Importance: Using hospital quality ratings, patients are able to make a better decision in what hospital they want to be treated and where the best care is available in state of California, based on overall hospital performance or based on particular medical condition or procedure.

Question: Can we predict hospital quality ratings based on risk adjusted mortality rates, number of deaths, number of cases, medical procedures performed and medical conditions treated for 2012-2013?

Dataset: is available from California Hospital Inpatient Mortality Rates and Quality Ratings, 2012-2013.

• Risk-adjusted mortality rates
• Number of deaths and number of cases
• 8 medical conditions treated and 6 medical procedures performed
• Year: 2012 and 2013
• County: 55 counties
• Hospital: 341 hospitals
• Longitude and latitude of hospitals
• Hospital Ratings: As Expected, Better and Worse

Density Plots for # of Cases, # of Deaths and Risk Adjusted Mortality Rate by Hospital Ratings.

• There is a possible association between the risk adjusted mortality rate and hospital ratings.

Density Plots for Risk Adjusted Mortality Rate by Procedures Performed and Hospital Ratings.

• There is association between the risk adjusted mortality rate and hospital ratings.

Density Plots for Risk Adjusted Mortality Rate by Conditions Treated and Hospital Ratings.

• There is association between the risk adjusted mortality rate and hospital ratings.

Associations between medical procedures or conditions with hospital ratings, number of cases, number of deaths and risk adjusted mortality rate.

Procedures.

## # A tibble: 6 x 4
##      Procedure.Condition all_cases all_deaths all_mortality_rate
##                   <fctr>     <int>      <int>              <dbl>
## 1             AAA Repair      4927         59              508.5
## 2 Carotid Endarterectomy     12478         60              290.2
## 3             Craniotomy     30164       2159             2354.6
## 4   Esophageal Resection       619         28              436.9
## 5   Pancreatic Resection      3356         93             1002.8
## 6                    PCI     78660       2028              793.6

• The most severe outcomes are for PCI, Craniotomy and Pancreatic Resection procedures.

Conditions.

## # A tibble: 8 x 4
##   Procedure.Condition all_cases all_deaths all_mortality_rate
##                <fctr>     <int>      <int>              <dbl>
## 1        Acute Stroke    217956      20461            26582.9
## 2                 AMI     93594       5731             3863.4
## 3       GI Hemorrhage     94804       2099             1597.8
## 4       Heart Failure    155066       4778             2200.0
## 5        Hip Fracture     32245        744              945.8
## 6   Pancreatic Cancer      1787         43              632.0
## 7    Pancreatic Other      1425         41              590.0
## 8           Pneumonia     20630       1019              552.5

• The most severe outcomes are for Acute Stroke, Heart Failure, AMI and GI Hemorrhage conditions.

Hospital Ratings.

##                         
##                          As Expected      Better       Worse
##   AAA Repair              5.80218873  0.00000000  0.04129672
##   Acute Stroke           10.81973983  1.01176956  0.90852777
##   AMI                    11.06752013  0.47491224  0.64009911
##   Carotid Endarterectomy  8.19739831  0.00000000  0.14453851
##   Craniotomy              5.40986992  0.37167045  0.37167045
##   Esophageal Resection    1.54862688  0.00000000  0.00000000
##   GI Hemorrhage          12.28577328  0.20648358  0.35102209
##   Heart Failure          11.48048730  0.47491224  0.76398926
##   Hip Fracture            8.71360727  0.00000000  0.08259343
##   Pancreatic Cancer       2.89077018  0.00000000  0.04129672
##   Pancreatic Other        2.64298988  0.00000000  0.04129672
##   Pancreatic Resection    3.84059467  0.00000000  0.08259343
##   PCI                     5.78154037  0.12389015  0.26842866
##   Pneumonia               3.03530869  0.08259343  0.00000000

• Better and worse ratings are for Craniotomy, PCI, Acute Stroke, AMI, Heart Failure and GI Hemorrhage.

Conclusions:

• There is association between the risk adjusted mortality rate and hospital ratings.
  • Lower the risk adjusted mortality rate, better the hospital ratings.
  • Higher the risk adjusted mortality rate, worse the hospital ratings.
• Procedures:
  • with severe outcomes: PCI, Craniotomy and Pancreatic Resection.
• Conditions:
  • with severe outcomes: Acute Stroke, AMI, Heart Failure and GI Hemorrhage.

Mapping of overall hospital quality ratings and mean mortality rate over all conditions and procedures.

Number of hospitals with ratings "As Expected": 172, "Better": 69 and "Worse": 99.

• Top 5 hospitals with the best quality ratings:

## # A tibble: 5 x 1
##                                      Hospital
##                                        <fctr>
## 1 Kaiser Foundation Hospital – Redwood City
## 2       Kaiser Foundation Hospital – Sunset
## 3           Centinela Hospital Medical Center
## 4                      Scripps Green Hospital
## 5                 Cedars Sinai Medical Center

• Top 5 hospitals with the lowest mean mortality rate:

## # A tibble: 5 x 1
##                                     Hospital
##                                       <fctr>
## 1                 Corcoran District Hospital
## 2 Eastern Plumas Hospital – Portola Campus
## 3                       Glenn Medical Center
## 4    Good Samaritan Hospital – Bakersfield
## 5                  Hoag Orthopedic Institute

Summary of hospital quality ratings and mortality rates for Acute Stroke, AMI and Heart Failure conditions, PCI, Craniotomy and Pancreatic Resection procedures.

