Interpretable Predictive Models for Knowledge Discovery from Home-Care Electronic Health Records

Westra, Bonnie L.; Dey, Sanjoy; Fang, Gang; Steinbach, Michael; Kumar, Vipin; Oancea, Cristina; Savik, Kay; Dierich, Mary

doi:https://doi.org/10.1260/2040-2295.2.1.55

Journal of Healthcare Engineering

On this page

Abstract References Copyright Related Articles

Research Article | Open Access

Volume 2 | Article ID 984349 | https://doi.org/10.1260/2040-2295.2.1.55

Interpretable Predictive Models for Knowledge Discovery from Home-Care Electronic Health Records

Bonnie L. Westra,¹Sanjoy Dey,²Gang Fang,²Michael Steinbach,²Vipin Kumar,²Cristina Oancea,³Kay Savik,¹and Mary Dierich¹

Received01 Jun 2010

Accepted01 Dec 2010

Abstract

The purpose of this methodological study was to compare methods of developing predictive rules that are parsimonious and clinically interpretable from electronic health record (EHR) home visit data, contrasting logistic regression with three data mining classification models. We address three problems commonly encountered in EHRs: the value of including clinically important variables with little variance, handling imbalanced datasets, and ease of interpretation of the resulting predictive models. Logistic regression and three classification models using Ripper, decision trees, and Support Vector Machines were applied to a case study for one outcome of improvement in oral medication management. Predictive rules for logistic regression, Ripper, and decision trees are reported and results compared using F-measures for data mining models and area under the receiver-operating characteristic curve for all models. The rules generated by the three classification models provide potentially novel insights into mining EHRs beyond those provided by standard logistic regression, and suggest steps for further study.

