Exploratory Data Visualization

Medical Coverage by State and Illnesses

Brief

You will be looking at a subset of a United States medical expenditures dataset with information on costs for different medical conditions and in different areas of the country.

You should do the following:

  • Make a plot that answers the question: what is the relationship between mean covered charges (average_covered_charges) and mean total payments (average_total_payments) in New York?
  • Make a plot (possibly multi-panel) that answers the question: how does the relationship between mean covered charges (average_covered_charges) and mean total payments (average_total_payments) vary by medical condition (drg_definition) and the state in which care was received (provider_state)?
library(janitor)
## 
## Attaching package: 'janitor'
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
Inpatient_Charges <- read_csv("Inpatient_Charges.csv",
                              show_col_types = FALSE)
Inpatient_Charges <- janitor::clean_names(Inpatient_Charges)
Inpatient_Charges_Sample <- Inpatient_Charges %>%
  filter(provider_state %in% c("TX","CA","NY","FL","WA")) %>%
  group_by(provider_state,drg_definition) %>%
  sample_frac(0.10)
Inpatient_Charges_Sample %>% tabyl(drg_definition) %>% arrange(desc(n)) %>% head(10) %>% kable()
drg_definition n percent
871 - SEPTICEMIA OR SEVERE SEPSIS W/O MV 96+ HOURS W MCC 84 0.0144878
292 - HEART FAILURE & SHOCK W CC 80 0.0137979
194 - SIMPLE PNEUMONIA & PLEURISY W CC 78 0.0134529
470 - MAJOR JOINT REPLACEMENT OR REATTACHMENT OF LOWER EXTREMITY W/O MCC 78 0.0134529
872 - SEPTICEMIA OR SEVERE SEPSIS W/O MV >96 HOURS W/O MCC 78 0.0134529
291 - HEART FAILURE & SHOCK W MCC 77 0.0132804
392 - ESOPHAGITIS, GASTROENT & MISC DIGEST DISORDERS W/O MCC 77 0.0132804
690 - KIDNEY & URINARY TRACT INFECTIONS W/O MCC 77 0.0132804
603 - CELLULITIS W/O MCC 75 0.0129355
190 - CHRONIC OBSTRUCTIVE PULMONARY DISEASE W MCC 74 0.0127630 
Inpatient_Charges_Sample %>% head(1) %>% t() %>% kable()
drg_definition 001 - HEART TRANSPLANT OR IMPLANT OF HEART ASSIST SYSTEM W MCC
provider_id 50454
provider_name UCSF MEDICAL CENTER
provider_street_address 505 PARNASSUS AVE, BOX 0296
provider_city SAN FRANCISCO
provider_state CA
provider_zip_code 94143
hospital_referral_region_hrr_description CA - San Francisco
total_discharges 19
average_covered_charges 1578240
average_total_payments 394118.9
average_medicare_payments 355075.8

Plot 1

g1 <- ggplot(Inpatient_Charges_Sample, aes(x=average_total_payments,
                       y=average_covered_charges))+
  geom_point()+
  stat_smooth()
g1
## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'

Plot 2

g2 <- ggplot(Inpatient_Charges_Sample, aes(x=average_total_payments,
                       y=average_covered_charges,    
                       group=provider_state))+
  geom_point()+
  stat_smooth(aes(colour=provider_state,fill=provider_state))
g2
## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'

Plot 3

g3 <- ggplot(Inpatient_Charges_Sample, aes(x=average_total_payments,
                       y=average_covered_charges))+
  geom_point()+
  stat_smooth(aes(colour=provider_state))
g3+theme(legend.position="bottom")
## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'

Plot 4

g4 <- ggplot(Inpatient_Charges_Sample, aes(x=average_total_payments,
                       y=average_covered_charges, colour=drg_definition))+
  geom_point()+
  facet_grid(. ~ provider_state)

g4+theme(legend.position="none") + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1))