Top

BMC Medical Informatics and Decision Making

Published in:

Open Access 01-12-2017 | Research article

Empirical advances with text mining of electronic health records

Authors: T. Delespierre, P. Denormandie, A. Bar-Hen, L. Josseran

Published in: BMC Medical Informatics and Decision Making | Issue 1/2017

Abstract

Background

Korian is a private group specializing in medical accommodations for elderly and dependent people. A professional data warehouse (DWH) established in 2010 hosts all of the residents’ data. Inside this information system (IS), clinical narratives (CNs) were used only by medical staff as a residents’ care linking tool.

The objective of this study was to show that, through qualitative and quantitative textual analysis of a relatively small physiotherapy and well-defined CN sample, it was possible to build a physiotherapy corpus and, through this process, generate a new body of knowledge by adding relevant information to describe the residents’ care and lives.

Methods

Meaningful words were extracted through Standard Query Language (SQL) with the LIKE function and wildcards to perform pattern matching, followed by text mining and a word cloud using R® packages. Another step involved principal components and multiple correspondence analyses, plus clustering on the same residents’ sample as well as on other health data using a health model measuring the residents’ care level needs.

Results

By combining these techniques, physiotherapy treatments could be characterized by a list of constructed keywords, and the residents’ health characteristics were built. Feeding defects or health outlier groups could be detected, physiotherapy residents’ data and their health data were matched, and differences in health situations showed qualitative and quantitative differences in physiotherapy narratives.

Conclusions

This textual experiment using a textual process in two stages showed that text mining and data mining techniques provide convenient tools to improve residents’ health and quality of care by adding new, simple, useable data to the electronic health record (EHR). When used with a normalized physiotherapy problem list, text mining through information extraction (IE), named entity recognition (NER) and data mining (DM) can provide a real advantage to describe health care, adding new medical material and helping to integrate the EHR system into the health staff work environment.

Available only for authorised users

n < 30. We removed the real number for NH de-identification and for data harmonization.

Maas ML, Delaney C. Nursing process outcome linkage research: issues, current status, and health policy implications. Med Care. 2004;42(2):II-40–8.

Ventres W, Kooienga S, Vuckovic N, et al. Physicians, Patients, and the Electronic Health Record: An Ethnographic Analysis Annals of Family Medecine, n°2 March/April. 2006;4:124–32. www.annfammed.org.

Mc Ginn CA, Grenier S, Duplantie J, et al. Comparison of user groups’ perspectives of barriers and facilitators to implementing electronic health records: a systematic review. BMC Med. 2011;9:46.CrossRef

Cebul RD, Love TE, Jain AK, et al. Electronic health records and quality of diabetes care. N Engl J Med. 2011;365:825–33.CrossRefPubMed

Genes N, Chandra D, Ellis S, et al. Validating emergency vital signs using a data quality engine for data warehouse. Open Med Inform J. 2013;7:34–9.CrossRefPubMedPubMedCentral

Zangara G, Corso PP, Cangemi F, et al. A cloud based architecture to support electronic health report. Stud Health Technol Inform. 2014;207:380–9.PubMed

Tremblay MC, Berndt DJ, Luther SL, et al. Identifying fall-related injuries: Textmining the electronic health record. Inf Technol Manag. 2009;10:253–63. doi:10.10007/s10799-009-0061-6.CrossRef

SM Meystre, GK Savova, KC Kipper-Schuler et al. Extracting information from textual documents in the electronic health record : a review of recent research IMIA yearbook of medical informatics 2008.

Hornberger J. Electronic health records: a guide for clinicians and administrators. Book and media review. JAMA. 2009;301:110.CrossRef

10.

Savova GK, Masanz JJ, Ogren PV. Mayo clinical text analysis and knowledge extraction system (cTAKES): architecture, component evaluation and applications. J Am Med Inform Assoc. 2010;17:507e513. doi:10.1136/jamia.2009.001560.CrossRef

11.

Middleton B, Bloomrosen M, Dente MA, et al. Enhancing patient safety and quality of care by improving the usability of electronic health record systems: recommendations from AMIA. J Am Med Inform Assoc. 2013;20:e2–8. doi:10.1136/amiajnl-2012-001458.CrossRefPubMedPubMedCentral

12.

Gundlapalli AV, Redd A, Carter M, et al. Validating a strategy for psychosocial phenotyping using a large corpus of clinical text. J Am Med Inform Assoc. 2013;20:e355–64. doi:10.1136/amiajnl-2013-001946.CrossRefPubMedPubMedCentral

13.

https://www.oracle.com/fr/index.html. Accessed 3 July 2017.

14.

Delespierre T, Denormandie P, Josseran L. New methods to evaluate physiotherapy care in nursing homes. JNHR the Journal of Nursing Home Research International Working Group December 2-3, 2015 Toulouse, France Vol 1 2015 OC 36 p30.

