scholarly journals Geospatial-Temporal, Explanatory, Demand, and Financial Models for Heart Failure

2020 ◽  
Author(s):  
Clemens Scott Kruse ◽  
Bradley M. Beauvais ◽  
Matthew S. Brooks ◽  
Michael Mileski ◽  
Lawrence Fulton
Keyword(s):  
Heart Failure ◽  
Medical School ◽  
The United States ◽  
Explanatory Models ◽  
Geographical Information ◽  
Medicare Reimbursement ◽  
Hospital Type ◽  
Test Set ◽  
School Affiliation ◽  
Over Time

Abstract 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 geospatial-temporal 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, and geospatial-temporal variables. The research also provides updated financial and demand estimates based on inflationary pressures and disease rate increases. Understanding patterns is important to both policymakers and health administrators alike for cost control and planning. Methods Geographical Information Systems maps of heart failure diagnosis-related groups (DRGs) from 2016 through 2018 depicted areas of high incidence as well as changes. Simple expenditure forecasts were calculated for 2016 through 2018. Linear, lasso, ridge, and Elastic Net models as well as ensembled tree regressors including were built on an 80% training set and evaluated on a 20% test set. 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 in rates from 2016. The best traditional regression model explained 75% of the variability in the number of DRGs experienced by hospital using a small subset of variables including discharges, DRG type, percent Medicare reimbursement, hospital type, and medical school affiliation. The best ensembled tree models achieved R2 over .97 on the blinded test set and identified discharges, percent Medicare reimbursement, hospital acute days, affiliated physicians, staffed beds, employees, hospital type, emergency room visits, medical school affiliation, geographical location, and the number of surgeries as highly important predictors. Conclusions 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.

scholarly journals Geospatial and Explanatory Models for Heart Failure Admissions, 2016 through 2018

2020 ◽  
Author(s):  
Clemens Scott Kruse ◽  
Bradley M. Beauvais ◽  
Matthew S. Brooks ◽  
Michael Mileski ◽  
Lawrence Fulton
Keyword(s):  
Heart Failure ◽  
Medical School ◽  
The United States ◽  
Explanatory Models ◽  
Disease Rate ◽  
Medicare Reimbursement ◽  
Hospital Type ◽  
Test Set ◽  
School Affiliation ◽  
Over Time

Abstract 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 rate increases. Understanding patterns is important to both policymakers and health administrators for cost control and planning. Methods. Maps of heart failure diagnosis-related groups (DRGs) from 2016 through 2018 depicted areas of high incidence as well as changes. Spatial regression identified no significant spatial correlations. Simple expenditure forecasts were calculated for 2016 through 2018. Linear, lasso, ridge, and Elastic Net models as well as ensembled tree regressors including were built on an 80% training set and evaluated on a 20% test set. 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 in rates from 2016. The best traditional regression model explained 75% of the variability in the number of DRGs experienced by hospital using a small subset of variables including discharges, DRG type, percent Medicare reimbursement, hospital type, and medical school affiliation. The best ensembled tree models achieved R2 over .97 on the blinded test set and identified discharges, percent Medicare reimbursement, hospital acute days, affiliated physicians, staffed beds, employees, hospital type, emergency room visits, medical school affiliation, geographical location, and the number of surgeries as highly important predictors. Conclusions. 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.

scholarly journals Hospital-Based Back Surgery: Geospatial-Temporal, Explanatory, and Predictive Models

10.2196/14609 ◽  
2019 ◽  
Vol 21 (10) ◽  
pp. e14609 ◽  
Author(s):  
Lawrence Fulton ◽  
Clemens Scott Kruse
Keyword(s):  
Time Series ◽  
Random Forests ◽  
Geographical Information Systems ◽  
The United States ◽  
Practice Variation ◽  
Geographical Information ◽  
Federal State ◽  
Test Set ◽  
Back Surgery ◽  
Over Time

