Start Submission Become a Reviewer

Reading: Preparing for the ICD-10-CM Transition: Automated Methods for Translating ICD Codes in Clini...

Download

A- A+
dyslexia friendly

Empirical research

Preparing for the ICD-10-CM Transition: Automated Methods for Translating ICD Codes in Clinical Phenotype Definitions

Authors:

Kin Wah Fung ,

National Library of Medicine, Bethesda, MD
X close

Rachel Richesson,

Duke University School of Nursing, Durham, NC
X close

Michelle Smerek,

Duke Clinical Research Institute, Durham, NC
X close

Katherine C. Pereira,

Duke University School of Nursing, Durham, NC
X close

Beverly B. Green,

Group Health Research Institute, Seattle, WA
X close

Ashwin Patkar,

Duke Clinical Research Institute, Durham, NC; Duke University School of Medicine, Durham, NC
X close

Megan Clowse,

Duke University School of Medicine, Durham, NC
X close

Alan Bauck,

Center for Health Research, Kaiser Permanente Northwest, Portland, OR
X close

Olivier Bodenreider

National Library of Medicine, Bethesda, MD
X close

Abstract

Background: The national mandate for health systems to transition from ICD-9-CM to ICD-10-CM in October 2015 has an impact on research activities. Clinical phenotypes defined by ICD-9-CM codes need to be converted to ICD-10-CM, which has nearly four times more codes and a very different structure than ICD-9-CM.

Methods: We used the Centers for Medicare & Medicaid Services (CMS) General Equivalent Maps (GEMs) to translate, using four different methods, condition-specific ICD-9-CM code sets used for pragmatic trials (n=32) into ICD-10-CM. We calculated the recall, precision, and F‑score of each method. We also used the ICD-9-CM and ICD-10-CM value sets defined for electronic quality measure as an additional evaluation of the mapping methods.

Results: The forward-backward mapping (FBM) method had higher precision, recall and F‑score metrics than simple forward mapping (SFM). The more aggressive secondary (SM) and tertiary mapping (TM) methods resulted in higher recall but lower precision. For clinical phenotype definition, FBM was the best (F=0.67), but was close to SM (F=0.62) and TM (F=0.60), judging on the F‑scores alone. The overall difference between the four methods was statistically significant (one-way ANOVA, F=5.749, p=0.001). However, pairwise comparisons between FBM, SM, and TM did not reach statistical significance. A similar trend was found for the quality measure value sets.

Discussion: The optimal method for using the GEMs depends on the relative importance of recall versus precision for a given use case. It appears that for clinically distinct and homogenous conditions, the recall of FBM is sufficient. The performance of all mapping methods was lower for heterogeneous conditions. Since code sets used for phenotype definition and quality measurement can be very similar, there is a possibility of cross-fertilization between the two activities.

Conclusion: Different mapping approaches yield different collections of ICD-10-CM codes. All methods require some level of human validation.

How to Cite: Fung KW, Richesson R, Smerek M, Pereira KC, Green BB, Patkar A, et al.. Preparing for the ICD-10-CM Transition: Automated Methods for Translating ICD Codes in Clinical Phenotype Definitions. eGEMs (Generating Evidence & Methods to improve patient outcomes). 2016;4(1):4. DOI: http://doi.org/10.13063/2327-9214.1211
Published on 12 Apr 2016.
Peer Reviewed

Downloads

  • PDF (EN)