Words prediction based on N-gram model for free-text entry in electronic health records

  • Azita Yazdani
  • Reza Safdari
  • Ali Golkar
  • Sharareh R. Niakan KalhoriEmail author
Part of the following topical collections:
  1. Special Issue on Application of Artificial Intelligence in Health Research


The process of documentation is one of the most important parts of electronic health records (EHR). It is time-consuming, and up until now, available documentation procedures have not been able to overcome this type of EHR limitations. Thus, entering information into EHR still has remained a challenge. In this study, by applying the trigram language model, we presented a method to predict the next words while typing free texts. It is hypothesized that using this system may save typing time of free text. The words prediction model introduced in this research was trained and tested on the free texts regarding to colonoscopy, transesophageal echocardiogram, and anterior-cervical-decompression. Required time of typing for each of the above-mentioned reports calculated and compared with manual typing of the same words. It is revealed that 33.36% reduction in typing time and 73.53% reduction in keystroke. The designed system reduced the time of typing free text which might be an approach for EHRs improvement in terms of documentation.


Electronic health record Data capture Natural language processing Word prediction N-gram Trigram model Free-text Data entry 


Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Shah S, et al. Neural networks for mining the associations between diseases and symptoms in clinical notes. Health Inf Sci Syst. 2019;7(1):1.Google Scholar
  2. 2.
    Finn C. Narrative nursing notes in the electronic health record: a key communication tool. Online J Nurs Inform. 2015;19(2):3.Google Scholar
  3. 3.
    Pollard SE, et al. How physicians document outpatient visit notes in an electronic health record. Int J Med Inform. 2013;82(1):39–46.Google Scholar
  4. 4.
    Shah AD, Martinez C, Hemingway H. The freetext matching algorithm: a computer program to extract diagnoses and causes of death from unstructured text in electronic health records. BMC Med Inform Decis Mak. 2012;12(1):88.Google Scholar
  5. 5.
    Cannon J, Lucci S. Transcription and EHRs: benefits of a blended approach. J AHIMA. 2010;81(2):36–40.Google Scholar
  6. 6.
    Abdelhak M, Grostick S, Hanken MA. Health Information: Management of a Strategic Resource. St. Louis: Elsevier; 2014.Google Scholar
  7. 7.
    Rosenbloom ST, et al. Generating clinical notes for electronic health record systems. Appl Clin Inform. 2010;1(3):232.Google Scholar
  8. 8.
    Liu W, et al. A genetic algorithm enabled ensemble for unsupervised medical term extraction from clinical letters. Health Inf Sci Syst. 2015;3(1):5.Google Scholar
  9. 9.
    Hall JM, Powell J. Understanding the person through narrative. Nurs Res Prac. 2011;2011:293837.Google Scholar
  10. 10.
    Chou D. Health IT and patient safety: building safer systems for better care. JAMA. 2012;308(21):2282.Google Scholar
  11. 11.
    Hoyt RE, Yoshihashi, AK. Health informatics: practical guide for healthcare and information technology professionals. 2014: Scholar
  12. 12.
    Shortliffe EH, Cimino JJ. Biomedical informatics: computer applications in health care and biomedicine. London: Springer; 2013.Google Scholar
  13. 13.
    Rule A, et al. Validating free-text order entry for a note-centric EHR. In: AMIA annual symposium proceedings. 2015. American Medical Informatics Association.Google Scholar
  14. 14.
    Collins SA, et al. Relationship between nursing documentation and patients’ mortality. Am J Crit Care. 2013;22(4):306–13.Google Scholar
  15. 15.
    Zhou L, et al. How many medication orders are entered through free-text in EHRs? A study on hypoglycemic agents. In: AMIA annual symposium proceedings. 2012. American Medical Informatics Association.Google Scholar
  16. 16.
    Rosenbloom ST, et al. Data from clinical notes: a perspective on the tension between structure and flexible documentation. J Am Med Inform Assoc. 2011;18(2):181–6.Google Scholar
  17. 17.
    Han H, Lopp L. Writing and reading in the electronic health record: an entirely new world. Med Edu Online. 2013;18(1):18634.Google Scholar
  18. 18.
    Hripcsak G, et al. Use of electronic clinical documentation: time spent and team interactions. J Am Med Inform Assoc. 2011;18(2):112–7.Google Scholar
  19. 19.
    Embi PJ, et al. Computerized provider documentation: findings and implications of a multisite study of clinicians and administrators. J Am Med Inform Assoc. 2013;20(4):718–26.Google Scholar
