUCLEOTIDE POLYMORPHISM; SYSTOLIC BLOOD PRESSURE; VERY ELDERLY; VITAL SIGN; ADULT; DATA MINING; ELECTRONIC HEALTH RECORD; GENETIC PREDISPOSITION; LEARNING; MIDDLE AGED; YOUNG ADULT;

ADOLESCENT; ADULT; AGE FACTORS; AGED; AGED, 80 AND OVER; COHORT STUDIES; DATA MINING; ELECTRONIC HEALTH RECORDS; FEMALE; GENETIC PREDISPOSITION TO DISEASE; GENOME-WIDE ASSOCIATION STUDY; HUMANS; LEARNING; MALE; MIDDLE AGED; POLYMORPHISM, SINGLE NUCLEOTIDE; YOUNG ADULT;

EID: 85033378916     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jbi.2017.11.003     Document Type: Article

References (48)

1. Baker Iii, G.T., Sprott, R.L., Biomarkers of aging. Exp. Gerontol. 23:4–5 (1988), 223–239.
2. Sprott, R.L., Biomarkers of aging and disease: introduction and definitions. Exp. Gerontol. 45:1 (2010), 2–4.
3. Bürkle, A., Moreno-Villanueva, M., Bernhard, J., Blasco, M., Zondag, G., Hoeijmakers, J.H.J., Toussaint, O., Grubeck-Loebenstein, B., Mocchegiani, E., Collino, S., et al. MARK-AGE biomarkers of ageing. Mech. Ageing Dev. 151 (2015), 2–12.
4. Lara, J., Cooper, R., Nissan, J., Ginty, A.T., Khaw, K.-T., Deary, I.J., Lord, J.M., Kuh, D., Mathers, J.C., A proposed panel of biomarkers of healthy ageing. BMC Med., 13(1), 2015, 222.
5. Chen, D.P., Morgan, A.A., Butte, A.J., Validating pathophysiological models of aging using clinical electronic medical records. J. Biomed. Inform. 43:3 (2010), 358–364.
6. Simm, A., Nass, N., Bartling, B., Hofmann, B., Silber, R.-E., Navarrete Santos, A., Potential biomarkers of ageing. Biol. Chem. 389:3 (2008), 257–265.
7. Johnson, T.E., Recent results: biomarkers of aging. Exp. Gerontol. 41:12 (2006), 1243–1246.
8. Lixie, E., Edgeworth, J., Shamir, L., Comprehensive analysis of large sets of age-related physiological indicators reveals rapid aging around the age of 55 years. Gerontology 61:6 (2015), 526–533.
9. López-Otín, C., Blasco, M.A., Partridge, L., Serrano, M., Kroemer, G., The hallmarks of aging. Cell 153:6 (2013), 1194–1217.
10. Tacutu, R., Craig, T., Budovsky, A., Wuttke, D., Lehmann, G., Taranukha, D., Costa, J., Fraifeld, V.E., de Magalhães, J.P., Human ageing genomic resources: integrated databases and tools for the biology and genetics of ageing. Nucleic Acids Res. 41:D1 (2012), D1027–D1033.
11. Budovsky, A., Craig, T., Wang, J., Tacutu, R., Csordas, A., Lourenço, J., Fraifeld, V.E., de Magalhães, J.P., LongevityMap: a database of human genetic variants associated with longevity. Trends Genet. 29:10 (2013), 559–560.
12. Lonsdale, J., Thomas, J., Salvatore, M., Phillips, R., Lo, E., Shad, S., Hasz, R., Walters, G., Garcia, F., Young, N., et al. The genotype-tissue expression (GTEx) project. Nat. Genet. 45:6 (2013), 580–585.
13. Yang, J., Huang, T., Petralia, F., Long, Q., Zhang, B., Argmann, C., Zhao, Y., Mobbs, C.V., Schadt, E.E., Zhu, J., et al. Synchronized age-related gene expression changes across multiple tissues in human and the link to complex diseases. Sci. Rep., 5, 2015, 15145.
14. 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. The transcriptional landscape of age in human peripheral blood. Nat. Commun., 6, 2015, 8570.
