Download PDF
Appl Clin Inform 2013; 04(01): 100-109
DOI: 10.4338/ACI-2012-12-RA-0051
Research Article
Schattauer GmbH

Validation of an Association Rule Mining-Based Method to Infer Associations Between Medications and Problems

A. Wright
1   Brigham & Women’s Hospital, Boston, MA, USA
2   Partners HealthCare, Boston, MA, USA
3   Harvard Medical School, Boston, MA, USA
,
A. McCoy
4   University of Texas Health Science Center at Houston, Boston, MA, USA
,
S. Henkin
1   Brigham & Women’s Hospital, Boston, MA, USA
5   Boston University School of Medicine, Boston, MA, USA
,
M. Flaherty
1   Brigham & Women’s Hospital, Boston, MA, USA
,
D. Sittig
4   University of Texas Health Science Center at Houston, Boston, MA, USA
› Author Affiliations
Further Information

Publication History

received: 05 December 2012

accepted: 09 February 2012

Publication Date:
19 December 2017 (online)

Also available at
   Permissions and Reprints

Summary

Background: In a prior study, we developed methods for automatically identifying associations between medications and problems using association rule mining on a large clinical data warehouse and validated these methods at a single site which used a self-developed electronic health record. Objective: To demonstrate the generalizability of these methods by validating them at an external site.

Methods: We received data on medications and problems for 263,597 patients from the University of Texas Health Science Center at Houston Faculty Practice, an ambulatory practice that uses the Allscripts Enterprise commercial electronic health record product. We then conducted association rule mining to identify associated pairs of medications and problems and characterized these associations with five measures of interestingness: support, confidence, chi-square, interest and conviction and compared the top-ranked pairs to a gold standard.

Results: 25,088 medication-problem pairs were identified that exceeded our confidence and support thresholds. An analysis of the top 500 pairs according to each measure of interestingness showed a high degree of accuracy for highly-ranked pairs.

Conclusion: The same technique was successfully employed at the University of Texas and accuracy was comparable to our previous results. Top associations included many medications that are highly specific for a particular problem as well as a large number of common, accurate medication-problem pairs that reflect practice patterns.

Citation: Wright A, McCoy A, Henkin S, Flaherty M, Sittig D. Validation of an association rule mining-based method to infer associations between medications and problems. ppl Clin Inf 2013; 4: 100–109

http://dx.doi.org/10.4338/ACI-2012-12-RA-0051

Keywords

Problem list - clinical decision support - data mining - automated inference - methodology
 