  20. 20.
    Yazdani A, et al. Scalable architecture for telemonitoring chronic diseases in order to support the CDSSs in a common platform. Acta Inform Med. 2018;26(3):195–200.MathSciNetGoogle Scholar
  21. 21.
    Kaufman DR, et al. Natural language processing-enabled and conventional data capture methods for input to electronic health records: a comparative usability study. JMIR Med Inform. 2016;4(4):e35.MathSciNetGoogle Scholar
  22. 22.
    Hoyt R, Yoshihashi A. Lessons learned from implementation of voice recognition for documentation in the military electronic health record system. Perspectives in health information management/AHIMA, American Health Information Management Association, 2010. 7 (Winter).Google Scholar
  23. 23.
    Johnson M, et al. A systematic review of speech recognition technology in health care. BMC Med Inform Decis Mak. 2014;14(1):94.Google Scholar
  24. 24.
    Sequeira KS. Electronic health records documentation: nurses attitudes and preferences in a given hospital. 2010, RGUHS.Google Scholar
  25. 25.
    dela Cruz JE, et al. Typed versus voice recognition for data entry in electronic health records: emergency physician time use and interruptions. West J Emerg Med. 2014;15(4):541.Google Scholar
  26. 26.
    Gong Y, Hua L, Wang S. Leveraging user’s performance in reporting patient safety events by utilizing text prediction in narrative data entry. Comput Methods Programs Biomed. 2016;131:181–9.Google Scholar
  27. 27.
    Sas J, Poreba T. Optimal acoustic model complexity selection in polish medical speech recognition. J Med Inform Technol. 2011;17:115–22.Google Scholar
  28. 28.
    Paulett JM, Langlotz CP. Improving language models for radiology speech recognition. J Biomed Inform. 2009;42(1):53–8.Google Scholar
  29. 29.
    Lin C-H, et al. Comparison of a semi-automatic annotation tool and a natural language processing application for the generation of clinical statement entries. J Am Med Inform Assoc. 2014;22(1):132–42.Google Scholar
  30. 30.
    Sevenster M, Aleksovski Z. SNOMED CT saves keystrokes: quantifying semantic autocompletion. In: AMIA annual symposium proceedings. 2010. American Medical Informatics Association.Google Scholar
  31. 31.
    Sevenster M, van Ommering R, Qian Y. Algorithmic and user study of an autocompletion algorithm on a large medical vocabulary. J Biomed Inform. 2012;45(1):107–19.Google Scholar
  32. 32.
    Eng J, Eisner JM. Informatics in radiology (info RAD) radiology report entry with automatic phrase completion driven by language modeling. Radiographics. 2004;24(5):1493–501.Google Scholar
  33. 33.
    Chen C-H, et al. Design and implementation of web-based discharge summary note based on service-oriented architecture. J Med Syst. 2012;36(1):335–45.Google Scholar
  34. 34.
    Ehrler F, Lovis C. Supporting drug prescription through autocompletion. Stud Health Technol Inform. 2013;186:120–4.Google Scholar
  35. 35.
    Gelšvartas J, Simutis R, Maskeliūnas R. User adaptive text predictor for mentally disabled Huntington’s patients. Comput Intell Neurosci. 2016;2016:2.Google Scholar
  36. 36.
    Hua L, Wang S, Gong Y. Text prediction on structured data entry in healthcare. Appl Clin Inform. 2014;5(01):249–63.Google Scholar
  37. 37.
    Spithourakis GP, Petersen SE, Riedel S. Clinical text prediction with numerically grounded conditional language models. arXiv preprint arXiv:1610.06370, 2016.
  38. 38.
    Makkar R, Kaur M, Sharma DV. Word prediction systems: a survey. Adv Comput Sci Inform Technol. 2015;2(2):177–80.Google Scholar
  39. 39.
    Ghayoomi M, Momtazi S. An overview on the existing language models for prediction systems as writing assistant tools. In: IEEE international conference on systems, man and cybernetics, 2009. SMC 2009. IEEE.Google Scholar
  40. 40.
    Sarker A, Gonzalez G. Portable automatic text classification for adverse drug reaction detection via multi-corpus training. J Biomed Inform. 2015;53:196–207.Google Scholar
  41. 41.
    Golkar A, et al. Word sense disambiguation based on number of lexical’s senses weighting in conceptual density. Int J Artif Intell Mechatron. 2014;3(1):12–5.Google Scholar
  42. 42.
    Poissant L, et al. The impact of electronic health records on time efficiency of physicians and nurses: a systematic review. J Am Med Inform Assoc. 2005;12(5):505–16.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Health Information Management, School of Allied Medical SciencesTehran University of Medical SciencesTehranIran
  2. 2.Department of Computer Engineering, Yasooj BranchIslamic Azad UniversityYasoojIran

Personalised recommendations