Advertisement

Prediction of Decline in Activities of Daily Living Through Deep Artificial Neural Networks and Domain Adaptation

  • Lorenzo Donati
  • Daniele Fongo
  • Luca CattelaniEmail author
  • Federico Chesani
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11946)

Abstract

In order to improve information available at the clinical level and to better focus resources for preventive interventions, it is paramount to estimate the general exposure to risk of adverse health events, commonly referred as frailty. This study compares the performance of shallow and deep multilayer perceptrons (sMLP and dMLP), and of long short-term memories (LSTM), on the prediction of a subject decline in activities of daily living, with and without a previous autoencoder based domain adaptation from an external dataset. Samples originates from two large epidemiological datasets: the English Longitudinal Study of Ageing (ELSA) and The Irish Longitudinal Study on Ageing, with 107879 and 15710 eligible samples, respectively. Deep networks performed better than shallow ones, while dMLP and LSTM performance were similar. Domain adaptation improved predictive ability in all comparisons. On the bigger ELSA dataset, sMLP attains a Brier score of 0.32 without domain adaptation, and 0.15 with domain adaptation, while dMLP attains 0.20 and 0.11, respectively. Thus, experimental results support the use of deep architectures in the prediction of functional decline, and of domain adaptation when data from another similar domain is available. These results may help improving the state of the art in predictive models for clinical practice and population screening.

Keywords

Artificial neural networks Deep learning Domain adaptation Frailty Risk assessment Transfer learning 

Notes

Acknowledgment

The data relative to ELSA were made available through the United Kingdom Data Archive - www.data-archive.ac.uk. ELSA was developed by a team of researchers based at the NatCen Social Research, University College London and the Institute for Fiscal Studies. The data were collected by NatCen Social Research. The funding is provided by the National Institute of Aging in the United States, and a consortium of United Kingdom government departments coordinated by the Office for National Statistics.

TILDA is an interinstitutional initiative led by Trinity College Dublin. TILDA data have been co-funded by the Government of Ireland through the Office of the Minister for Health and Children, by Atlantic Philanthropies, and by Irish Life; have been collected under the Statistics Act, 1993, of the Central Statistics Office. The project has been designed and implemented by the TILDA study team, Department of Health and Children. Copyright and all other intellectual property rights relating to the data are vested in TILDA. Ethical approval for each wave of data collection is granted by the Trinity College Research Ethics Committee. TILDA data is accessible for free from the following sites: Irish Social Science Data Archive at University College Dublin http://www.ucd.ie/issda/data/tilda/; Interuniversity Consortium for Political and Social Research at the University of Michigan (http://www.icpsr.umich.edu/icpsrweb/ICPSR/studies/34315).

The original data creators, depositors or copyright holders, the funders of the data collections and the archives of the datasets bear no responsibility for their further analysis or interpretation presented here.

Conflict of Interest

All authors declare no competing interests and to be aware of the submission of this manuscript.