Background Hospital-based back surgery in the United States increased by 60% from January 2012 to December 2017, yet the supply of neurosurgeons remained relatively constant. During this time, adult obesity grew by 5%. Objective This study aimed to evaluate the demand and associated costs for hospital-based back surgery by geolocation over time to evaluate provider practice variation. The study then leveraged hierarchical time series to generate tight demand forecasts on an unobserved test set. Finally, explanatory financial, technical, workload, geographical, and temporal factors as well as state-level obesity rates were investigated as predictors for the demand for hospital-based back surgery. Methods Hospital data from January 2012 to December 2017 were used to generate geospatial-temporal maps and a video of the Current Procedural Terminology codes beginning with the digit 63 claims. Hierarchical time series modeling provided forecasts for each state, the census regions, and the nation for an unobserved test set and then again for the out-years of 2018 and 2019. Stepwise regression, lasso regression, ridge regression, elastic net, and gradient-boosted random forests were built on a training set and evaluated on a test set to evaluate variables important to explaining the demand for hospital-based back surgery. Results Widespread, unexplained practice variation over time was seen using geographical information systems (GIS) multimedia mapping. Hierarchical time series provided accurate forecasts on a blind dataset and suggested a 6.52% (from 497,325 procedures in 2017 to 529,777 in 2018) growth of hospital-based back surgery in 2018 (529,777 and up to 13.00% by 2019 [from 497,325 procedures in 2017 to 563,023 procedures in 2019]). The increase in payments by 2019 are estimated to be US $323.9 million. Extreme gradient-boosted random forests beat constrained and unconstrained regression models on a 20% unobserved test set and suggested that obesity is one of the most important factors in explaining the increase in demand for hospital-based back surgery. Conclusions Practice variation and obesity are factors to consider when estimating demand for hospital-based back surgery. Federal, state, and local planners should evaluate demand-side and supply-side interventions for this emerging problem.

scholarly journals Hospital-Based Back Surgery: Geospatial-Temporal, Explanatory, and Predictive Models (Preprint)

2019 ◽  
Author(s):  
Lawrence Fulton ◽  
Clemens Scott Kruse
Keyword(s):  
Time Series ◽  
Random Forests ◽  
Geographical Information Systems ◽  
The United States ◽  
Practice Variation ◽  
Geographical Information ◽  
Federal State ◽  
Test Set ◽  
Back Surgery ◽  
Over Time

BACKGROUND Hospital-based back surgery in the United States increased by 60% from January 2012 to December 2017, yet the supply of neurosurgeons remained relatively constant. During this time, adult obesity grew by 5%. OBJECTIVE This study aimed to evaluate the demand and associated costs for hospital-based back surgery by geolocation over time to evaluate provider practice variation. The study then leveraged hierarchical time series to generate tight demand forecasts on an unobserved test set. Finally, explanatory financial, technical, workload, geographical, and temporal factors as well as state-level obesity rates were investigated as predictors for the demand for hospital-based back surgery. METHODS Hospital data from January 2012 to December 2017 were used to generate geospatial-temporal maps and a video of the Current Procedural Terminology codes beginning with the digit 63 claims. Hierarchical time series modeling provided forecasts for each state, the census regions, and the nation for an unobserved test set and then again for the out-years of 2018 and 2019. Stepwise regression, lasso regression, ridge regression, elastic net, and gradient-boosted random forests were built on a training set and evaluated on a test set to evaluate variables important to explaining the demand for hospital-based back surgery. RESULTS Widespread, unexplained practice variation over time was seen using geographical information systems (GIS) multimedia mapping. Hierarchical time series provided accurate forecasts on a blind dataset and suggested a 6.52% (from 497,325 procedures in 2017 to 529,777 in 2018) growth of hospital-based back surgery in 2018 (529,777 and up to 13.00% by 2019 [from 497,325 procedures in 2017 to 563,023 procedures in 2019]). The increase in payments by 2019 are estimated to be US $323.9 million. Extreme gradient-boosted random forests beat constrained and unconstrained regression models on a 20% unobserved test set and suggested that obesity is one of the most important factors in explaining the increase in demand for hospital-based back surgery. CONCLUSIONS Practice variation and obesity are factors to consider when estimating demand for hospital-based back surgery. Federal, state, and local planners should evaluate demand-side and supply-side interventions for this emerging problem.

scholarly journals Geospatial and Explanatory Models for Heart Failure Admissions, 2016 through 2018

2020 ◽  
Author(s):  
Clemens Scott Kruse ◽  
Bradley M. Beauvais ◽  
Matthew S. Brooks ◽  
Michael Mileski ◽  
Lawrence Fulton
Keyword(s):  
Heart Failure ◽  
The United States ◽  
Explanatory Models ◽  
Disease Rate ◽  
County Level ◽  
Unit Of Analysis ◽  
Hospital Unit ◽  
Admission Rates ◽  
Heart Failure Admission ◽  
Over Time

Abstract 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 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.

