Healthc Inform Res.  2018 Jul;24(3):179-186. 10.4258/hir.2018.24.3.179.

Temporal Segmentation for Capturing Snapshots of Patient Histories in Korean Clinical Narrative

• Lee W
• Choi J

• KMID: 2418168
• DOI: http://doi.org/10.4258/hir.2018.24.3.179

Abstract

OBJECTIVES
Clinical discharge summaries provide valuable information about patients' clinical history, which is helpful for the realization of intelligent healthcare applications. The documents tend to take the form of separate segments based on temporal or topical information. If a patient's clinical history can be seen as a consecutive sequence of clinical events, then each temporal segment can be seen as a snapshot, providing a certain clinical context at a specific moment. This study aimed to demonstrate a temporal segmentation method of Korean clinical narratives for identifying textual snapshots of patient history as a proof-of-a-concept.
METHODS
Our method uses pattern-based segmentation to approximate human recognition of the temporal or topical shifts in clinical documents. We utilized rheumatic patients' discharge summaries and transformed them into sequences of constituent chunks. We built 97 single pattern functions to denote whether a certain chunk has attributes that indicate that it can be a segment boundary. We manually defined the relationships between the pattern functions to resolve multiple pattern matchings and to make a final decision.
RESULTS
The algorithm segmented 30 discharge summaries and processed 1,849 decision points. Three human judges were asked whether they agreed with the algorithm's prediction, and the agreement percentage on the judges' majority opinion was 89.61%.
CONCLUSIONS
Although this method is based on manually constructed rules, our findings demonstrate that the proposed algorithm can achieve fairly good segmentation results, and it may be the basis for methodological improvement in the future.

Keyword

Natural Language Processing; Electronic Health Records; Automated Pattern Recognition; Rheumatic Diseases

MeSH Terms

Delivery of Health Care
Electronic Health Records
Humans
Methods
Natural Language Processing
Pattern Recognition, Automated
Rheumatic Diseases

Figure

• 

  Figure 1 Snapshots from an original clinical text. Underlines indicate temporal anchoring points.

• 

  Figure 2 Process flow of temporal segmentation in Korean clinical narratives.

• 

  Figure 3 Graphic illustration of the temporal segmentation steps.

Reference

1. Zhou L, Friedman C, Parsons S, Hripcsak G. System architecture for temporal information extraction, representation and reasoning in clinical narrative reports. AMIA Annu Symp Proc. 2005; 2005:869–873.

2. Combi C, Shahar Y. Temporal reasoning and temporal data maintenance in medicine: issues and challenges. Comput Biol Med. 1997; 27(5):353–368.

3. Madkour M, Benhaddou D, Tao C. Temporal data representation, normalization, extraction, and reasoning: A review from clinical domain. Comput Methods Programs Biomed. 2016; 128:52–68.

4. Verhagen M, Gaizauskas R, Schilder F, Hepple M, Katz G, Pustejovsky J. SemEval-2007 task 15: TempEval temporal relation identification. In : 4th International Workshop on Semantic Evaluations; 2007 Jun 23–24; Prague, Czech Republic. p. 75–80.

5. Bramsen PJ. Doing time: inducing temporal graphs [dissertation]. Cambridge (MA): Massachusetts Institute of Technology;2006.

6. Zhou L, Parsons S, Hripcsak G. The evaluation of a temporal reasoning system in processing clinical discharge summaries. J Am Med Inform Assoc. 2008; 15(1):99–106.

7. Pustejovsky J, Stubbs A. Increasing informativeness in temporal annotation. In : 5th Linguistic Annotation Workshop; 2011 Jun 23–24; Portland, OR. p. 152–160.

8. Dligach D, Miller T, Lin C, Bethard S, Savova G. Neural temporal relation extraction. In : 15th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2, Short Papers); 2017 Apr 3–7; Valencia, Spain. p. 746–751.

9. Tao C, Solbrig HR, Sharma DK, Wei WQ, Savova GK, Chute CG. Time-oriented question answering from clinical narratives using semantic-web techniques. In : Patel-Schneider PF, Pan Y, Hitzler P, Mika P, Zhang L, Pan JZ, Horrocks I, editors. International Semantic Web Conference. Heidelberg: Springer;2010. p. 241–256.