References

  1. 1.
    Bengio, Y.: Deep learning of representations for unsupervised and transfer learning. In: JMLR Workshop Conference Proceedings, vol. 7, pp. 1–20 (2011).  https://doi.org/10.1109/IJCNN.2011.6033302
  2. 2.
    Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. CoRR abs/1206.5533 (2012). http://arxiv.org/abs/1206.5533
  3. 3.
    Bengio, Y.: Deep learning of representations: looking forward. In: Dediu, A.-H., Martín-Vide, C., Mitkov, R., Truthe, B. (eds.) SLSP 2013. LNCS, vol. 7978, pp. 1–37. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-39593-2_1CrossRefGoogle Scholar
  4. 4.
    Bengio, Y., Boulanger-Lewandowski, N., Pascanu, R.: Advances in optimizing recurrent networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8624–8628. IEEE (2013)Google Scholar
  5. 5.
    Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013).  https://doi.org/10.1109/TPAMI.2013.50, http://www.ncbi.nlm.nih.gov/pubmed/23787338CrossRefGoogle Scholar
  6. 6.
    Berrendero, J.R., Cuevas, A., Torrecilla, J.L.: The mRMR variable selection method: a comparative study for functional data. J. Stat. Comput. Simul. 86(5), 891–907 (2016).  https://doi.org/10.1080/00949655.2015.1042378MathSciNetCrossRefGoogle Scholar
  7. 7.
    Bouillon, K., et al.: Measures of frailty in population-based studies: an overview. BMC Geriatr. 13(1), 64 (2013).  https://doi.org/10.1186/1471-2318-13-64CrossRefGoogle Scholar
  8. 8.
    Brier, G.W.: Verification of forecasts expressed in terms of probability. Mon. Weather Rev. 78, 1 (1950).  https://doi.org/10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2CrossRefGoogle Scholar
  9. 9.
    Buckinx, F., Rolland, Y., Reginster, J.Y., Ricour, C., Petermans, J., Bruyère, O.: Burden of frailty in the elderly population: perspectives for a public health challenge. Arch. Public Health 73(1), 19 (2015).  https://doi.org/10.1186/s13690-015-0068-xCrossRefGoogle Scholar
  10. 10.
    Buz, J., Cortés-Rodríguez, M.: Measurement of the severity of disability in community-dwelling adults and older adults: interval-level measures for accurate comparisons in large survey data sets. BMJ Open 6(9), e011842 (2016).  https://doi.org/10.1136/bmjopen-2016-011842, https://bmjopen.bmj.com/content/6/9/e011842CrossRefGoogle Scholar
  11. 11.
    Chang, S.F., Lin, P.L.: Frail phenotype and mortality prediction: a systematic review and meta-analysis of prospective cohort studies. Int. J. Nurs. Stud. 52(8), 1362–1374 (2015).  https://doi.org/10.1016/j.ijnurstu.2015.04.005CrossRefGoogle Scholar
  12. 12.
    Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Meas. 20(1), 37–46 (1960).  https://doi.org/10.1177/001316446002000104CrossRefGoogle Scholar
  13. 13.
    Csurka, G.: Domain adaptation for visual applications: a comprehensive survey, pp. 1–46. CoRR abs/1702.05374 (2017). http://arxiv.org/abs/1702.05374
  14. 14.
    Daniels, R., Van Rossum, E., Beurskens, A., Van Den Heuvel, W., De Witte, L.: The predictive validity of three self-report screening instruments for identifying frail older people in the community. BMC Public Health 12(1), 69 (2012).  https://doi.org/10.1186/1471-2458-12-69CrossRefGoogle Scholar
  15. 15.
    De Lepeleire, J., Iliffe, S., Mann, E., Degryse, J.M.: Frailty: an emerging concept for general practice. Br. J. Gen. Pract. 59(562), 364–369 (2009).  https://doi.org/10.3399/bjgp09X420653CrossRefGoogle Scholar
  16. 16.
    Deng, J., Zhang, Z., Eyben, F., Schuller, B.: Autoencoder-based unsupervised domain adaptation for speech emotion recognition. IEEE Signal Process. Lett. 21(9), 1068–1072 (2014).  https://doi.org/10.1109/LSP.2014.2324759CrossRefGoogle Scholar
  17. 17.
    Dent, E., Kowal, P., Hoogendijk, E.O.: Frailty measurement in research and clinical practice: a review. Eur. J. Intern. Med. 31, 3–10 (2016).  https://doi.org/10.1016/j.ejim.2016.03.007CrossRefGoogle Scholar
  18. 18.
    Donati, L.: Domain adaptation through deep neural networks for health informatics (2017)Google Scholar
  19. 19.
    Erhan, D., Courville, A., Vincent, P.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625–660 (2010).  https://doi.org/10.1145/1756006.1756025, http://portal.acm.org/citation.cfm?id=1756025
  20. 20.