15. Horvath, S., DNA methylation age of human tissues and cell types. Genome Biol., 14(10), 2013, 3156.
16. Hripcsak, G., Albers, D.J., Next-generation phenotyping of electronic health records. J. Am. Med. Inf. Assoc. 20:1 (2013), 117–121.
17. Gottesman, O., Kuivaniemi, H., Tromp, G., Faucett, W.A., Li, R., Manolio, T.A., Sanderson, S.C., Kannry, J., Zinberg, R., Basford, M.A., et al. The electronic medical records and genomics (eMERGE) network: past, present, and future. Genet. Med. 15:10 (2013), 761–771.
18. Kirby, J.C., Speltz, P., Rasmussen, L.V., Basford, M., Gottesman, O., Peissig, P.L., Pacheco, J.A., Tromp, G., Pathak, J., Carrell, D.S., et al. PheKB: a catalog and workflow for creating electronic phenotype algorithms for transportability. J. Am. Med. Inf. Assoc. 23:6 (2016), 1046–1052.
19. Mo, H., Thompson, W.K., Rasmussen, L.V., Pacheco, J.A., Jiang, G., Kiefer, R., Zhu, Q., Xu, J., Montague, E., Carrell, D.S., et al. Desiderata for computable representations of electronic health records-driven phenotype algorithms. J. Am. Med. Inf. Assoc. 22:6 (2015), 1220–1230.
20. Shivade, C., Raghavan, P., Fosler-Lussier, E., Embi, P.J., Elhadad, N., Johnson, S.B., Lai, A.M., A review of approaches to identifying patient phenotype cohorts using electronic health records. J. Am. Med. Inf. Assoc. 21:2 (2014), 221–230.
21. Miotto, R., Li, L., Kidd, B.A., Dudley, J.T., Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Sci. Rep., 6, 2016, 26094.
22. X. Glorot, Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Aistats, 2010, pp. 249–256.
23. D. Kingma, J. Ba, Adam: a method for stochastic optimization, 2014. arXiv preprint arXiv:14126980.
24. F. Chollet, Keras, 2015. URL .
25. J. Bergstra, O. Breuleux, F. Bastien, P. Lamblin, R. Pascanu, G. Desjardins, J. Turian, D. Warde-Farley, Y. Bengio, Theano: a CPU and GPU math compiler in Python, in: Proc 9th Python in Science Conf, 2010, pp. 1–7.
26. Y. Benjamini, Y. Hochberg, Controlling the false discovery rate: a practical and powerful approach to multiple testing, J.R. Stat. Soc. 57 (1995).
27. Delaneau, O., Marchini, J., Zagury, J.-F., A linear complexity phasing method for thousands of genomes. Nat. Meth. 9:2 (2012), 179–181.
28. Howie, B.N., Donnelly, P., Marchini, J., A flexible and accurate genotype imputation method for the next generation of genome-wide association studies. PLOS Genet., 5(6), 2009, e1000529.
29. Kang, H.M., Sul, J.H., Service, S.K., Zaitlen, N.A., Kong, S.-Y., Freimer, N.B., Sabatti, C., Eskin, E., Variance component model to account for sample structure in genome-wide association studies. Nat. Genet. 42:4 (2010), 348–354.
30. Galinsky Kevin, J., Bhatia, G., Loh, P.-R., Georgiev, S., Mukherjee, S., Patterson Nick, J., Price Alkes, L., Fast principal-component analysis reveals convergent evolution of ADH1B in Europe and East Asia. Am. J. Hum. Genet. 98:3 (2016), 456–472.
31. Galinsky Kevin, J., Loh, P.-R., Mallick, S., Patterson Nick, J., Price Alkes, L., Population structure of UK Biobank and ancient eurasians reveals adaptation at genes influencing blood pressure. Am. J. Hum. Genet. 99:5 (2016), 1130–1139.
32. Obenchain, V., Lawrence, M., Carey, V., Gogarten, S., Shannon, P., Morgan, M., VariantAnnotation: a bioconductor package for exploration and annotation of genetic variants. Bioinformatics 30:14 (2014), 2076–2078.
33. Kuleshov, M.V., Jones, M.R., Rouillard, A.D., Fernandez, N.F., Duan, Q., Wang, Z., Koplev, S., Jenkins, S.L., Jagodnik, K.M., Lachmann, A., et al. Enrichr: a comprehensive gene set enrichment analysis web server 2016 update. Nucleic Acids Res., 2016.