Abstract 439: Trajectory Analysis of Left Ventricular Dimensions From Biobank Data Uncovers Novel Genetic Associations

2020 ◽  
Vol 127 (Suppl_1) ◽  
Author(s):  
Tess Pottinger ◽  
Megan J Puckelwartz ◽  
Lorenzo L Pesce ◽  
Anthony Gacita ◽  
Isabella Salamone ◽  
...  
Keyword(s):  
Heart Failure ◽  
Longitudinal Data ◽  
Association Studies ◽  
The United States ◽  
Left Ventricular ◽  
Genome Wide Association Studies ◽  
Qtc Interval ◽  
Regulatory Regions ◽  
Genome Wide ◽  
Over Time

Background: Approximately 6 million adults in the United States have heart failure. The progression of heart failure is variable arising from differences in sex, age, genetic background including ancestry, and medication response. Many population-based genetic studies of heart failure have been cross-sectional in nature, failing to gain additional power from longitudinal analyses. As heart failure is known to change over time, using longitudinal data trajectories as a quantitative trait will increase power in genome wide association studies (GWAS). Methods: We used the electronic health record in a racially and ethnically diverse medical biobank from a single, metropolitan US center. We used whole genome data from 896 unrelated participants analyzed, including 494 who had at least 1 electrocardiogram and 324 who had more than 1 echocardiogram (average of 3 observations per person). A mixture model based semiparametric latent growth curve model was used to cluster outcome measures used for genome-wide analyses. Results: GWAS on the trajectory probability of QTc interval identified significant associations with variants in regulatory regions proximal to the WLS gene, which encodes Wntless, a Wnt ligand secretion mediator. WLS was previously associated with QTc and myocardial infarction, thus confirming the power of the method. GWAS on the trajectory probability of left ventricular diameter (LVIDd) identified significant associations with variants in regulatory regions near MYO10 , which encodes unconventional Myosin-10. MYO10 was previously associated with obesity and metabolic syndrome. Conclusions: This is the first study to show an association with variants in or near MYO10 and left ventricular dimension changes over time. Further, we found that using trajectory probabilities can provide increased power to find novel associations with longitudinal data. This reduces the need for larger cohorts, and increases yield from smaller, well-phenotyped cohorts, such as those found in biobanks. This approach should be useful in the study of rare diseases and underrepresented populations.

Use of the NBME Comprehensive Basic Science Examination as a progress test in the preclerkship curriculum of a new medical school

2014 ◽  
Vol 38 (4) ◽  
pp. 315-320 ◽  
Author(s):  
Teresa R. Johnson ◽  
Mohammed K. Khalil ◽  
Richard D. Peppler ◽  
Diane D. Davey ◽  
Jonathan D. Kibble
Keyword(s):  
Medical School ◽  
Basic Science ◽  
External Validation ◽  
Multiple Choice ◽  
The United States ◽  
Progress Test ◽  
Formal Curriculum ◽  
Usmle Step 1 ◽  
Usmle Step ◽  
Over Time

In the present study, we describe the innovative use of the National Board of Medical Examiners (NBME) Comprehensive Basic Science Examination (CBSE) as a progress test during the preclerkship medical curriculum. The main aim of this study was to provide external validation of internally developed multiple-choice assessments in a new medical school. The CBSE is a practice exam for the United States Medical Licensing Examination (USMLE) Step 1 and is purchased directly from the NBME. We administered the CBSE five times during the first 2 yr of medical school. Student scores were compared with scores on newly created internal summative exams and to the USMLE Step 1. Significant correlations were observed between almost all our internal exams and CBSE scores over time as well as with USMLE Step 1 scores. The strength of correlations of internal exams to the CBSE and USMLE Step 1 broadly increased over time during the curriculum. Student scores on courses that have strong emphasis on physiology and pathophysiology correlated particularly well with USMLE Step 1 scores. Student progress, as measured by the CBSE, was found to be linear across time, and test performance fell behind the anticipated level by the end of the formal curriculum. These findings are discussed with respect to student learning behaviors. In conclusion, the CBSE was found to have good utility as a progress test and provided external validation of our new internally developed multiple-choice assessments. The data also provide performance benchmarks both for our future students to formatively assess their own progress and for other medical schools to compare learning progression patterns in different curricular models.

Abstract 18070: Disparities in Advanced Heart Failure Therapy

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Khalil Murad ◽  
Samit S Roy ◽  
Nonye Harcourt ◽  
Monica Colvin
Keyword(s):  
Heart Failure ◽  
Healthcare Delivery ◽  
Multivariate Logistic Regression Analysis ◽  
Female Gender ◽  
The United States ◽  
Public Health Research ◽  
Geographic Region ◽  
Advanced Heart Failure ◽  
Circulatory Support ◽  
Hospital Type

Background and Objective: Disparities in healthcare delivery are increasingly recognized. In this study, we explored disparities based on gender, race, age, region, and hospital type, in receiving advanced heart failure therapies (AHFT) defined as mechanical circulatory support (MCS) and heart transplantation (HT). Methods: Using data from the Nationwide Inpatient Sample (NIS), the largest all-payer inpatient health care database in the United States, we identified all hospitalizations between 2005-2011 for patients 18-85 years old, with the diagnosis of congestive heart failure, cardiomyopathy, or cardiogenic shock, and with no known contraindications to AHFT. Multivariate logistic regression analysis was used to determine the likelihood of receiving AHFT based on gender (men versus women), race (White versus Black, Hispanic, or others), age (≤50 versus 51-70 or ≥71 years old), hospital type (teaching versus non teaching), and geographic region (West versus Northeast, Mid-west, or South). Results: A total of 3,789,875 hospitalizations met our inclusion criteria, of which 3,769 (0.1%) patients received AHFT: 1,923 (51.0%) received MCS and 1,846 (49.0%) received HT. The following were associated with lower likelihood of receiving AHFT (table 1): female gender, non-white race, older age, non-teaching hospital, and Midwest, Northeast or South geographical region. Conclusion: Gender, race, age and regional disparities exist in the delivery of AHFT therapy. As the population of patients with end-stage heart failure continues to grow, effective public health research and policies are needed to identify the sources of disparities and to ensure equity in delivering AHFT.

Abstract 15447: Trends in Use of Pulmonary Artery Catheterization in Heart Failure in the United States, 2006 - 2012

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Rohan Khera ◽  
Ambarish Pandey ◽  
Nilay Kumar ◽  
Saket Girotra ◽  
Gregg C Fonarow
Keyword(s):  
Heart Failure ◽  
Respiratory Failure ◽  
Pulmonary Artery ◽  
Cardiogenic Shock ◽  
The United States ◽  
Primary Diagnosis ◽  
Circulatory Support ◽  
Major Surgery ◽  
Escape Trial ◽  
Over Time

Introduction: Use of pulmonary artery(PA) catheterization in heart failure(HF) patients without cardiogenic shock has not been shown to improve clinical outcomes (ESCAPE trial, 2005) and is not routinely recommended in the absence of shock or respiratory failure. However, contemporary trends in PA catheter use among HF patients are not known. Methods: The National Inpatient Sample (2006-2012) was used to identify adults(>18 years) hospitalized with a primary diagnosis of HF using ICD-9 codes 402.x1, 404.x1, 404.x3 and 428.x. PA catheter use was identified using procedure codes 89.6x. Patients undergoing major surgery or receiving mechanical circulatory support were excluded. Propensity-matched analyses were performed to compare risk-adjusted in-hospital mortality in patients with and without PA catheter use. Results: During 2006-2012, PA catheters were used in 39,247 HF hospitalizations, at a rate of 6 per 1000 HF admissions. Patients with PA catheter placement were younger and more commonly had cardiogenic shock (11%) or respiratory failure (11%). PA catheter use increased significantly over time from 5.3/1000 HF(2006) to 7.9/1000 HF(2012)(P<0.001,Figure). In subgroup analyses, in patients with cardiogenic shock, the proportional use of PA catheter was higher and increased only modestly (118 to 121/1000 HF cases,Ptrend 0.04). In contrast, patients without shock or respiratory failure had lower proportional use of PA catheter with a substantial increase during the study period (4.2 to 6.5 per 1000 HF cases, Ptrend< 0.001). In propensity-matched analyses of patients without shock or respiratory failure, mortality in HF was higher with the use of PA catheter compared to no PA catheter use (Risk-adjusted odd ratio 1.42, 95%CI 1.30, 1.56) Conclusions: PA catheter use has increased significantly over time among patients hospitalized with HF after ESCAPE, even in patients without cardiogenic shock/respiratory failure and is associated with worse outcomes.