References

R. Steinbrook, “Health Care and the American Recovery and Reinvestment Act,” N. Engl. J. Med., vol. 360, no. 11, pp. 1057–1060, 2009.
View at: Google Scholar
U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, Advances in Knowledge Discovery and Data Mining, AAI Press/The MIT Press, Menlo Park, CA, 1996.
P. Tan, M. Steinbach, and V. Kumar, Introduction to Data Mining, Pearson Addison-Wesley, Boston, 1st edition, 2005.
M. J. A. Berry and G. Linhoff, Data Mining Techniques For Marketing, Wiley, New York, 1997.
E. A. Madigan and O. L. Curet, “A Data Mining Approach in Home Healthcare: Outcomes and Service Use,” BMC Health Serv. Res., vol. 6:18, 2006.
View at: Google Scholar
P. A. Abbott, S. Quirolgico, D. Candidate, R. Manchand, K. Canfield, and M. Adya, “Can the US Minimum Data Set Be Used for Predicting Admissions to Acute Care Facilities?” Medinfo, pp. 91318–1321, 1998.
View at: Google Scholar
J. Demsar, B. Zupan, N. Aoki, M. J. Wall, T. H. Granchi, and J. Robert Beck, “Feature Mining and Predictive Model Construction from Severe Trauma Patient's Data,” Int. J. Med. Inform., vol. 63, no. 1–2, pp. 41–50, 2001.
View at: Google Scholar
W. J. Rudman, C. A. Brown, C. R. Hewitt et al., “The Use of Data Mining Tools in Identifying Medication Error Near Misses and Adverse Drug Events,” Top Health Inform. Manag., vol. 23, no. 2, pp. 94–103, 2002.
View at: Google Scholar
M. Hauben and L. Reich, “Potential Utility of Data-Mining Algorithms for Early Detection of Potentially Fatal/Disabling Adverse Drug Reactions: A Retrospective Evaluation,” J. Clin. Pharmacol., vol. 45, no. 4, pp. 378–384, 2005.
View at: Google Scholar
Centers for Medicare and Medicaid Services, CMS Home Health Quality Initiatives: Overview, 2010, http://www.cms.hhs.gov/HomeHealthQualityInits/, (accessed January 1 2011).
R. J. Rosati, “The History of Quality Measurement in Home Health Care,” Clin. Geriatr. Med., vol. 25, no. 1, pp. 121–134, 2009.
View at: Google Scholar
K. S. Martin, The Omaha System: A Key to Practice, Documentation, and Information Management, Elsevier Saunders, St. Louis, 2005.
K. H. Bowles, “Use of the Omaha System in Research,” in The Omaha System: A Key To Practice, Documentation, and Information Management, K. S. Martin, Ed., pp. 105–133, Elsevier Saunders, St. Louis, 2nd edition, 2005.
View at: Google Scholar
AHRQ, Clinical Classifications Software (CCS) for ICD-9-CM, 2009, http://www.hcup-us.ahrq.gov/toolssoftware/ccs/ccs.jsp, (accessed February 16 2009).
B. L. Westra, Clinical Classification Software Diagnoses Groupings, 2009, http://www.nursing.umn.edu/ICNP/OtherProjects/index.htm, (accessed January 1 2011).
M. E. Charlson, P. Pompei, K. L. Ales, and C. R. MacKenzie, “A New Method of Classifying Prognostic Comorbidity in Longitudinal Studies: Development and Validation,” J Chronic Dis., vol. 40, no. 5, pp. 373–383, 1987.
View at: Google Scholar
HCUP CCS, Healthcare Cost and Utilization Project (HCUP), 2009, http://www.hcup-us.ahrq.gov/toolssoftware/ccs/ccs.jsp, (accessed May 31 2009).
B. L. Westra, Omaha System Intervention Expert Groups, 2009, http://www.nursing.umn.edu/ICNP/OtherProjects/index.htm, (accessed January 1 2011).
B. L. Westra, Oral Medication Data Dictionary for Data Mining, 2009, http://www.nursing.umn.edu/ICNP/OtherProjects/index.htm, (accessed January 1 2011).
R. Bellazzi and B. Zupan, “Predictive Data Mining in Clinical Medicine: Current Issues and Guidelines,” Int. J. Med. Inf., vol. 77, no. 2, pp. 81–97, 2008.
View at: Google Scholar
F. E. Harrell, K. L. Lee, and P. Mark, “Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors,” Stat. Med., pp. 15361–387, 1996.
View at: Google Scholar
Centers for Medicare & Medicaid Services, OASIS - Based Home Health Agency Patient Outcome and Case Mix Reports, 2008, http://www.cms.hhs.gov/OASIS/09a_hhareports.asp, (accessed December 13 2008).
K. D. Marek and L. Antle, “Medication Management of the Community Dwelling Older Adult,” in Patient Safety and Quality: An Evidence-Based Handbook For Nurses. AHRQ Publication No. 08-0043, R. G. Hughes, Ed., Agency for Healthcare Research and Quality, Rockville, MD, 2008, http://www.ahrq.gov/qual/nurseshdbk/, (accessed January 1 2011).
View at: Google Scholar
C. H. Ellenbecker, S. C. Frazier, and S. Verney, “Nurse's Observations and Experiences of Problems and Adverse Effects of Medication Management in Home Care,” Geriatr. Nurs., vol. 25, no. 3, pp. 164–170, 2004.
View at: Google Scholar
J. Shearer, “Improving Oral Medication Management in Home Health Agencies,” Home Healthc. Nurse, vol. 27, no. 3, pp. 184–192, 2009, [Corrected] [Published Erratum Appears in HOME HEALTHC NURSE, 2009 May,27(5):270].
View at: Google Scholar
K. Monsen, B. L. Westra, F. Yu, V. K. Ramadoss, and M. J. Kerr, “Data Management for Intervention Effectiveness Research: Comparing Deductive and Inductive Approaches,” Res. Nurs. Health, vol. 32, no. 6, pp. 647–656, 2009.
View at: Google Scholar

Copyright

Copyright © 2011 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PDF Download Citation Order printed copies

Views

634

Downloads

838

Citations