Download PDF
CC BY-NC-ND 4.0 · Methods Inf Med 2023; 62(03/04): 110-118
DOI: 10.1055/a-2039-3773
Original Article

An Alternative Application of Natural Language Processing to Express a Characteristic Feature of Diseases in Japanese Medical Records

Yoshinori Yamanouchi
1   Department of Medical Information Science, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan
,
Taishi Nakamura
1   Department of Medical Information Science, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan
,
Tokunori Ikeda
2   Department of Pharmaceutical Sciences, Faculty of Pharmaceutical Sciences, Sojo University, Nishi-ku, Kumamoto, Japan
,
Koichiro Usuku
1   Department of Medical Information Science, Graduate School of Medical Sciences, Kumamoto University, Kumamoto, Japan
› Author Affiliations Funding This study was supported by Bristol-Myers Squibb Foundation Grants Number 41762123 (to TN) and an endowment fund of the department – Project Number 147100001k.
› Further Information
   Permissions and Reprints

Abstract

Background Owing to the linguistic situation, Japanese natural language processing (NLP) requires morphological analyses for word segmentation using dictionary techniques.

Objective We aimed to clarify whether it can be substituted with an open-end discovery-based NLP (OD-NLP), which does not use any dictionary techniques.

Methods Clinical texts at the first medical visit were collected for comparison of OD-NLP with word dictionary-based-NLP (WD-NLP). Topics were generated in each document using a topic model, which later corresponded to the respective diseases determined in International Statistical Classification of Diseases and Related Health Problems 10 revision. The prediction accuracy and expressivity of each disease were examined in equivalent number of entities/words after filtration with either term frequency and inverse document frequency (TF-IDF) or dominance value (DMV).

Results In documents from 10,520 observed patients, 169,913 entities and 44,758 words were segmented using OD-NLP and WD-NLP, simultaneously. Without filtering, accuracy and recall levels were low, and there was no difference in the harmonic mean of the F-measure between NLPs. However, physicians reported OD-NLP contained more meaningful words than WD-NLP. When datasets were created in an equivalent number of entities/words with TF-IDF, F-measure in OD-NLP was higher than WD-NLP at lower thresholds. When the threshold increased, the number of datasets created decreased, resulting in increased values of F-measure, although the differences disappeared. Two datasets near the maximum threshold showing differences in F-measure were examined whether their topics were associated with diseases. The results showed that more diseases were found in OD-NLP at lower thresholds, indicating that the topics described characteristics of diseases. The superiority remained as much as that of TF-IDF when filtration was changed to DMV.

Conclusion The current findings prefer the use of OD-NLP to express characteristics of diseases from Japanese clinical texts and may help in the construction of document summaries and retrieval in clinical settings.

Keywords

natural language processing - text mining - topic model - electronic health record - Japanese clinical texts

Authors' Contribution

Y.Y. designed the study and retrieved a series of data under the supervision by T.N. and K.U. Y.Y. and T.I. performed a statistical analysis of collected data. T.N. and K.U. helped make the overall study design and conceptualized interpretations and criticisms. Y.Y. and T.N. drafted the manuscript and it was critically revised by T.N., T.I., and K.U. The final manuscript was approved by all authors.


Supplementary Material



Publication History

Received: 17 October 2021

Accepted: 13 April 2022

Accepted Manuscript online:
21 February 2023

Article published online:
04 April 2023

© 2023. The Author(s). This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/)