    Fongo, D.: Previsione del declino funzionale tramite l’utilizzo di reti neurali ricorrenti (2017)Google Scholar
  21. 21.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 9, pp. 249–256. PMLR, Chia Laguna Resort, Sardinia, Italy, 13–15 May 2010. http://proceedings.mlr.press/v9/glorot10a.html
  22. 22.
    Glorot, X., Bordes, A., Bengio, Y.: Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th International Conference on Machine Learning, no. 1, pp. 513–520 (2011). http://www.icml-2011.org/papers/342_icmlpaper.pdf
  23. 23.
    Gobbens, R.J.J., Van Assen, M.A.L.M.: The prediction of ADL and IADL disability using six physical indicators of frailty: a longitudinal study in the Netherlands. Curr. Gerontol. Geriatr. Res. 2014 (2014).  https://doi.org/10.1155/2014/358137CrossRefGoogle Scholar
  24. 24.
    Haley, S.M., et al.: Late life function and disability instrument: I. Development and evaluation of the disability component. J. Gerontol. A Biol. Sci. Med. Sci. 57(4), M209–M216 (2002)CrossRefGoogle Scholar
  25. 25.
    Haley, S.M., et al.: Late life function and disability instrument: II. Development and evaluation of the function component. J. Gerontol. A Biol. Sci. Med. Sci. 57(4), M217–M222 (2002).  https://doi.org/10.1093/gerona/57.4.M217CrossRefGoogle Scholar
  26. 26.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1–32 (1997).  https://doi.org/10.1144/GSL.MEM.1999.018.01.02CrossRefGoogle Scholar
  27. 27.
    Banks, J., Batty, G.D., Nazroo, J., Steptoe, A.: The dynamics of ageing: evidence from the English Longitudinal Study of Ageing 2002–15 (Wave 7). The Institute for Fiscal Studies (2016)Google Scholar
  28. 28.
    Kenny, R.A.: The Irish longitudinal study on ageing (TILDA) 2009–2011 (2014).  https://doi.org/10.3886/ICPSR34315.v1
  29. 29.
    Kenny, R.A., et al.: The design of the Irish longitudinal study on ageing. Lifelong Learn. (2010)Google Scholar
  30. 30.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs/1412.6980 (2014). http://arxiv.org/abs/1412.6980
  31. 31.
    Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79–86 (1951)MathSciNetCrossRefGoogle Scholar
  32. 32.
    Kumar, R., Indrayan, A.: Receiver operating characteristic (ROC) curve for medical researchers. Indian Pediatr. 48(4), 277–287 (2011).  https://doi.org/10.1007/s13312-011-0055-4CrossRefGoogle Scholar
  33. 33.
    Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015).  https://doi.org/10.1038/nature14539CrossRefGoogle Scholar
  34. 34.
    Lee, L., Heckman, G., Molnar, F.J.: Frailty: identifying elderly patients at high risk of poor outcomes. Can. Fam. physician Mèdecin Fam. Can. 61(3), 227–231 (2015). http://www.cfp.ca/content/61/3/227Google Scholar
  35. 35.
    Lee, L., Patel, T., Hillier, L.M., Maulkhan, N., Slonim, K., Costa, A.: Identifying frailty in primary care: a systematic review. Geriatr. Gerontol. Int. 17(10), 1358–1377 (2017).  https://doi.org/10.1111/ggi.12955CrossRefGoogle Scholar
  36. 36.
    Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning. arXiv preprint, pp. 1–38 (2015).  https://doi.org/10.1145/2647868.2654889, http://arxiv.org/abs/1506.00019
  37. 37.
    Lipton, Z.C., Kale, D.C., Elkan, C., Wetzell, R.: Learning to diagnose with LSTM recurrent neural networks. In: ICLR, pp. 1–18 (2015). http://arxiv.org/abs/1511.03677
  38. 38.
    Lisboa, P.: A review of evidence of health benefit from artificial neural networks in medical intervention. Neural Netw. 15(1), 11–39 (2002).  https://doi.org/10.1016/S0893-6080(01)00111-3CrossRefGoogle Scholar
  39. 39.
    Markle-Reid, M., Browne, G.: Conceptualizations of frailty in relation to older adults. J. Adv. Nurs. 44(1), 58–68 (2003).  https://doi.org/10.1046/j.1365-2648.2003.02767.xCrossRefGoogle Scholar
  40. 40.
    Miotto, R., Wang, F., Wang, S., Jiang, X., Dudley, J.T.: Deep learning for healthcare: review, opportunities and challenges. Brief. Bioinform. (February) 1–11 (2017).  https://doi.org/10.1093/bib/bbx044CrossRefGoogle Scholar
  41. 41.
    Patel, V.M., Gopalan, R., Li, R., Chellappa, R.: Visual domain adaptation: a survey of recent advances. IEEE Signal Process. Mag. 32(3), 53–69 (2015).  https://doi.org/10.1109/MSP.2014.2347059CrossRefGoogle Scholar
  42. 42.
