Advertisement

Clinical Utility of Machine Learning and Longitudinal EHR Data

  • Walter F. StewartEmail author
  • Jason Roy
  • Jimeng Sun
  • Shahram Ebadollahi
Chapter
Part of the Intelligent Systems Reference Library book series (ISRL, volume 56)

Abstract

The widespread adoption of electronic health records in large health systems, combined with recent advances in data mining and machine learning methods, creates opportunities for the rapid acquisition and translation of knowledge for use in clinical practice. One area of great potential is in risk prediction of chronic progressive diseases from longitudinal medical records. In this Chapter, we illustrate this potential using a case study involving prediction of heart failure. Throughout, we discuss challenges and areas in need of further development.

Keywords

Electronic health records Hearth failure Machine learning Prediction models Text mining 

References

  1. 1.
    Stewart WF, Shah NR, Selna MJ, Paulus RA, Walker JM (2007) Bridging the inferential gap: the electronic health record and clinical evidence. Health Aff 26:w181–91CrossRefGoogle Scholar
  2. 2.
    Fonseca C, Oliveira AG, Mota T, Matias F, Morais H, Costa C, Ceia F (2004) Evaluation of the performance and concordance of clinical questionnaires for the diagnosis of heart failure in primary care. Eur J Heart Fail 6:813–820CrossRefGoogle Scholar
  3. 3.
    Roy J, Hennessy S (2011) Bayesian hierarchical pattern mixture models for comparative effectiveness of drugs and drug classes using healthcare data: a case study involving antihypertensive medications. Stat Biosci 3:79–93CrossRefGoogle Scholar
  4. 4.
    Wu J, Roy J, Stewart WF (2010) Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Med Care 48(6 Suppl):S106–113CrossRefGoogle Scholar
  5. 5.
    Zhu J, Rosset S, Hastie T (2003) 1-norm support vector machines. Neural Inf Proc Sys 2003:16Google Scholar
  6. 6.
    Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer, StanfordCrossRefzbMATHGoogle Scholar
  7. 7.
    IBM. Text analytics tools and runtime for IBM Language ware. Available at: http://www.alphaworks.ibm.com/tech/lrw2011
  8. 8.
    Apache UIMA. Available at: http://uima.apache.org/
  9. 9.
    Norén G, Hopstadius J, Bate A, Star K, Edwards I (2010) Temporal pattern discovery in longitudinal electronic patient records. Data Min Knowl Disc 20:361–387CrossRefGoogle Scholar
  10. 10.
    Mörchen F, Ultsch A (2007) Efficient mining of understandable patterns from multivariate interval time series. Data Min Knowl Disc 15:181–215CrossRefGoogle Scholar
  11. 11.
    Wang W, Yang J (2005) Mining sequential patterns from large data sets, series. Adv Database Sys 28Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Walter F. Stewart
    • 1
    Email author
  • Jason Roy
    • 2
  • Jimeng Sun
    • 3
  • Shahram Ebadollahi
    • 3
  1. 1.Sutter HealthConcordUS
  2. 2.University of PennsylvaniaPhiladelphiaUS
  3. 3.IBM TJ Watson Research CenterHawthorneUS

Personalised recommendations