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Industry JAHIS. . Research on the implementation of medical information systems (order entry and electronic medical record systems). Accessed March 6, 2023 at: https://www.jahis.jp/action/id=57?contents_type=23
    PubMed
  • 2 Raghupathi W, Raghupathi V. Big data analytics in healthcare: promise and potential. Health Inf Sci Syst 2014; 2: 3
    CrossrefPubMedGoogle Scholar
  • 3 Ford E, Carroll JA, Smith HE, Scott D, Cassell JA. Extracting information from the text of electronic medical records to improve case detection: a systematic review. J Am Med Inform Assoc 2016; 23 (05) 1007-1015
    CrossrefPubMedGoogle Scholar
  • 4 Pham AD, Névéol A, Lavergne T. et al. Natural language processing of radiology reports for the detection of thromboembolic diseases and clinically relevant incidental findings. BMC Bioinformatics 2014; 15 (01) 266
    CrossrefPubMedGoogle Scholar
  • 5 Wilke RA, Xu H, Denny JC. et al. The emerging role of electronic medical records in pharmacogenomics. Clin Pharmacol Ther 2011; 89 (03) 379-386
    CrossrefPubMedGoogle Scholar
  • 6 Meystre SM, Savova GK, Kipper-Schuler KC, Hurdle JF. Extracting information from textual documents in the electronic health record: a review of recent research. Yearb Med Inform 2008; 17 (01) 128-144
    Article in Thieme ConnectPubMedGoogle Scholar
  • 7 Demner-Fushman D, Chapman WW, McDonald CJ. What can natural language processing do for clinical decision support?. J Biomed Inform 2009; 42 (05) 760-772
    CrossrefPubMedGoogle Scholar
  • 8 Nadkarni PM, Ohno-Machado L, Chapman WW. Natural language processing: an introduction. J Am Med Inform Assoc 2011; 18 (05) 544-551
    CrossrefPubMedGoogle Scholar
  • 9 Nishimoto N, Terae S, Uesugi M, Ogasawara K, Sakurai T. Development of a medical-text parsing algorithm based on character adjacent probability distribution for Japanese radiology reports. Methods Inf Med 2008; 47 (06) 513-521
    Article in Thieme ConnectPubMedGoogle Scholar
  • 10 Ahltorp M, Skeppstedt M, Kitajima S, Henriksson A, Rzepka R, Araki K. Expansion of medical vocabularies using distributional semantics on Japanese patient blogs. J Biomed Semantics 2016; 7 (01) 58
    CrossrefPubMedGoogle Scholar
  • 11 Usui M, Aramaki E, Iwao T, Wakamiya S, Sakamoto T, Mochizuki M. Extraction and standardization of patient complaints from electronic medication histories for pharmacovigilance: natural language processing analysis in Japanese. JMIR Med Inform 2018; 6 (03) e11021
    CrossrefPubMedGoogle Scholar
  • 12 Aramaki E, Yano K, Wakamiya S. MedEx/J: A one-scan simple and fast NLP tool for Japanese clinical texts. Stud Health Technol Inform 2017; 245: 285-288
    PubMedGoogle Scholar
  • 13 Jiang G, Ogasawara K, Endoh A, Sakurai T. Context-based ontology building support in clinical domains using formal concept analysis. Int J Med Inform 2003; 71 (01) 71-81
    CrossrefPubMedGoogle Scholar
  • 14 Suzuki T, Yokoi H, Fujita S, Takabayashi K. Automatic DPC code selection from electronic medical records: text mining trial of discharge summary. Methods Inf Med 2008; 47 (06) 541-548
    Article in Thieme ConnectPubMedGoogle Scholar
  • 15 Li Y, Wang X, Hui L. et al. Chinese clinical named entity recognition in electronic medical records: development of a lattice long short-term memory model with contextualized character representations. JMIR Med Inform 2020; 8 (09) e19848
    CrossrefPubMedGoogle Scholar
  • 16 Lei J, Tang B, Lu X, Gao K, Jiang M, Xu H. A comprehensive study of named entity recognition in Chinese clinical text. J Am Med Inform Assoc 2014; 21 (05) 808-814
    CrossrefPubMedGoogle Scholar
  • 17 Hu D, Huang Z, Chan TM, Dong W, Lu X, Duan H. Utilizing Chinese admission records for MACE prediction of acute coronary syndrome. Int J Environ Res Public Health 2016; 13 (09) 912
