Skip to main content
SpringerLink
Log in

An Evaluation on Entity Extraction and Semantic Similarity Metrics to Facilitate Medical Text Analysis Based on WordNet

  • Conference paper
  • First Online:
Design, Operation and Evaluation of Mobile Communications (HCII 2021)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 12796))

Included in the following conference series:

  • 762 Accesses

Abstract

This paper aims to evaluate the previous entity extraction methods and semantic similarity metrics in order to improve the entity extraction and semantic analysis process for narrative text in electronic medical records. With the dataset collected from Medical Information Mart for Intensive Care III (MIMIC-III), our results showed that WordNet-based lemmatization and Part of Speech tagging have more of a significant influence in medical text analysis. For the sematic similarity metrics, the experimental results show that the measure proposed by Lin, which is based on IC, has the highest correlation coefficient with the artificial dataset of r = 0.727. The metric combining Resnik and Tversky’s measures, which is based on features as well as IC, also has relatively stable performance, which indicates that IC and feature are the factors should be particularly considered for the future research.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Sun, W., Cai, Z., Li, Y., Liu, F., Fang, S., Wang, G.: Data processing and text mining technologies on electronic medical records: a review. J. Healthcare Eng. 5, 1–9 (2018)

    Article  Google Scholar 

  2. Hirst, C., Hill, J., Khosla, S., et al.: The application of natural language processing (NLP) technology to enrich electronic medical records (EMRs) for outcomes research in oncology. Value Health 17(03), A6 (2014)

    Article  Google Scholar 

  3. Segura-Bedmar, I., Colón-Ruiz, C., Tejedor-Alonso, M.Á., Moro-Moro, M.: Predicting of anaphylaxis in big data EMR by exploring machine learning approaches. J. Biomed. Inf. 87, 50–59 (2018)

    Article  Google Scholar 

  4. Wang, Y., Wu, S., Li, D., Mehrabi, S., Liu, H.: A part-of-speech term weighting scheme for biomedical information retrieval. J. Biomed. Inf. 63, 379–389 (2016)

    Article  Google Scholar 

  5. Gao, Y., Wang, Y., Wang, P., Gu, L.: Medical named entity extraction from chinese resident admit notes using character and word attention-enhanced neural network. Int. J. Environ. Res. Public Health 17(5), 1–17 (2020)

    Article  Google Scholar 

  6. Linguamatics: The World’S Leading NLP Text Mining Platform for Health Sciences. https://www.linguamatics.com/healthcare. Accessed 19 May 2020

  7. IHTSDO, SNOMED CT Starter Guide. https://www.snomed.org. Accessed 12 Sep 2020

  8. Zhou, L., Plasek, J.M., Mahoney, L.M., et al.: Using medical text extraction, reasoning and mapping system (MTERMS) to process medication information in outpatient clinical notes. In: 2011 AMIA Annual Symposium Proceedings, Minnesota, USA, pp. 1639–1648 (2011)

    Google Scholar 

  9. Fellbaum, C.: WordNet: An Electronic Lexical Database, 1st edn. MIT Press, Cambridge (1998)

    Book  Google Scholar 

  10. Guo, D., Duan, G., Yu, Y., Li, Y., Wu, F., Li, M.: A disease inference method based on symptom extraction and bidirectional long short-term memory networks. Methods 173, 75–82 (2020)

    Article  Google Scholar 

  11. Miller, G., Charles, W.: Contextual correlates of semantic similarity. Lang. Cogn. Process. 6(01), 1–28 (2007)

    Article  Google Scholar 

  12. Wu, Z. and Palmer, M.: Verbs semantics and lexical selection. In: Proceedings of the 32nd Annual Meeting on Association for Computational Linguistics, Kyoto, Japan, pp. 133–138 (1994)

    Google Scholar 

  13. Leacock, C., Miller, G., Chodorow, M.: Using corpus statistics and WordNet relations for sense identification. Comput. Linguist. 24(01), 147–165 (1998)

    Google Scholar 

  14. Resnik, P.: Using information content to evaluate semantic similarity in a taxonomy. In: International Joint Conference on Artificial Intelligence, Montreal, Quebec, Canada (1995)

    Google Scholar 

  15. Lin, D.: An information-theoretic definition of similarity. In: Proceedings of the Fifteenth International Conference on Machine Learning (ICML), Madison, Wisconsin, USA, pp. 296–304 (1998)

    Google Scholar 

  16. Tversky, A.: Features of similarity. Psychol. Rev. 84(02), 327–352 (1977)

    Article  Google Scholar 

  17. Pirró, G.: A semantic similarity metric combining features and intrinsic information content. Data Knowl. Eng. 68(11), 1289–1308 (2009)

