Charlson Comorbidity Index: ICD-9 Update and ICD-10 Translation

The original Charlson Comorbidity Index (CCI) encompassed 19 categories of medical conditions that were identifiable in medical records. Subsequent publications provided scoring algorithms based on ( ) codes. The recent adoption of ( ) codes in the United States created a need for a new scoring scheme. In addition, a review of existing claims-based scoring systems suggested 3 areas for improvement: the lack of explicit identification of secondary diabetes, the lack of differentiation between HIV infection and AIDS, and insufficient guidance on scoring hierarchy. In addition, addressing the third need raised the issue of disease severity in renal disease. This initiative aimed to create an expanded and refined scoring system for CCI, addressing the classification of issues noted above, create a corresponding system, assess the comparability of - and -based scores, and validate the new scoring scheme. We created and code tables for 19 CCI medical conditions. The new scoring scheme was labeled CDMF CCI and was tested using claims-based data for individuals aged ≥65 years who participated in a Humana Medicare Advantage plan during at least 1 of 3 consecutive 12-month periods. Two 12-month periods were during the era and the third 12-month period was during the era. Because many individuals were counted in more than one 12-month period, we described the study population as comprising 3 panels. We used regression models to analyze the association between the CCI score and same-year inpatient admissions and near-term (90-day) mortality. Additional testing was done by comparing the mean CCI score or disease prevalence in the 3 subpopulations of people with HIV/AIDS, renal disease, or diabetes. Finally, we calculated area under the receiver operating characteristics (AUC-ROC) curve values by applying the Deyo system and our and scoring systems. The CDMF and scoring scheme yielded comparable scores across the 3 panels, and inpatient admissions and mortality rates consistently increased in each panel as the CCI score increased. Comparisons of the performance of the Deyo system and our proposed CDMF system in the 3 key subpopulations showed that the CDMF system produced a lower CCI score in the presence of HIV infection without AIDS, achieved similar detection ability of diabetes, and allowed good differentiation between mild-to-moderate and severe renal disease. AUC-ROC values were similar between the CDMF coding system and the Deyo system. Our results support the im