34. Chen, E., Tan, C., Kou, Y., Duan, Q., Wang, Z., Meirelles, G., Clark, N., Ma'ayan, A., Enrichr: interactive and collaborative HTML5 gene list enrichment analysis tool. BMC Bioinf., 14(1), 2013, 128.
35. A. Barbeira, K.P. Shah, J.M. Torres, H.E. Wheeler, E.S. Torstenson, T. Edwards, T. Garcia, G.I. Bell, D. Nicolae, N.J. Cox, MetaXcan: summary statistics based gene-level association method infers accurate PrediXcan results, bioRxiv (2016) 045260.
36. Cleveland, W.S., Robust locally weighted regression and smoothing scatterplots. J. Am. Stat. Assoc. 74:368 (1979), 829–836.
37. Manson, J.E., Willett, W.C., Stampfer, M.J., Colditz, G.A., Hunter, D.J., Hankinson, S.E., Hennekens, C.H., Speizer, F.E., Body weight and mortality among women. N. Engl. J. Med. 333:11 (1995), 677–685.
38. Blagosklonny, M.V., Why men age faster but reproduce longer than women: mTOR and evolutionary perspectives. Aging 2:5 (2010), 265–273.
39. Ahmad, A., Banerjee, S., Wang, Z., Kong, D., Majumdar, A.P.N., Sarkar, F.H., Aging and inflammation: etiological culprits of cancer. Curr. Aging Sci. 2:3 (2009), 174–186.
40. Timberlake, D.S., Nikitin, D., Johnson, N.J., Altekruse, S.F., A longitudinal study of smokeless tobacco use and mortality in the United States. Int. J. Cancer 141:2 (2017), 264–270.
41. Ohtsuka, M., Arase, H., Takeuchi, A., Yamasaki, S., Shiina, R., Suenaga, T., Sakurai, D., Yokosuka, T., Arase, N., Iwashima, M., NFAM1, an immunoreceptor tyrosine-based activation motif-bearing molecule that regulates B cell development and signaling. Proc. Natl. Acad. Sci. USA 101:21 (2004), 8126–8131.
42. Van Leuven, F., Stas, L., Hilliker, C., Miyake, Y., Bilinski, P., Gossler, A., Molecular cloning and characterization of the human interleukin-11 receptor α-chain gene, IL11RA, located on chromosome 9p13. Genomics 31:1 (1996), 65–70.
43. Yang, H.-Y., Kim, S.H., Kim, S.-H., Kim, D.-J., Kim, S.-U., Yu, D.-Y., Yeom, Y.I., Lee, D.-S., Kim, Y.-J., Park, B.-J., The suppression of zfpm-1 accelerates the erythropoietic differentiation of human CD34+ cells. Biochem. Biophys. Res. Commun. 353:4 (2007), 978–984.
44. Kotoh, J., Sasaki, D., Matsumoto, K., Maeda, A., Plekhs1 and Prdx3 are candidate genes responsible for mild hyperglycemia associated with obesity in a new animal model of F344-fa-nidd6 rat. J. Vet. Med. Sci., 78(11), 2016, 1683.
45. Mailman, M.D., Feolo, M., Jin, Y., Kimura, M., Tryka, K., Bagoutdinov, R., Hao, L., Kiang, A., Paschall, J., Phan, L., et al. The NCBI dbGaP database of genotypes and phenotypes. Nat. Genet. 39:10 (2007), 1181–1186.
46. D. Croft, G. O'Kelly, G. Wu, R. Haw, M. Gillespie, L. Matthews, M. Caudy, P. Garapati, G. Gopinath, B. Jassal, et al., Reactome: a database of reactions, pathways and biological processes, Nucleic Acids Res. 39(Suppl. 1) (2011) D691–D697.
47. Ngo, M., Ridgway, N.D., Oxysterol binding protein–related protein 9 (ORP9) is a cholesterol transfer protein that regulates Golgi structure and function. Mol. Biol. Cell 20:5 (2009), 1388–1399.
48. D. Bau, B. Zhou, A. Khosla, A. Oliva, A. Torralba, Network dissection: quantifying interpretability of deep visual representations, 2017. arXiv preprint arXiv:170405796.