    Prechelt, L.: Early stopping—but when? In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 53–67. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-35289-8_5CrossRefGoogle Scholar
  43. 43.
    Prieto, A., et al.: Neural networks: an overview of early research, current frameworks and new challenges. Neurocomputing 214, 242–268 (2016).  https://doi.org/10.1016/j.neucom.2016.06.014CrossRefGoogle Scholar
  44. 44.
    Purushotham, S., Carvalho, W., Nilanon, T., Liu, Y.: Variational adversarial deep domain adaptation for health care time series analysis. In: 29th Conference on Neural Information Processing System (NIPS) (2016). https://wcarvalho.github.io/files/nips_2016/VADA_main.pdf
  45. 45.
    Puts, M.T., et al.: Interventions to prevent or reduce the level of frailty in community-dwelling older adults: a scoping review of the literature and international policies. Age Ageing 46(3), 383–392 (2017).  https://doi.org/10.1093/ageing/afw247CrossRefGoogle Scholar
  46. 46.
    Ravi, D., et al.: Deep learning for health informatics. IEEE J. Biomed. Health Inform. 21(1), 1 (2016).  https://doi.org/10.1109/JBHI.2016.2636665, http://ieeexplore.ieee.org/document/7801947/CrossRefGoogle Scholar
  47. 47.
    Robert, C., Arreto, C.D., Azerad, J., Gaudy, J.F.: Bibliometric overview of the utilization of artificial neural networks in medicine and biology. Scientometrics 59(1), 117–130 (2004).  https://doi.org/10.1023/B:SCIE.0000013302.59845.34CrossRefGoogle Scholar
  48. 48.
    Song, X., Mitnitski, A., Cox, J., Rockwood, K.: Comparison of machine learning techniques with classical statistical models in predicting health outcomes. Medinfo 11, 736–740 (2004)Google Scholar
  49. 49.
    Spector, W.D., Fleishman, J.: Combining activities of daily living with instrumental activities of daily living to measure functional disability. J. Gerontol. Ser. B Psychol. Sci. Soc. Sci. 53(1), S46–S57 (1998)CrossRefGoogle Scholar
  50. 50.
    Steptoe, A., Breeze, E., Banks, J., Nazroo, J.: Cohort profile: the English longitudinal study of ageing. Int. J. Epidemiol. 42(6), 1640–1648 (2013).  https://doi.org/10.1093/ije/dys168CrossRefGoogle Scholar
  51. 51.
    Tak, E., Kuiper, R., Chorus, A., Hopman-Rock, M.: Prevention of onset and progression of basic ADL disability by physical activity in community dwelling older adults: a meta-analysis. Ageing Res. Rev. 12(1), 329–338 (2013).  https://doi.org/10.1016/j.arr.2012.10.001CrossRefGoogle Scholar
  52. 52.
    Vermeulen, J., Neyens, J.C., Van Rossum, E., Spreeuwenberg, M.D., De Witte, L.P.: Predicting ADL disability in community-dwelling elderly people using physical frailty indicators: a systematic review. BMC Geriatr. 11, 33 (2011).  https://doi.org/10.1186/1471-2318-11-33CrossRefGoogle Scholar
  53. 53.
    Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of 25th International Conference on Machine Learning, ICML 2008, pp. 1096–1103 (2008).  https://doi.org/10.1145/1390156.1390294, http://portal.acm.org/citation.cfm?doid=1390156.1390294
  54. 54.
    Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, ICML 2008, pp. 1096–1103. ACM, New York (2008).  https://doi.org/10.1145/1390156.1390294
  55. 55.
    Wang, M., Deng, W.: Deep visual domain adaptation: a survey. arXiv preprint (2018). http://arxiv.org/abs/1802.03601CrossRefGoogle Scholar
  56. 56.
    Weber, M., et al.: Feasibility and effectiveness of intervention programmes integrating functional exercise into daily life of older adults: a systematic review. Gerontology 64, 172–187 (2017).  https://doi.org/10.1159/000479965, http://www.ncbi.nlm.nih.gov/pubmed/28910814CrossRefGoogle Scholar
  57. 57.
    Weiss, K., Khoshgoftaar, T.M., Wang, D.D.: A survey of transfer learning. J. Big Data 3, 9 (2016).  https://doi.org/10.1186/s40537-016-0043-6CrossRefGoogle Scholar
  58. 58.
    Whelan, B.J., Savva, G.M.: Design and methodology of the Irish longitudinal study on ageing. J. Am. Geriatr. Soc. 61, S265–S268 (2013).  https://doi.org/10.1111/jgs.12199CrossRefGoogle Scholar
  59. 59.
    Zhou, Z.H., Liu, X.Y.: Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans. Knowl. Data Eng. 18(1), 63–77 (2006).  https://doi.org/10.1109/TKDE.2006.17MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringUniversity of BolognaBolognaItaly

Personalised recommendations