Geospatial and Explanatory Models for Heart Failure Admissions, 2016 through 2018 [post]

Clemens Scott Kruse, Bradley M. Beauvais, Matthew S. Brooks, Michael Mileski, Lawrence Fulton
2020 unpublished
Background. About 5.7 million individuals in the United States have heart failure, and the disease was estimated to cost about $42.9 billion in 2020. This research provides geographical incidence models of this disease in the U.S. and explanatory models to account for hospitals' number of heart failure DRGs using technical, workload, financial, geographical, and time-related variables. The research also provides updated financial and demand estimates based on inflationary pressures and disease
more » ... ssures and disease rate increases. Understanding patterns is important to both policymakers and health administrators for cost control and planning. Methods. The number of diagnoses is forecast using regression (constrained and unconstrained) and ensemble (random forests, extra trees regressor, gradient boosting, and bagging) techniques at the hospital unit of analysis. Descriptive maps of heart failure diagnosis-related groups (DRGs) depict areas of high incidence. State and county level spatial and non-spatial regression models of heart failure admission rates are performed. Expenditure forecasts were calculated for 2016 through 2018. Results: The incidence of heart failure has increased over time with highest intensities in the East and center of the country; however, several Northern states (e.g., Minnesota) have seen large increases since 2016. The best predictive model for forecasting the number of diagnoses at the hospital unit of analysis was an extremely randomized tree ensemble (predictive R2 = 0.86 applied to a 20% unobserved test set.) The important variables in this model included workload metrics and hospital type. State level spatial lag models using 1st order Queen's criteria were best at estimating heart failure admission rates (R2 =.816). At the county level, OLS was preferred over any GIS model based on a statistically insignificant Moran's I and resultant R2; however, none of the traditional models performed well (R2=.169 for the OLS). Gradient boosted tree models were able to predict 36% of the total Sum of Squares; however, and the most important factors were facility workload, mean cash-on-hand of the hospitals in the county, and mean equity of those hospitals.. Online interactive maps at the state and county levels are provided. Conclusions. Heart failure and associated expenditures are increasing. Overall, the total cost of the three DRGs in the study has increased approximately $61 billion from 2016 through 2018 (average of two estimates). The increase in the more expensive DRG (DRG 291) has outpaced others with an associated increase of $92 billion in expenditures. With the increase in demand (linked to obesity and other factors) as well as the relatively steady-state supply of cardiologists over time, the costs are likely to balloon over the next decade. Models like the ones presented here that reliably forecast demand are needed to inform healthcare leaders.
doi:10.21203/rs.2.21707/v3 fatcat:wmxecvdfnne4fpfdxkgub7xtu4