Beyond Volume: The Impact of Complex Healthcare Data on the Machine Learning Pipeline

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10344)


From medical charts to national census, healthcare has traditionally operated under a paper-based paradigm. However, the past decade has marked a long and arduous transformation bringing healthcare into the digital age. Ranging from electronic health records, to digitized imaging and laboratory reports, to public health datasets, today, healthcare now generates an incredible amount of digital information. Such a wealth of data presents an exciting opportunity for integrated machine learning solutions to address problems across multiple facets of healthcare practice and administration. Unfortunately, the ability to derive accurate and informative insights requires more than the ability to execute machine learning models. Rather, a deeper understanding of the data on which the models are run is imperative for their success. While a significant effort has been undertaken to develop models able to process the volume of data obtained during the analysis of millions of digitalized patient records, it is important to remember that volume represents only one aspect of the data. In fact, drawing on data from an increasingly diverse set of sources, healthcare data presents an incredibly complex set of attributes that must be accounted for throughout the machine learning pipeline. This chapter focuses on highlighting such challenges, and is broken down into three distinct components, each representing a phase of the pipeline. We begin with attributes of the data accounted for during preprocessing, then move to considerations during model building, and end with challenges to the interpretation of model output. For each component, we present a discussion around data as it relates to the healthcare domain and offer insight into the challenges each may impose on the efficiency of machine learning techniques.


Healthcare informatics Machine learning Knowledge discovery 


  1. 1.
    Yoo, I., Alafaireet, P., Marinov, M., Pena-Hernandez, K., Gopidi, R., Chang, J.F., Hua, L.: Data mining in healthcare and biomedicine: a survey of the literature. J. Med. Syst. 36(4), 2431–2448 (2012)CrossRefGoogle Scholar
  2. 2.
    Jensen, P.B., Jensen, L.J., Brunak, S.: Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 13(6), 395–405 (2012)CrossRefGoogle Scholar
  3. 3.
    Hughes, G.: How big is big data in healthcare. From a Shot in the Arm Blog (2011)Google Scholar
  4. 4.
    Raghupathi, W., Raghupathi, V.: Big data analytics in healthcare: promise and potential. Health Inf. Sci. Syst. 2(1), 3 (2014)CrossRefGoogle Scholar
  5. 5.
    Han, J., Pei, J., Kamber, M.: Data Mining: Concepts and Techniques. Elsevier (2011)Google Scholar
  6. 6.
    Murphy, K.P.: Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge (2012)zbMATHGoogle Scholar
  7. 7.
    Sammut, C., Webb, G.I.: Encyclopedia of Machine Learning. Springer Science & Business Media, New York (2011)zbMATHGoogle Scholar
  8. 8.
    Kantardzic, M.: Data Mining: Concepts, Models, Methods, and Algorithms. Wiley, Chichester (2011)CrossRefzbMATHGoogle Scholar
  9. 9.
    Diamond, M.: Mastering Medical Coding. Elsevier Health Sciences (2013)Google Scholar
  10. 10.
    Tan, P.N., et al.: Introduction to Data Mining. Pearson Education India (2006)Google Scholar
  11. 11.
    Tsymbal, A.: The problem of concept drift: definitions and related work. Computer Science Department, Trinity College Dublin 106(2) (2004)Google Scholar
  12. 12.
    Rahm, E., Do, H.H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23(4), 3–13 (2000)Google Scholar
  13. 13.
    King, L.A., Fisher, J., Jacquin, L., Zeltwanger, P.: The digital hospital: opportunities and challenges. J. Healthc. Inf. Manag. JHIM 17(1), 37–45 (2002)Google Scholar
  14. 14.
    Andreu-Perez, J., Leff, D.R., Ip, H.M., Yang, G.Z.: From wearable sensors to smart implants–toward pervasive and personalized healthcare. IEEE Trans. Biomed. Eng. 62(12), 2750–2762 (2015)CrossRefGoogle Scholar
  15. 15.