    Article  Google Scholar 

  18. Zhou, Z., Wang, Y., Gu, J.: A new model of information content for semantic similarity in WordNet. In: International Conference on Future Generation Communication and Networking Symposia, IEEE Computer Society, Hainan, China, pp. 85–89 (2009)

    Google Scholar 

  19. Li, Y., Bandar, Z.A., McLean, D.: An approach for measuring semantic similarity between words using multiple information sources. IEEE Trans. Knowl. Data Eng. 15(04), 871–882 (2003)

    Article  Google Scholar 

  20. Dong, C., Yan, J., Fang, L., Shi, B.: Measure semantic distance in WordNet based on directed graph search. In: International Conference on E-Learning, E-Business, Enterprise Information Systems, and E-Government, Las Vegas, Nevada, USA, pp. 57–60 (2009).

    Google Scholar 

  21. Johnson, AEW., Pollard, TJ., Shen, L., et al.: MIMIC-III, a freely accessible critical care database. Scientific Data 3, 1–9 (2016)

    Google Scholar 

  22. Goldberger, A.L., Amaral, L.A., Glass, L., et al.: Physiobank, physiotoolkit, and physionet components of a new research resource for complex physiologic signals. Circulation 101(23), 215-e220 (2000)

    Article  Google Scholar 

  23. WordNet Interface. https://www.nltk.org/howto/wordnet.html. Accessed 10 Dec 2020

  24. Erra, U., Senatore, S., Minnella, F., Caggianese, G.: Approximate TF–IDF based on topic extraction from massive message stream using the GPU. Inf. Sci. 292, 143–161 (2015)

    Article  Google Scholar 

  25. Jha, N. K.: An approach towards text to emoticon conversion and vice-versa using NLTK and WordNet. In: 2nd International Conference on Data Science and Business Analytics (ICDSBA), ChangSha, Hunan, China, pp. 161–166 (2018)

    Google Scholar 

  26. Ingvaldsen, J., Veres, C.: Using the WordNet ontology for interpreting medical records. In: CAiSE'04 Workshops in connection with the 16th Conference on Advanced Information Systems Engineering, Knowledge and Model Driven Information Systems Engineering for Networked Organizations, Proceedings, Riga, Latvia, vol. 3, pp. 355–358 (2014)

    Google Scholar 

  27. McInnes, B.T., Pedersen, T., Pakhomov, S.V.: UMN medical residents similarity/relatedenss set (UMNSRS-Similarity and UMNSRS-Relatedenss): semantic similarity and relatedness between clinical terms: an experimental study. In: AMIA Annual Symposium proceedings, Washington, DC, USA, pp. 572–6 (2010)

    Google Scholar 

  28. Mari, D.D., Kotz, S., Drouet, D.: Correlation and Dependence: An Introspection, 1st edn. Imperial College Press, London (2001)

    Book  Google Scholar 

  29. Tang, B., Wu, Y., Jiang, M., et al.: A hybrid system for temporal information extraction from clinical text. J. Am. Med. Inf. Assoc. 20(05), 828–835 (2013)

    Article  Google Scholar 

  30. Lester, C.A., Wang, M., Vydiswaran, V.G.V.: Describing the patient experience from Yelp reviews of community pharmacies. J. Am. Pharmacists Assoc. 59(3), 349–355 (2019)

    Article  Google Scholar 

  31. Ahsaee, M.G., Naghibzadeh, M., Naieni, S.E.Y.: Weighted semantic similarity assessment using WordNet. In: International Conference on Computer and Information Science (ICCIS), Chongqing, China, pp. 66–71 (2012)

    Google Scholar 

Download references

Acknowledgments

The authors would like to thank those who had done previous studies in the field of entity extraction and semantic analysis. This work was inspired in part by their contributions. The authors would also like to thank Doctor Donghua Chen for whose instructions for this research are highly appreciated.

Author information

Authors and Affiliations

  1. Beijing Jiaotong University, Beijing, 100044, China

    Qinwei Zhang & Runtong Zhang

Authors
  1. Qinwei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Runtong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Runtong Zhang .

Editor information

Editors and Affiliations

  1. University of Central Florida, Orlando, FL, USA

    Gavriel Salvendy

  2. College of Business, University of West Florida, Pensacola, FL, USA

    June Wei

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, Q., Zhang, R. (2021). An Evaluation on Entity Extraction and Semantic Similarity Metrics to Facilitate Medical Text Analysis Based on WordNet. In: Salvendy, G., Wei, J. (eds) Design, Operation and Evaluation of Mobile Communications. HCII 2021. Lecture Notes in Computer Science(), vol 12796. Springer, Cham. https://doi.org/10.1007/978-3-030-77025-9_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-77025-9_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-77024-2

  • Online ISBN: 978-3-030-77025-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation