Detecting Low Back Pain from Clinical Narratives Using Machine Learning Approaches

  • Michael Judd
  • Farhana ZulkernineEmail author
  • Brent Wolfrom
  • David Barber
  • Akshay Rajaram
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 903)


Free-text clinical notes recorded during the patients’ visits in the Electronic Medical Record (EMR) system narrates clinical encounters, often using ‘SOAP’ notes (an acronym for subject, objective, assessment, and plan). The free-text notes represent a wealth of information for discovering insights, particularly in medical conditions such as pain and mental illness, where regular health metrics provide very little knowledge about the patients’ medical situations and reactions to treatments. In this paper, we develop a generic text-mining and decision support framework to diagnose chronic low back pain. The framework utilizes open-source algorithms for anonymization, natural language processing, and machine learning to classify low back pain patterns from unstructured free-text notes in the Electronic Medical Record (EMR) system as noted by the primary care physicians during patients’ visits. The initial results show a high accuracy for the limited thirty-four patient labelled data set that we used in this pilot study. We are currently processing a larger data set to test our approach.


Text-mining Natural language processing Machine learning Clinical decision support system Back pain 


  1. 1.
    Soldaini, L., Goharian, N.: QuickUMLS: a fast, unsupervised approach for medical concept extraction (2016)Google 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, 395–405 (2012)CrossRefGoogle Scholar
  3. 3.
    Rau, J.: Medicare’s Readmission Penalties Hit New High. Accessed 15 Jan 2018
  4. 4.
    Hassanzadeh, H., Nguyen, A., Koopman, B.: Evaluation of medical concept annotation systems. In: Proceedings of Australasian Language Technology Association Workshop, pp. 15–24 (2016)Google Scholar
  5. 5.
    Buckley, J., et al.: The feasibility of using natural language processing to extract clinical information from breast pathology reports. J. Pathol. Inform. 3, 23 (2012)CrossRefGoogle Scholar
  6. 6.
    Spasić, I., Livsey, J., Keane, J., Nenadić, G.: Text mining of cancer-related information: review of current status and future directions. Int. J. Med. Inform. 83, 605–623 (2014)CrossRefGoogle Scholar
  7. 7.
    Ford, E., et al.: Extracting information from the text of electronic medical records to improve case detection: a systematic review. J. Am. Med. Inform. Assoc. 23(5), 1007–1015 (2016)CrossRefGoogle Scholar
  8. 8.
    IBM: IBM Watson Health. Accessed 3 Jan 2018
  9. 9.
    Sevenster, M., van Ommering, R., Qjan, Y.: Bridging the text-image gap: a decision support tool for real-time PACS browsing. J. Digit. Imaging 25, 227–239 (2012)CrossRefGoogle Scholar
  10. 10.
    Jensen, K. et al.: Analysis of free text in electronic health records for identification of cancer patient trajectories. Sci. Rep. 7 (2017)Google Scholar
  11. 11.
    OSCAR Canada: About OSCAR. Accessed 28 Oct 2017
  12. 12.
    Bone and Joint Canada: Low Back Pain. Accessed 10 Jan 2018
  13. 13.
    Canadian College of Family Physicians of Canada: Evidence-informed primary care management of low back pain. Accessed 11 Jan 2018
  14. 14.
    Webster, B., Courtney, T., Huang, Y.H., Christiani, D.: Physicians’ initial management of acute low back pain versus evidence-based guidelines. J. Gen. Intern. Med. 20, 1132–1135 (2005)CrossRefGoogle Scholar
  15. 15.
    Devereaux, M.: Low back pain. Prim. Care: Clin. Off. Pract. 31, 33–51 (2004)CrossRefGoogle Scholar
  16. 16.
    Savova, G.K., et al.: Mayo clinical text analysis and knowledge extraction system (cTAKES): architecture, component evaluation and applications. J. Am. Med. Inform. Assoc. 17, 507–513 (2010)CrossRefGoogle Scholar
  17. 17.
    Szlosek, D.A., Ferrett, J.: Using machine learning and natural language processing algorithms to automate the evaluation of clinical decision support in electronic medical record systems. Gener. Evid. Methods Improv. Patient Outcomes 4(3), 1222 (2016)Google Scholar
  18. 18.
    Ferrández, O., South, B.R., Shen, S., et al.: Evaluating current automatic de-identification methods with Veteran’s health administration clinical documents. BMC Med. Res. Methodol. 12, 109 (2012)CrossRefGoogle Scholar
  19. 19.
    Meystre, S., Savova, G., Kipper-Schuler, K., Hurdle, J.F.: Extracting information from textual documents in the electronic health record: a review of recent research. In: Yearbook of Medical Informatics, pp. 128–144 (2008)Google Scholar
  20. 20.
    Moja, L., et al.: Effectiveness of computerized decision support systems linked to electronic health records: a systematic review and meta-analysis. Am. J. Public Health 104(10), 104–116 (2014)Google Scholar
  21. 21.
    Okazaki, N., Tsujii, J.: Simple and efficient algorithm for approximate dictionary matching. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 851–859 (2010)Google Scholar
  22. 22.
    Bodenreider, O.: The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res. 32, D267–D270 (2004)CrossRefGoogle Scholar
  23. 23.
    Xu, H., Fu, Z., Chen, Y., et al.: Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases. In: AMIA Annual Symposium Proceedings, pp. 1564–1572 (2011)Google Scholar
  24. 24.
    D’Avolio, L.W., et al.: Evaluation of a generalizable approach to clinical information retrieval using the automated retrieval console (ARC). J. Am. Med. Inform. Assoc. 17(4), 375–382 (2010)CrossRefGoogle Scholar
  25. 25.
    Centre for Effective Practice: Clinically Organized Relevant Exam. Accessed 20 Aug 2017
  26. 26.
    Neamatullah, I., et al.: Automated de-identification of free-text medical records. BMC Med. Inform. Decis. Mak. 8, 8–32 (2008)CrossRefGoogle Scholar
  27. 27.
    Rudolf, C.N.: Clinical records anonymisation and text extraction (CRATE): an open-source software system. BMC Med. Inform. Decis. Mak. 17, 50 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Michael Judd
    • 1
  • Farhana Zulkernine
    • 1
    Email author
  • Brent Wolfrom
    • 1
  • David Barber
    • 1
  • Akshay Rajaram
    • 1
  1. 1.Queen’s UniversityKingstonCanada

Personalised recommendations