Sharon-Lise T. Normand, Karen B. Dorsey, Susannah M. Bernheim, Jacqueline N. Grady, Elizabeth W. Triche, Andreas Coppi, Shu-Xia Li, Nihar R. Desai, Yixin Li, Harlan M. Krumholz, Shiwani Mahajan, Zhenqiu Lin, and Frederick Warner
This comparative effectiveness research study assesses whether using present on admission codes and single, rather than grouped, diagnostic codes can enhance Centers for Medicare & Medicaid (CMS) models to predict payment for hospitalization for acute myocardial infarction, heart failure, and pneumonia., Key Points Question Does leveraging present on admission codes and using single, rather than grouped, diagnostic codes enhance risk models for acute myocardial infarction, heart failure, and pneumonia payment measures? Findings In this comparative effectiveness research study of risk models on 1 667 983 patients with 1 943 049 Medicare fee-for-service hospitalizations, use of present on admission codes and single diagnosis codes and separation of index admission codes from codes in the previous year improved models predicting payment that were compared with models based on Centers for Medicare & Medicaid Services grouped codes. The patient-level pseudo R2 improved from 0.077 to 0.129 for acute myocardial infarction, from 0.042 to 0.129 for heart failure, and from 0.114 to 0.237 for pneumonia. Meaning Changing candidate variables from the current standard improved models predicting payments, which has implications for research, benchmarking, public reporting, and calculations for population-based programs., Importance Predicting payments for particular conditions or populations is essential for research, benchmarking, public reporting, and calculations for population-based programs. Centers for Medicare & Medicaid Services (CMS) models often group codes into disease categories, but using single, rather than grouped, diagnostic codes and leveraging present on admission (POA) codes may enhance these models. Objective To determine whether changes to the candidate variables in CMS models would improve risk models predicting patient total payment within 30 days of hospitalization for acute myocardial infarction (AMI), heart failure (HF), and pneumonia. Design, Setting, and Participants This comparative effectiveness research study used data from Medicare fee-for-service hospitalizations for AMI, HF, and pneumonia at acute care hospitals from July 1, 2013, through September 30, 2015. Payments across multiple care settings, services, and supplies were included and adjusted for geographic and policy variations, corrected for inflation, and winsorized. The same data source was used but varied for the candidate variables and their selection, and the method used by CMS for public reporting that used grouped codes was compared with variations that used POA codes and single diagnostic codes. Combinations of use of POA codes, separation of index admission diagnoses from those in the previous 12 months, and use of individual International Classification of Diseases, Ninth Revision, Clinical Modification codes instead of grouped diagnostic categories were tested. Data analysis was performed from December 4, 2017, to June 10, 2019. Main Outcomes and Measures The models’ goodness of fit was compared using root mean square error (RMSE) and the McFadden pseudo R2. Results Among the 1 943 049 total hospitalizations of the study participants, 343 116 admissions were for AMI (52.5% male; 37.4% aged ≤74 years), 677 044 for HF (45.5% male; 25.9% aged ≤74 years), and 922 889 for pneumonia (46.4% male; 28.2% aged ≤74 years). The mean (SD) 30-day payment was $23 103 ($18 221) for AMI, $16 365 ($12 527) for HF, and $17 097 ($12 087) for pneumonia. Each incremental model change improved the pseudo R2 and RMSE. Incorporating all 3 changes improved the pseudo R2 of the patient-level models from 0.077 to 0.129 for AMI, from 0.042 to 0.129 for HF, and from 0.114 to 0.237 for pneumonia. Parallel improvements in RMSE were found for all 3 conditions. Conclusions and Relevance Leveraging POA codes, separating index from previous diagnoses, and using single diagnostic codes improved payment models. Better models can potentially improve research, benchmarking, public reporting, and calculations for population-based programs.