Top 5 hospitals for treatment of Heart Failure condition.

## # A tibble: 5 x 1
##                               Hospital
##                                 <fctr>
## 1 Adventist Medical Center – Reedley
## 2             Anaheim General Hospital
## 3                Sherman Oaks Hospital
## 4           Barstow Community Hospital
## 5    Centinela Hospital Medical Center

Top 5 hospitals to perform the Pancreatic Resection procedure.

## # A tibble: 5 x 1
##                                           Hospital
##                                             <fctr>
## 1                    Alameda County Medical Center
## 2            Community Hospital Monterey Peninsula
## 3     Community Hospital of The Monterey Peninsula
## 4 Community Memorial Hospital – San Buenaventura
## 5                              Eden Medical Center

Approach

• Predict hospital quality ratings using random forests and classification decision trees.
• Train the models and evaluate the model performances on 2012 training data.
• Test the model performances on 2013 test data.

Hospital Ratings Prediction Using Random Forests for Dataset in Wide Format.

Split the Data Set into 2012 training and 2013 test sets.

train_wide <- df_wide[which(df_wide$Year==2012),]
test_wide_original <- df_wide[which(df_wide$Year==2013),]
test_wide <- subset(test_wide_original, select = -Hospital.Ratings)

Feature Enginering with Random Forests

• The most important variables are Heart Failure, GI Hemorrhage, AMI and Acute Stroke, Hip Fracture conditions.

Model performance on train_wide dataset using all variables.

##             As Expected Better Worse class.error
## As Expected         296     18    12  0.09202454
## Better                9     36     2  0.23404255
## Worse                23      6    36  0.44615385

• Accuracy: 0.8387 and Error Rate: 0.1613

Predictions on test_wide dataset using all variables.

##              Predicted
## Actual        As Expected Better Worse
##   As Expected         291     20    13
##   Better                7     40     4
##   Worse                25      1    42

• Accuracy: 0.842 and Error Rate: 0.158

Hospital Ratings Prediction Using Classification Decision Trees (CART).

Model 1: All variables are included in tree construction.

Predictions on test_wide dataset.

##              Predicted
## Actual        As Expected Better Worse
##   As Expected         287     24    13
##   Better                4     44     3
##   Worse                26     13    29

• Accuracy: 0.8126
• Error Rate: 0.1874

Model 2: AMI, GIHemorrhage and HeartFailure variables are included in tree construction.

Predictions on test_wide dataset.

##              Predicted
## Actual        As Expected Better Worse
##   As Expected         292     27     5
##   Better                5     46     0
##   Worse                29     30     9

• Accuracy: 0.7833
• Error Rate: 0.2167

Conclusions:

• Accuracy on the test data set using
  • Random Forests with all variables: 0.842
  • CART with all variables: 0.8126
  • CART with three variables: 0.7833
• Random forests gives the best performance, however is not good enough to predict hospitals with the best care in future.
• Random forests predicts that classification of hospital ratings depend on conditions and not procedures with the most severe patient outcomes.

• Predict hospital quality ratings using multinomial logistic regression.
  • Train the model and evaluate the model performance on 2012 training data.
  • Test the model performance on 2013 test data.
• Compare three models: random forests, classification decision trees and multinomial logistic regression.
  • Summarize which model gives the best performance on 2012 training data and on 2013 test data.
  • Choose the best model and test its performance on 2014 test data.
• Recommend which hospitals will have the best care in future using predicted hospital ratings.

Top 25 hospitals with the best overall ratings and the lowest mean mortality rate in state of California.

Top 10 hospitals with the best overall ratings and the lowest mean mortality rate in state of California.

##  [1] Encino Hospital Medical Center               
##  [2] Feather River Hospital                       
##  [3] Chino Valley Medical Center                  
##  [4] Marina Del Rey Hospital                      
##  [5] Paradise Valley Hospital                     
##  [6] Pacific Alliance Medical Center, Inc.        
##  [7] Kaiser Foundation Hospital – Oakland Campus
##  [8] Desert Valley Hospital                       
##  [9] Sutter Solano Medical Center                 
## [10] Sherman Oaks Hospital                        
## 341 Levels: Adventist Medical Center ...

Top hospitals with the best ratings and the lowest mean mortality rate for Acute Stroke, AMI and Heart Failure conditions.

There are 7 hospitals that have the best ratings and the lowest mortality rate for the most severe conditions.

## [1] Encino Hospital Medical Center Anaheim General Hospital      
## [3] Sherman Oaks Hospital          Encino Hospital Medical Center
## [5] Desert Valley Hospital         Paradise Valley Hospital      
## [7] Scripps Green Hospital        
## 341 Levels: Adventist Medical Center ...

Top hospitals with the best ratings and the lowest mean mortality rate for PCI, Craniotomy and Pancreatic Resection procedures.

There are 7 hospitals that have the best ratings and the lowest mortality rate for the most severe procedures.

## [1] El Camino Hospital                                  
## [2] California Pacific Medical Center – Pacific Campus
## [3] Glendale Adventist Medical Center – Wilson Terrace
## [4] Community Hospital Monterey Peninsula               
## [5] Community Hospital of The Monterey Peninsula        
## [6] Community Memorial Hospital – San Buenaventura    
## [7] Fresno Heart and Surgical Hospital                  
## 341 Levels: Adventist Medical Center ...

Capstone Project Files are available online

• Rpubs
• github