15.

Min Song Opinion: Text Mining in the Clinic. The Scientist (April 1, 2013).

16.

https://www.rstudio.com/. Accessed 3 July 2017.

17.

ST Wu, H Liu, D li et al. Unified medical language system term occurrences in clinical notes: a large-scale corpus analysis J Am Med Inform Assoc 2012; 19:e149-e156, DOI 10.1136/amiajnl-2011-000744.

18.

Biro S, Williamson T, Leggett JA, et al. Utility of linking primary care electronic medical records with Canadian census data to study the determinants of chronic disease: an example based on socioeconomic status and obesity. BMC Med Inform Decis Mak. 2016;16:32. doi:10.1186/s12911-016-0272-9.CrossRefPubMedPubMedCentral

19.

Nguyen B. Techniques d’anonymisation. Statistique et société, Vol. 2, N° 4 décembre 2014. http://www.benjamin-nguyen.fr/papers/ss.pdf. Accessed 11 Aug 2017.

20.

http://drees.social-sante.gouv.fr/IMG/pdf/5_test_anonymisation_donnees_pmsi.pdf. Accessed 11 Aug 2017.

21.

http://www.tutorialspoint.com/sql/sql-like-clause.htm. Accessed 11 Aug 2017.

22.

http://edutechwiki.unige.ch/fr/Tutoriel_tm_text_mining_package. Accessed 11 Aug 2017. https://cran.r-project.org/web/packages/tm/vignettes/tm.pdf. Accessed 11 Aug 2017.

23.

https://cran.r-project.org/web/packages/SnowballC/index.html. Accessed 11 Aug 2017.

24.

https://cran.r-project.org/web/packages/wordcloud/index.html. Accessed 11 Aug 2017.

25.

https://cran.r-project.org/web/packages/RColorBrewer/index.html. Accessed 11 Aug 2017.

26.

Lee TT, Liu CY, Kuo Y-H, et al. Application of data mining to the identification of critical factors in patient falls using a web-based reporting system. Int J Med Inform. 2011;80(2):141–50. Special Issue: Security in Health Information Systems. February 2011CrossRefPubMed

27.

Lazkani A, Delespierre T, Bauduceau B, et al. Predicting falls in elderly patients with chronic pain and other chronic conditions. Aging Clin Exp Res. 2015;27(5):653–61. doi:10.1007/s40520-015-0319-2. Epub 2015. Epub 2015CrossRefPubMed

28.

Leemrijse CJ, de Boer ME, van den Ende CHM, et al. Factors associated with physiotherapy provision in a population of elderly nursing home residents; a cross sectional study. BMC Geriatr. 2007;7:7. doi:10.1186/1471-2318-7-7.CrossRefPubMedPubMedCentral

29.

Office of Inspector General J G Brown Physical And Occupational Therapy in Nursing Homes Medical Necessity and Quality of Care. Department of Health and Human Services OEI-09-97-00121 1999.

30.

JM Ducoudray, Y Eon, C Le Provost et al. Le modèle PATHOS, Guide d’utilisation 2017 rédigé par la CNAMTS (Caisse Nationale d’Assurance Maladie des Travailleurs Salariés) et le SNGC (Syndicat National de Gérontologie Clinique).

31.

Krefis AC, Schwarz NG, Nkrumah B, et al. Principal component analysis of socioeconomic factors and their association with malaria in children from the Ashanti region. Ghana Malar J. 2010;9:201.CrossRefPubMed

32.

Ahmed SA, Siddiqi JS, Quaiser S. Principal component analysis to explore climatic variability that facilitates the emergence of dengue outbreak in Karachi. Pak J Meteorol. 2014;11(21):1.

33.

http://maths.cnam.fr/IMG/pdf/CHIENS2012_cle0f5221.pdf. Accessed 11 Aug 2017. http://maths.cnam.fr/IMG/pdf/Epose-Pages-Dec09.pdf. Accessed 11 Aug 2017.

34.

Ayele D, Zewotir T, Mwambi H. Multiple correspondence analysis as a tool for analysis of large health surveys in African settings. Afr Health Sci. 2014;14(4):1036.CrossRefPubMedPubMedCentral

35.

P Soares Costa, N Correia Santos, P Cunha et al. The Use of Multiple Correspondence Analysis to Explore Associations between Categories of Qualitative Variables in Healthy Ageing Hindawi Publishing Corporation Journal of Aging Research Volume 2013, Article ID 302163, 12 pages http://dx.doi.org/10.1155/2013/302163 (Accessed 28 July 2016).

36.

F Husson, J Josse, J Pagès. Principal component methods – hierarchical clustering – partitional clustering : why would we need to choose for visualizing data ? Technical report Agrocampus 2010.

37.

http://factominer.free.fr/. Accessed 11 Aug 2017.

38.

