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

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.

[1]  John Riedl,et al.  Analysis of recommendation algorithms for e-commerce , 2000, EC '00.

[2]  David Sarne,et al.  Computerized physician order entry of medications and clinical decision support can improve problem list documentation compliance , 2010, Int. J. Medical Informatics.

[3]  Tao Luo,et al.  Effective personalization based on association rule discovery from web usage data , 2001, WIDM '01.

[4]  Paul N. Gorman,et al.  Using medication list-problem list mismatches as markers of potential error , 2002, AMIA.

[5]  Jaideep Srivastava,et al.  Selecting the right interestingness measure for association patterns , 2002, KDD.

[6]  David W. Bates,et al.  A method and knowledge base for automated inference of patient problems from structured data in an electronic medical record , 2011, J. Am. Medical Informatics Assoc..

[7]  D. Blumenthal,et al.  The "meaningful use" regulation for electronic health records. , 2010, The New England journal of medicine.

[8]  Shichao Zhang,et al.  Association Rule Mining: Models and Algorithms , 2002 .

[9]  Adam Wright,et al.  Development and evaluation of a crowdsourcing methodology for knowledge base construction: identifying relationships between clinical problems and medications , 2012, J. Am. Medical Informatics Assoc..

[10]  Bart Goethals,et al.  Survey on Frequent Pattern Mining , 2003 .

[11]  Daniel B Hier,et al.  Assessing physician comprehension of and attitudes toward problem list documentation. , 2008, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[12]  D. Bates,et al.  Use of an Electronic Problem List by Primary Care Providers and Specialists , 2012, Journal of General Internal Medicine.

[13]  David W. Bates,et al.  Improving completeness of electronic problem lists through clinical decision support: a randomized, controlled trial , 2012, J. Am. Medical Informatics Assoc..

[14]  Peter J. Haug,et al.  Bmc Medical Informatics and Decision Making Automation of a Problem List Using Natural Language Processing , 2005 .

[15]  Mary K Goldstein,et al.  Accuracy of computerized outpatient diagnoses in a Veterans Affairs general medicine clinic. , 2002, The American journal of managed care.

[16]  Peter J. Haug,et al.  Randomized controlled trial of an automated problem list with improved sensitivity , 2008, Int. J. Medical Informatics.

[17]  Adam Wright,et al.  Clinician attitudes toward and use of electronic problem lists: a thematic analysis , 2011, BMC Medical Informatics Decis. Mak..

[18]  Tonya Hongsermeier,et al.  Research Paper: A Description and Functional Taxonomy of Rule-based Decision Support Content at a Large Integrated Delivery Network , 2007, J. Am. Medical Informatics Assoc..

[19]  W. Hammond,et al.  Computerized decision support based on a clinical practice guideline improves compliance with care standards. , 1997, The American journal of medicine.

[20]  Ulrich Güntzer,et al.  Algorithms for association rule mining — a general survey and comparison , 2000, SKDD.

[21]  Adam Wright,et al.  An automated technique for identifying associations between medications, laboratory results and problems , 2010, J. Biomed. Informatics.