scholarly journals National Trends in the Burden of Atrial Fibrillation During Hospital Admissions for Heart Failure

2021 ◽  
Author(s):  
Samuel W. Reinhardt ◽  
Fouad Chouairi ◽  
P. Elliott Miller ◽  
Katherine A. A. Clark ◽  
Bradley Kay ◽  
...  
Keyword(s):  
Heart Failure ◽  
Atrial Fibrillation ◽  
Ejection Fraction ◽  
Hospital Mortality ◽  
Hospital Admissions ◽  
The United States ◽  
Hospital Charges ◽  
Future Research ◽  
Reduced Ejection Fraction ◽  
Over Time

Background Heart failure (HF) and atrial fibrillation (AF) frequently coexist and may be associated with worse HF outcomes, but there is limited contemporary evidence describing their combined prevalence. We examined current trends in AF among hospitalizations for HF with preserved (HFpEF) ejection fraction or HF with reduced ejection fraction (HFrEF) in the United States, including outcomes and costs. Methods and Results Using the National Inpatient Sample, we identified 10 392 189 hospitalizations for HF between 2008 and 2017, including 4 250 698 with comorbid AF (40.9%). HF hospitalizations with AF involved patients who were older (average age, 76.9 versus 68.8 years) and more likely White individuals (77.8% versus 59.1%; P <0.001 for both). HF with preserved ejection fraction hospitalizations had more comorbid AF than HF with reduced ejection fraction (44.9% versus 40.8%). Over time, the proportion of comorbid AF increased from 35.4% in 2008 to 45.4% in 2017, and patients were younger, more commonly men, and Black or Hispanic individuals. Comorbid hypertension, diabetes mellitus, and vascular disease all increased over time. HF hospitalizations with AF had higher in‐hospital mortality than those without AF (3.6% versus 2.6%); mortality decreased over time for all HF (from 3.6% to 3.4%) but increased for HF with reduced ejection fraction (from 3.0% to 3.7%; P <0.001 for all). Median hospital charges were higher for HF admissions with AF and increased 40% over time (from $22 204 to $31 145; P <0.001). Conclusions AF is increasingly common among hospitalizations for HF and is associated with higher costs and in‐hospital mortality. Over time, patients with HF and AF were younger, less likely to be White individuals, and had more comorbidities; in‐hospital mortality decreased. Future research will need to address unique aspects of changing patient demographics and rising costs.

scholarly journals Models for Heart Failure Admissions and Admission Rates, 2016 through 2018

Healthcare ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 22
Author(s):  
Clemens Scott Kruse ◽  
Bradley M. Beauvais ◽  
Matthew S. Brooks ◽  
Michael Mileski ◽  
Lawrence V. Fulton
Keyword(s):  
Heart Failure ◽  
The United States ◽  
Explanatory Models ◽  
Gradient Boosting ◽  
County Level ◽  
Unit Of Analysis ◽  
Hospital Unit ◽  
Admission Rates ◽  
Disease Costs ◽  
Heart Failure Admission

Background: Approximately 6.5 to 6.9 million individuals in the United States have heart failure, and the disease costs approximately $43.6 billion in 2020. This research provides geographical incidence and cost 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. 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 diagnostic-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 are estimated. Results: The incidence of heart failure has increased over time with the highest intensities in the East and center of the country; however, several Northern states have seen large increases since 2016. The best predictive model for the number of diagnoses (hospital unit of analysis) was an extremely randomized tree ensemble (predictive R2 = 0.86). The important variables in this model included workload metrics and hospital type. State-level spatial lag models using first-order Queen criteria were best at estimating heart failure admission rates (R2 = 0.816). At the county level, OLS was preferred over any GIS model based on Moran’s I and resultant R2; however, none of the traditional models performed well (R2 = 0.169 for the OLS). Gradient-boosted tree models predicted 36% of the total sum of squares; 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. Costs of DRGs in the study increased $61 billion from 2016 through 2018. The increase in the more expensive DRG 291 outpaced others with an associated increase of $92 billion. With the increase in demand and steady-state supply of cardiologists, the costs are likely to balloon over the next decade. Models such as the ones presented here are needed to inform healthcare leaders.

Sign in / Sign up

Export Citation Format

Share Document