Cheng B-W, Chang C-L, Liu I-S. Enhancing care services quality of nursing homes using data mining. Total Qual Manage Bus Excell. July 2005;16(5):575–96.CrossRef

39.

Holzinger A, Jurisica I. Knowledge Discovery and Data Mining in Biomedical Informatics: The Future Is in Integrative, Interactive Machine Learning Solutions. LNCS 8401 pp 1–18, 2014 Springer Verlag.https://link.springer.com/chapter/10.1007/978-3-662-43968-5_1. Accessed 11 Aug 2017.

40.

J Beel, S Langer, B Gipp (2017). TF-IDuF: A Novel Term-Weighting Scheme for User Modeling based on Users’ Personal Document Collections (Accessed 6 June 2017) (PDF). iConference.

41.

Piantadosi ST. Zipf’s word frequency law in natural language: a critical review and future directions June 2, 2015. https://colala.bcs.rochester.edu/papers/piantadosi2014zipfs.pdf. Accessed 11 Aug 2017.

42.

Fung KW, McDonald C, Srinivasan S. The UMLS-CORE project: a study of the problem list terminologies used in large healthcare institution. J Am Med Inform Assoc. 2010;17:675e680. doi:10.1136/jamia.2010.007047.CrossRef

43.

Atenstaedt R. Word cloud analysis of the BJGP. Br J Gen Pract. 2012;62(596):148. doi:10.3399/bjgp12X630142.

44.

Dressel K, Schüle S. Using Word Clouds for Risk Perception in the Field of Public Health – the Case of Vector-Borne Diseases. In: Planet@Risk, Davos: Global Risk Forum GRF Davos. 2014;2(2):85-88.

45.

http://www.sthda.com/english/wiki/principal-component-analysis-in-r-prcomp-vs-princomp-r-software-and-data-mining. Accessed 11 Aug 2017.

46.

A Nicholson, E Ford, KA Davies et al. Optimising Use of Electronic Health Records to Describe the Presentation of Rheumatoid Arthritis in Primary Care: A Strategy for Developing Code Lists. PLOS One February 2013, Volume 8 Issue 2 e54878 http://dx.doi.org/10.1371/journal.pone.0054878 (Accessed 13 Sept 2016).

47.

Ford E, Nicholson A, Koeling R, et al. Optimising the use of electronic health records to estimate the incidence of rheumatoid arthritis in primary care: what information is hidden in free text? BMC Med Res Methodol. 2013;13:105. Volume 8 Issue 2 e54878CrossRefPubMedPubMedCentral

48.

Kern LM, Edwards A, Kaushal R. The meaningful use of electronic health records and health care quality. Am J Med Qual. 2015;30(6):512–9. doi:10.1177/1062860614546547.CrossRefPubMed

49.

MM Cruz-Cunha, IM Miranda, P Conçales. Handbook on Research on ICT for Human-Centered Healthcare and Social Care Services 2013, IGI Global.

50.

Wright A, Maloney FL, Feblowitz JC. Clinician attitudes toward and use of electronic problem lists: a thematic analysis. BMC Med Inform Decis Making. 2011;11:36. https://doi.org/10.1186/1472-6947-11-36.

51.

Holmes C, Brown M, Hilaire D St. Healthcare provider attitudes towards the problem list in an electronic health record: a mixed-methods qualitative study. BMC Med Inform Decis Making. 2012;12:127. https://doi.org/10.1186/1472-6947-12-127.

52.

Makam AN, Lanham HJ, Batchelor K, et al. Use and satisfaction with key functions of a common commercial electronic health record: a survey of primary care providers. BMC Med Inform Decis Making. 2013;13:86. https://doi.org/10.1186/1472-6947-13-86.

53.

Bowman S, Rhia MJ, Fahima CCS. Impact of electronic health record systems on information integrity: quality and safety implications. Perspect Health Inf Manag. 2013 Fall; 10(Fall): 1c.

Title: Empirical advances with text mining of electronic health records
Authors: T. Delespierre
P. Denormandie
A. Bar-Hen
L. Josseran
Publication date: 01-12-2017
Publisher: BioMed Central
Published in: BMC Medical Informatics and Decision Making / Issue 1/2017
Electronic ISSN: 1472-6947
DOI: https://doi.org/10.1186/s12911-017-0519-0

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Empirical advances with text mining of electronic health records

Abstract

Background

Methods

Results

Conclusions

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2017

A meta-model for computer executable dynamic clinical safety checklists

Automatic identification of variables in epidemiological datasets using logic regression

Validation of multisource electronic health record data: an application to blood transfusion data

Patient perspectives on engagement in decision-making in early management of non-ST elevation acute coronary syndrome: a qualitative study

Validation of an algorithm that determines stroke diagnostic code accuracy in a Japanese hospital-based cancer registry using electronic medical records

Secure and scalable deduplication of horizontally partitioned health data for privacy-preserving distributed statistical computation