  • References

  • 1 Blumenthal D, Tavenner M. The "meaningful use" regulation for electronic health records. The New England journal of medicine 2010; 363 (06) 501-504. Epub 2010/07/22.
    CrossrefPubMedGoogle Scholar
  • 2 Information Management Processes (Standard IM 6.40): 2008 Comprehensive Accreditation Manual for Hospitals. The Official Handbook Oakbrook Terrace; Illinois: 2008
    Google Scholar
  • 3 Wright A, Goldberg H, Hongsermeier T, Middleton B. A description and functional taxonomy of rule-based decision support content at a large integrated delivery network. Journal of the American Medical Informatics Association : JAMIA 2007; 14 (04) 489-496. Epub 2007/04/27.
    CrossrefPubMedGoogle Scholar
  • 4 Lobach DF, Hammond WE. Computerized decision support based on a clinical practice guideline improves compliance with care standards. The American journal of medicine 1997; 102 (01) 89-98. Epub 1997/01/01.
    CrossrefPubMedGoogle Scholar
  • 5 Szeto HC, Coleman RK, Gholami P, Hoffman BB, Goldstein MK. Accuracy of computerized outpatient diagnoses in a Veterans Affairs general medicine clinic. The American journal of managed care 2002; 8 (01) 37-43. Epub 2002/01/30.
    PubMedGoogle Scholar
  • 6 Wright A, Pang J, Feblowitz JC, Maloney FL, Wilcox AR, Ramelson HZ, Schneider LI, Bates DW. A method and knowledge base for automated inference of patient problems from structured data in an electronic medical record. Journal of the American Medical Informatics Association : JAMIA 2011; 18 (06) 859-867. Epub 2011/05/27.
    CrossrefPubMedGoogle Scholar
  • 7 Wright A, Feblowitz J, Maloney FL, Henkin S, Bates DW. Use of an Electronic Problem List by Primary Care Providers and Specialists. Journal of general internal medicine. 2012 Epub 2012/03/20.
    PubMedGoogle Scholar
  • 8 Wright A, Maloney FL, Feblowitz JC. Clinician attitudes toward and use of electronic problem lists: a thematic analysis. BMC Med Inform Decis Mak 2011; 11: 36. Epub 2011/05/27.
    CrossrefPubMedGoogle Scholar
  • 9 Jao C, Hier D, Galanter W, Valenta A. Assessing physician comprehension of and attitudes toward problem list documentation. AMIA Annual Symposium proceedings / AMIA Symposium AMIA Symposium 2008; 990. Epub 2008/11/13.
    PubMedGoogle Scholar
  • 10 Galanter WL, Hier DB, Jao C, Sarne D. Computerized physician order entry of medications and clinical decision support can improve problem list documentation compliance. Int J Med Inform 2010; 79 (05) 332-338. Epub 2008/07/05.
    CrossrefPubMedGoogle Scholar
  • 11 Carpenter JD, Gorman PN. Using medication list--problem list mismatches as markers of potential error. Proceedings / AMIA Annual Symposium AMIA Symposium 2002: 106-110. Epub 2002/12/05.
    PubMedGoogle Scholar
  • 12 Meystre SM, Haug PJ. Randomized controlled trial of an automated problem list with improved sensitivity. Int J Med Inform 2008; 77 (09) 602-612. Epub 2008/02/19.
    CrossrefPubMedGoogle Scholar
  • 13 Meystre S, Haug PJ. Automation of a problem list using natural language processing. BMC Med Inform Decis Mak 2005; 5: 30. Epub 2005/09/02.
    CrossrefPubMedGoogle Scholar
  • 14 McCoy AB, Wright A, Laxmisan A, Ottosen MJ, McCoy JA, Butten D, Sittig DF. Development and evaluation of a crowdsourcing methodology for knowledge base construction: identifying relationships between clinical problems and medications. Journal of the American Medical Informatics Association: JAMIA. 2012 Epub 2012/05/15.
    PubMedGoogle Scholar
  • 15 Wright A, Chen ES, Maloney FL. An automated technique for identifying associations between medications, laboratory results and problems. Journal of biomedical informatics 2010; 43 (06) 891-901. Epub 2010/10/05.
    CrossrefPubMedGoogle Scholar
  • 16 Wright A, Pang J, Feblowitz JC, Maloney FL, Wilcox AR, McLoughlin KS, Ramelson H, Schneider L, Bates DW. Improving completeness of electronic problem lists through clinical decision support: a randomized, controlled trial. Journal of the American Medical Informatics Association: JAMIA. 2012 Epub 2012/01/05.
    PubMedGoogle Scholar
  • 17 Goethals B. Survey on frequent pattern mining. Univ of Helsinki; 2003
    Google Scholar
  • 18 Zhang C, Zhang S. Association rule mining: models and algorithms. Springer-Verlag; 2002
    Google Scholar
  • 19 Tan PN, Kumar V, Srivastava J. editors. Selecting the right interestingness measure for association patterns. 2002. ACM;
    Google Scholar
  • 20 Hipp J, Güntzer U, Nakhaeizadeh G. Algorithms for association rule mining—a general survey and comparison. ACM SIGKDD Explorations Newsletter 2000; 2 (01) 58-64.
    CrossrefPubMedGoogle Scholar
  • 21 Mobasher B, Dai H, Luo T, Nakagawa M. editors. Effective personalization based on association rule discovery from web usage data. Proceedings of the 3rd international workshop on Web information and data management. 2001. ACM;
    Google Scholar
  • 22 Sarwar B, Karypis G, Konstan J, Riedl J. editors. Analysis of recommendation algorithms for e-commerce. Proceedings of the 2nd ACM conference on Electronic commerce. 2000. ACM;
    Google Scholar
  • 23 Wright A CE, Maloney FL. An automated technique for identifying associations between medications, laboratory results, and problems. J Biomed Inf 2010; 43: 891-901.
    CrossrefPubMedGoogle Scholar