    CrossrefPubMedGoogle Scholar
  • 18 Fushimi K, Hashimoto H, Imanaka Y. et al. Functional mapping of hospitals by diagnosis-dominant case-mix analysis. BMC Health Serv Res 2007; 7: 50
    CrossrefPubMedGoogle Scholar
  • 19 Bronselaer A, Tré GD. Concept-relational text clustering. Int J Intell Syst 2012; 27 (11) 970-993
    CrossrefPubMedGoogle Scholar
  • 20 Corporation I. . iKnow. Accessed March 6, 2023 at: https://github.com/intersystems/iknow
    PubMed
  • 21 MeCab. . MeCab: Yet Another Part-of-Speech and Morphological Analyzer. Accessed March 6, 2023 at: http://taku910.github.io/mecab/
    PubMed
  • 22 Liu J, Shindo H, Matsumoto Y. Development of a computer-assisted Japanese functional expression learning system for Chinese-speaking learners. Educ Technol Res Dev 2019; 67 (05) 1307-1331
    CrossrefPubMedGoogle Scholar
  • 23 Ujiie S, Yada S, Wakamiya S, Aramaki E. Identification of adverse drug event-related Japanese articles: natural language processing analysis. JMIR Med Inform 2020; 8 (11) e22661
    CrossrefPubMedGoogle Scholar
  • 24 Aoki M, Yokota S, Kagawa R, Shinohara E, Imai T, Ohe K. Automatic classification of electronic nursing narrative records based on Japanese standard terminology for nursing. Comput Inform Nurs 2021; 39 (11) 828-834
    PubMedGoogle Scholar
  • 25 Sagara K. . ComeJisyo. Accessed March 6, 2023 at: https://ja.osdn.net/projects/comedic/
    PubMed
  • 26 Aizawa A. An information-theoretic perspective of TF-IDF measures. Inf Process Manage 2003; 39 (01) 45-65
    CrossrefPubMedGoogle Scholar
  • 27 Blei DM, Ng AY, Jordan MI. Latent Dirichlet allocation. Journal of Machine Learning Research 2003; 3 (04–05): 993-1022
    PubMedGoogle Scholar
  • 28 Luo G. MLBCD: a machine learning tool for big clinical data. Health Inf Sci Syst 2015; 3: 3
    CrossrefPubMedGoogle Scholar
  • 29 Schmidhuber J. Deep learning in neural networks: an overview. Neural Netw 2015; 61: 85-117
    CrossrefPubMedGoogle Scholar
  • 30 Haider MM, Hossin MA, Mahl HR, Arif H. Automatic Text Summarization Using Gensim Word2Vec and K-Means Clustering Algorithm. Ieee Region 10 Symp 2020; 283-286
    PubMedGoogle Scholar
  • 31 Liu L, Tang L, Dong W, Yao S, Zhou W. An overview of topic modeling and its current applications in bioinformatics. Springerplus 2016; 5 (01) 1608
    CrossrefPubMedGoogle Scholar
  • 32 Xue J, Chen J, Chen C, Zheng C, Li S, Zhu T. Public discourse and sentiment during the COVID 19 pandemic: using latent Dirichlet Allocation for topic modeling on Twitter. PLoS One 2020; 15 (09) e0239441
    CrossrefPubMedGoogle Scholar
  • 33 Wang H, Wu F, Lu W. et al. Identifying objective and subjective words via topic modeling. IEEE Trans Neural Netw Learn Syst 2018; 29 (03) 718-730
    CrossrefPubMedGoogle Scholar
  • 34 Torii M, Yang EW, Doan S. A Preliminary Study of Clinical Concept Detection Using Syntactic Relations. AMIA Annu Symp Proc 2018; 2018: 1028-1035
    PubMedGoogle Scholar
  • 35 Henriksson A, Moen H, Skeppstedt M, Daudaravičius V, Duneld M. Synonym extraction and abbreviation expansion with ensembles of semantic spaces. J Biomed Semantics 2014; 5 (01) 6
    CrossrefPubMedGoogle Scholar
  • 36 Hazewinkel MC, de Winter RFP, van Est RW. et al. Text analysis of electronic medical records to predict seclusion in psychiatric wards: proof of concept. Front Psychiatry 2019; 10: 188
    CrossrefPubMedGoogle Scholar
  • 37 Wang Q, Zhou YM, Ruan T, Gao DQ, Xia YH, He P. Incorporating dictionaries into deep neural networks for the Chinese clinical named entity recognition. Journal of Biomedical Informatics 2019;92
    PubMedGoogle Scholar
  • 38 Li LQ, Zhao J, Hou L, Zhai YK, Shi JM, Cui FF. . An attention-based deep learning model for clinical named entity recognition of Chinese electronic medical records. Bmc Med Inform Decis 2019;19(Suppl 5):235
    PubMed