    Kidd, C.D., Orr, R., Abowd, G.D., Atkeson, C.G., Essa, I.A., MacIntyre, B., Mynatt, E., Starner, T.E., Newstetter, W.: The aware home: a living laboratory for ubiquitous computing research. In: Streitz, N.A., Siegel, J., Hartkopf, V., Konomi, S. (eds.) CoBuild 1999. LNCS, vol. 1670, pp. 191–198. Springer, Heidelberg (1999). doi: 10.1007/10705432_17 CrossRefGoogle Scholar
  16. 16.
    Caceres, C.A.: Medical Devices-measurement, Quality Assurance, and Standards. Number 800. ASTM International (1983)Google Scholar
  17. 17.
    Koumoundouros, E.: Clinical engineering and uncertainty in clinical measurements. Australas. Phys. Eng. Sci. Med. 37(3), 467 (2014)CrossRefGoogle Scholar
  18. 18.
    Bland, J.M., Altman, D.G.: Statistics notes: measurement error. BMJ 313(7059), 744 (1996)CrossRefGoogle Scholar
  19. 19.
    Sethi, N., Sethi, J., Torgovnick, E., Arsura, E.: Physiological and non-physiological EEG artifacts. Internet J. Neuromonitoring 5(1) (2007)Google Scholar
  20. 20.
    Wood, A.M., White, I.R., Thompson, S.G.: Are missing outcome data adequately handled? A review of published randomized controlled trials in major medical journals. Clin. Trials 1(4), 368–376 (2004)CrossRefGoogle Scholar
  21. 21.
    Little, R.J., D’agostino, R., Cohen, M.L., Dickersin, K., Emerson, S.S., Farrar, J.T., Frangakis, C., Hogan, J.W., Molenberghs, G., Murphy, S.A., et al.: The prevention and treatment of missing data in clinical trials. N. Engl. J. Med. 367(14), 1355–1360 (2012)CrossRefGoogle Scholar
  22. 22.
    Marlin, B.M., Kale, D.C., Khemani, R.G., Wetzel, R.C.: Unsupervised pattern discovery in electronic health care data using probabilistic clustering models. In: Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium, pp. 389–398. ACM (2012)Google Scholar
  23. 23.
    Azarm-Daigle, M., Kuziemsky, C., Peyton, L.: A review of cross organizational healthcare data sharing. Procedia Comput. Sci. 63, 425–432 (2015)CrossRefGoogle Scholar
  24. 24.
    Quan, H., Li, B., Duncan Saunders, L., Parsons, G.A., Nilsson, C.I., Alibhai, A., Ghali, W.A.: Assessing validity of ICD-9-CM and ICD-10 administrative data in recording clinical conditions in a unique dually coded database. Health Serv. Res. 43(4), 1424–1441 (2008)CrossRefGoogle Scholar
  25. 25.
    International classification of diseases, (ICD-10-CM/PCS) transition, October 2015Google Scholar
  26. 26.
    Meyer, H.: Coding complexity: US health care gets ready for the coming of ICD-10. Health Aff. 30(5), 968–974 (2011)CrossRefGoogle Scholar
  27. 27.
    Fisher, E.S., Whaley, F.S., Krushat, W.M., Malenka, D.J., Fleming, C., Baron, J.A., Hsia, D.C.: The accuracy of medicare’s hospital claims data: progress has been made, but problems remain. Am. J. Public Health 82(2), 243–248 (1992)CrossRefGoogle Scholar
  28. 28.
    MacIntyre, C.R., Ackland, M.J., Chandraraj, E.J., Pilla, J.E.: Accuracy of ICD-9-CM codes in hospital morbidity data, victoria: implications for public health research. Aust. N. Z. J. Public Health 21(5), 477–482 (1997)CrossRefGoogle Scholar
  29. 29.
    Cortes, C., Jackel, L.D., Chiang, W.P., et al.: Limits on learning machine accuracy imposed by data quality. KDD 95, 57–62 (1995)Google Scholar
  30. 30.
    Vapnik, V.N., Vapnik, V.: Statistical Learning Theory, vol. 1. Wiley, New York (1998)zbMATHGoogle Scholar
  31. 31.
    Kearns, M.J., Vazirani, U.V.: An Introduction to Computational Learning Theory. MIT press (1994)Google Scholar
  32. 32.
    Sessions, V., Valtorta, M.: The effects of data quality on machine learning algorithms. ICIQ 6, 485–498 (2006)Google Scholar
  33. 33.
    Knorr, E.M., Ng, R.T., Tucakov, V.: Distance-based outliers: algorithms and applications. VLDB J. Int. J. Very Large Data Bases 8(3–4), 237–253 (2000)CrossRefGoogle Scholar
  34. 34.
    Bacioiu, A.S., Sauntry, D.M., Boyle, J.S., Wong, L.C.W., Leonard, P.F., Chandrasekar, R.: Method and apparatus for analysis and decomposition of classifier data anomalies. US Patent 7,426,497, 16 September 2008Google Scholar
  35. 35.
    Little, R., Rubin, D.: Statistical analysis with missing data (1987)Google Scholar
  36. 36.
    Arbuckle, J.L., Marcoulides, G.A., Schumacker, R.E.: Full information estimation in the presence of incomplete data. In: Advanced Structural Equation Modeling: Issues and Techniques, vol. 243, p. 277 (1996)Google Scholar
  37. 37.
    Rubin, D.B.: Multiple Imputation for Nonresponse in Surveys, vol. 81. Wiley (2004)Google Scholar
  38. 38.
    Collins, L.M., Schafer, J.L., Kam, C.M.: A comparison of inclusive and restrictive strategies in modern missing data procedures. Psychol. Methods 6(4), 330 (2001)CrossRefGoogle Scholar
  39. 39.
    Graham, J.W.: Missing data theory. In: Graham, J.W. (ed.) Missing Data, pp. 3–46. Springer, New York (2012). doi: 10.1007/978-1-4614-4018-5_1 CrossRefGoogle Scholar
  40. 40.
    Rector, A.L., Brandt, S.: Why do it the hard way? The case for an expressive description logic for snomed. J. Am. Med. Inform. Assoc. 15(6), 744–751 (2008)CrossRefGoogle Scholar
  41. 41.
    Lindenauer, P.K., Lagu, T., Shieh, M.S., Pekow, P.S., Rothberg, M.B.: Association of diagnostic coding with trends in hospitalizations and mortality of patients with pneumonia, 2003–2009. JAMA 307(13), 1405–1413 (2012)CrossRefGoogle Scholar
  42. 42.
    Weber, G.M., Mandl, K.D., Kohane, I.S.: Finding the missing link for big biomedical data. JAMA 311(24), 2479–2480 (2014)Google Scholar
  43. 43.
    Stoto, M.A.: Population health in the Affordable Care Act Era, vol. 1. AcademyHealth, Washington, DC (2013)Google Scholar
  44. 44.
    Feldman, K., Hazekamp, N., Chawla, N.V.: Mining the clinical narrative: all text are not equal. In: 2016 IEEE International Conference on Healthcare Informatics (ICHI), pp. 271–280. IEEE (2016)Google Scholar
  45. 45.
    Visscher, P.M., Brown, M.A., McCarthy, M.I., Yang, J.: Five years of GWAS discovery. Am. J. Hum. Genet. 90(1), 7–24 (2012)CrossRefGoogle Scholar
  46. 46.
    Lewis, D.P., Jebara, T., Noble, W.S.: Support vector machine learning from heterogeneous data: an empirical analysis using protein sequence and structure. Bioinformatics 22(22), 2753–2760 (2006)CrossRefGoogle Scholar
  47. 47.
    Diamond, C.C., Mostashari, F., Shirky, C.: Collecting and sharing data for population health: a new paradigm. Health Aff. 28(2), 454–466 (2009)CrossRefGoogle Scholar
  48. 48.
    Hillestad, R.: Identity crisis: an examination of the costs and benefits of a unique patient identifier for the US health care system. Rand Corporation (2008)Google Scholar
  49. 49.
    Fan, J., Han, F., Liu, H.: Challenges of big data analysis. Natl. Sci. Rev. 1(2), 293–314 (2014)CrossRefGoogle Scholar
  50. 50.
    Johnstone, I.M., Titterington, D.M.: Statistical challenges of high-dimensional data (2009)Google Scholar
  51. 51.
    Lafferty, J.D., Wasserman, L.: Challenges in statistical machine learning. Statistica Sinica 16, 307 (2006)MathSciNetGoogle Scholar
  52. 52.
    He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)CrossRefGoogle Scholar
  53. 53.
    López, V., Fernández, A., García, S., Palade, V., Herrera, F.: An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Inf. Sci. 250, 113–141 (2013)CrossRefGoogle Scholar
  54. 54.
    Box, G.E.: Robustness in the strategy of scientific model building. Robust. Stat. 1, 201–236 (1979)CrossRefGoogle Scholar
  55. 55.
    Oreskes, N., Shrader-Frechette, K., Belitz, K., et al.: Verification, validation, and confirmation of numerical models in the earth sciences. Science 263(5147), 641–646 (1994)CrossRefGoogle Scholar
  56. 56.
    Szummer, M.O.: Learning from partially labeled data. PhD thesis, Massachusetts Institute of Technology (2002)Google Scholar
  57. 57.
    Gensinger Jr., R.A.: Analytics in Healthcare: An Introduction. HIMSS (2014). CPHIMS, FHIMSSGoogle Scholar
  58. 58.
    Glas, A.S., Lijmer, J.G., Prins, M.H., Bonsel, G.J., Bossuyt, P.M.: The diagnostic odds ratio: a single indicator of test performance. J. Clin. Epidemiol. 56(11), 1129–1135 (2003)CrossRefGoogle Scholar
  59. 59.
    Kulis, B., et al.: Metric learning: a survey. Found. Trends® Mach. Learn. 5(4), 287–364 (2013)CrossRefzbMATHMathSciNetGoogle Scholar
  60. 60.
    Arcuri, A., Fraser, G.: Parameter tuning or default values? An empirical investigation in search-based software engineering. Empir. Softw. Eng. 18(3), 594–623 (2013)CrossRefGoogle Scholar
  61. 61.
    Hoos, H.H.: Automated algorithm configuration and parameter tuning. In: Hamadi, Y., Monfroy, E., Saubion, F. (eds.) Autonomous Search, pp. 37–71. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-21434-9_3 CrossRefGoogle Scholar
  62. 62.
    Kelley, C.T.: Iterative methods for optimization. SIAM (1999)Google Scholar
  63. 63.
    Sra, S., Nowozin, S., Wright, S.J.: Optimization for Machine Learning. MIT Press (2012)Google Scholar
  64. 64.
    Lange, K., Chi, E.C., Zhou, H.: A brief survey of modern optimization for statisticians. Int. Stat. Rev. 82(1), 46–70 (2014)CrossRefMathSciNetGoogle Scholar
  65. 65.
    Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Inf. Process. Manage. 45(4), 427–437 (2009)CrossRefGoogle Scholar
  66. 66.
    Zhao, J., Papapetrou, P., Asker, L., Boström, H.: Learning from heterogeneous temporal data in electronic health records. J. Biomed. Inform. 65, 105–119 (2017)CrossRefGoogle Scholar
  67. 67.
    Carter, H., Hofree, M., Ideker, T.: Genotype to phenotype via network analysis. Curr. Opin. Genet. Dev. 23(6), 611–621 (2013)CrossRefGoogle Scholar
  68. 68.
    Feldman, K., Stiglic, G., Dasgupta, D., Kricheff, M., Obradovic, Z., Chawla, N.V.: Insights into population health management through disease diagnoses networks. Sci. Rep. 6, Article no. 30465 (2016)Google Scholar
  69. 69.
    Hunyadi, B., Van Huffel, S., De Vos, M.: The power of tensor decompositions in biomedical applications (2016)Google Scholar
  70. 70.
    Luo, Y., Wang, F., Szolovits, P.: Tensor factorization toward precision medicine. Brief. Bioinform. 18(3), 511–514 (2017)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.University of Notre DameNotre DameUSA
  2. 2.Indiana Biosciences Research InstituteIndianapolisUSA

Personalised recommendations