10. Park H, Choi J. V-Model: a new perspective for EHR-based phenotyping. BMC Med Inform Decis Mak. 2014; 14:90.

11. Jung H, Allen J, Blaylock N, De Beaumont W, Galescu L, Swift M. Building timelines from narrative clinical records: initial results based-on deep natural language understanding. In : BioNLP 2011 Workshop; 2011 Jun 23–24; Portland, OR. p. 146–154.

12. Monroe M, Lan R, Lee H, Plaisant C, Shneiderman B. Temporal event sequence simplification. IEEE Trans Vis Comput Graph. 2013; 19(12):2227–2236.

13. Angelova G, Boytcheva S. Towards temporal segmentation of patient history in discharge letters. In : Workshop on Biomedical Natural Language Processing; 2011 Sep 15–16; Hissar, Bulgaria. p. 49–54.

14. Bramsen P, Deshpande P, Lee YK, Barzilay R. Finding temporal order in discharge summaries. AMIA Annu Symp Proc. 2006; 2006:81–85.

15. Nakhimovsky A, Rapaport WJ. Discontinuities in narratives. In : 12th Conference on Computational Linguistics; 1988 Aug 22–27; Budapest, Hungary. p. 465–470.

16. Allen J. Natural language understanding. 2nd ed. Redwood City (CA): Pearson;1995.

17. Nakhimovsky A. Aspect, aspectual class, and the temporal structure of narrative. Comput Linguist. 1988; 14(2):29–43.

18. Grosz BJ, Sidner CL. Attention, intentions, and the structure of discourse. Comput Linguist. 1986; 12(3):175–204.

19. Anderson A, Garrod SC, Sanford AJ. The accessibility of pronominal antecedents as a function of episode shifts in narrative text. Q J Exp Psychol A. 1983; 35(3):427–440.

20. Maybury MT. Using discourse focus, temporal focus, and spatial focus to generate multisentential text. In : 5th International Workshop on Natural Language Generation; 1990 Jun 3–6; Dawson, PA. p. 70–78.

21. Passonneau RJ, Litman DJ. Empirical analysis of three dimensions of spoken discourse: segmentation, coherence, and linguistic devices. In : Hovy EH, Scott DR, editors. Computational and conversational discourse. Heidelberg: Springer;1996. p. 161–194.

22. Marcu D. The theory and practice of discourse parsing and summarization. Cambridge (MA): MIT Press;2000.

23. Beeferman D, Berger A, Lafferty J. Text segmentation using exponential models. In : 2nd Conference on Empirical Methods in Natural Language Processing; 1997 Aug 1–2; Providence, RI. p. 37–46.

24. Pevzner L, Hearst MA. A critique and improvement of an evaluation metric for text segmentation. Comput Linguist. 2002; 28(1):19–36.

25. Kim Y, Choi J. Recognizing temporal information in korean clinical narratives through text normalization. Healthc Inform Res. 2011; 17(3):150–155.

26. Chapman WW, Nadkarni PM, Hirschman L, D'Avolio LW, Savova GK, Uzuner O. Overcoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions. J Am Med Inform Assoc. 2011; 18(5):540–543.

27. Seol JW, Yi W, Choi J, Lee KS. Causality patterns and machine learning for the extraction of problem-action relations in discharge summaries. Int J Med Inform. 2017; 98:1–12.

28. Uzuner O, South BR, Shen S, DuVall SL. 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text. J Am Med Inform Assoc. 2011; 18(5):552–556.

29. Sun W, Rumshisky A, Uzuner O. Evaluating temporal relations in clinical text: 2012 i2b2 Challenge. J Am Med Inform Assoc. 2013; 20(5):806–813.

30. Bramsen P, Deshpande P, Lee YK, Barzilay R. Inducing temporal graphs. In : 2006 Conference on Empirical Methods in Natural Language Processing; 2006 Jul 22–23; Sydney, Australia. p. 189–198.