RTI uses cookies to offer you the best experience online. By clicking “accept” on this website, you opt in and you agree to the use of cookies. If you would like to know more about how RTI uses cookies and how to manage them please view our Privacy Policy here. You can “opt out” or change your mind by visiting: http://optout.aboutads.info/. Click “accept” to agree.
Maintaining automated measurement of Choosing Wisely adherence across the ICD 9 to 10 transition
Angiolillo, J., Rosenbloom, S. T., McPheeters, M., Tregoning, G. S., Rothman, R. L., & Walsh, C. G. (2019). Maintaining automated measurement of Choosing Wisely adherence across the ICD 9 to 10 transition. Journal of Biomedical Informatics, 93, Article 103142. https://doi.org/10.1016/j.jbi.2019.103142
Background: It remains unclear how to incorporate terminology changes, such as the International Classification of Disease (ICD) transition from ICD-9 to ICD-10, into established automated healthcare quality metrics.
Objective: To evaluate whether general equivalence mapping (GEM) can apply ICD-9 based metrics to ICD-10 patient data. To develop and validate novel ICD-10 reference codesets.
Design: Retrospective analysis for eleven Choosing Wisely (CW) metrics was performed using three scripted algorithms on an institutional clinical data warehouse. ICD-10 data were compared against published ICD-9 based metric definitions using two equivalence mapping algorithms. A third algorithm implemented novel reference ICD-10 codes matching the original ICD-9 codes' intent for comparison with patient ICD-10 data.
Participants: All adult patients seen at Vanderbilt University Medical Center, April - September 2016.
Main measures: The prevalence of eleven CW services during the six-month period.
Key results: The three algorithms found similar prevalence of avoidable CW services, with an unweighted-mean of 8.4% (range: 0.16-65%), or approximately 20,000 CW services out of 240,000 potential cases in 515,406 unique patients. The algorithms' median sensitivity was 0.80 (interquartile range: 0.75-0.95), median specificity was 0.88 (IQR: 0.77-0.94), and median Rand accuracy was 0.84 (IQR: 0.79-0.89). The attributed waste of these eleven services for the period ranged from $871,049 to $951,829 between methods. Accuracy assessment demonstrated that the GEM-based methods suffered recall losses for metrics requiring multistep mapping due to incompleteness, while novel ICD-10 metric definitions avoided these challenges.
Conclusions: Comprehensive mapping enables use of legacy metrics across ICD generations, but requires computational complexity that can be avoided with novel ICD-10 based metric definitions. Variation in the dollars attributed to waste due to ICD mapping introduces ambiguity that may affect quality-based reimbursement.
