R for Healthcare Exercises: 20 Practice Problems
Twenty practice problems for healthcare data analysis in R: survival, odds ratios, longitudinal data, risk scores, prevalence. Hidden solutions.
RRun this once before any exercise
library(dplyr)
library(survival)
library(broom)
Exercise 1: Prevalence
Difficulty: Beginner.
Show solution
RInteractive R
cases <- 250; population <- 10000
cases / population
Exercise 2: Incidence rate
Difficulty: Intermediate.
Show solution
RInteractive R
new_cases <- 30; person_years <- 5000
new_cases / person_years
Exercise 3: Sensitivity and specificity
Difficulty: Intermediate.
Show solution
RInteractive R
TP <- 80; FN <- 20; TN <- 850; FP <- 50
list(sens = TP/(TP+FN), spec = TN/(TN+FP))
Exercise 4: Positive predictive value
Difficulty: Intermediate.
Show solution
RInteractive R
TP <- 80; FP <- 50
TP / (TP + FP)
Exercise 5: Relative risk
Difficulty: Intermediate.
Show solution
RInteractive R
# 2x2: exposed/disease
m <- matrix(c(40, 60, 20, 80), 2, 2)
risk_exp <- m[1,1] / sum(m[1,])
risk_un <- m[2,1] / sum(m[2,])
risk_exp / risk_un
Exercise 6: Odds ratio
Difficulty: Intermediate.
Show solution
RInteractive R
m <- matrix(c(40, 60, 20, 80), 2, 2)
(m[1,1] * m[2,2]) / (m[1,2] * m[2,1])
Exercise 7: Kaplan-Meier survival
Difficulty: Advanced.
Show solution
RInteractive R
fit <- survfit(Surv(time, status) ~ 1, data = lung)
plot(fit)
Exercise 8: KM by group
Difficulty: Advanced.
Show solution
RInteractive R
fit <- survfit(Surv(time, status) ~ sex, data = lung)
plot(fit, col = 1:2)
Exercise 9: Log-rank test
Difficulty: Advanced.
Show solution
RInteractive R
survdiff(Surv(time, status) ~ sex, data = lung)
Exercise 10: Cox PH model
Difficulty: Advanced.
Show solution
RInteractive R
fit <- coxph(Surv(time, status) ~ age + sex, data = lung)
summary(fit)
Exercise 11: Hazard ratio from Cox
Difficulty: Advanced.
Show solution
RInteractive R
fit <- coxph(Surv(time, status) ~ age + sex, data = lung)
exp(coef(fit))
Exercise 12: Median survival time
Difficulty: Advanced.
Show solution
RInteractive R
fit <- survfit(Surv(time, status) ~ 1, data = lung)
summary(fit)$table["median"]
Exercise 13: 5-year survival rate
Difficulty: Advanced.
Show solution
RInteractive R
fit <- survfit(Surv(time, status) ~ 1, data = lung)
summary(fit, times = 365*5)$surv
Exercise 14: Logistic regression for disease
Difficulty: Intermediate.
Show solution
RInteractive R
df <- tibble(age = sample(20:80, 200, replace = TRUE),
smoke = sample(0:1, 200, replace = TRUE),
disease = rbinom(200, 1, 0.2))
fit <- glm(disease ~ age + smoke, data = df, family = binomial)
summary(fit)
Exercise 15: BMI calculation
Difficulty: Beginner.
Show solution
RInteractive R
weight_kg <- 70; height_m <- 1.75
weight_kg / height_m^2
Exercise 16: BMI category
Difficulty: Intermediate.
Show solution
RInteractive R
bmi <- c(17, 22, 28, 32)
cut(bmi, breaks = c(-Inf, 18.5, 25, 30, Inf),
labels = c("under","normal","over","obese"))
Exercise 17: Repeated measures (longitudinal mean)
Difficulty: Advanced.
Show solution
RInteractive R
df <- tibble(id = rep(1:5, 3), time = rep(1:3, each = 5),
bp = c(120,130,125,140,135, 118,128,122,138,132, 116,126,120,136,130))
df |> group_by(id) |> summarise(mean_bp = mean(bp))
Exercise 18: Standardize lab values to z-scores
Difficulty: Intermediate.
Show solution
RInteractive R
lab <- c(120, 135, 110, 140, 125)
(lab - mean(lab)) / sd(lab)
Exercise 19: Detect outlier vital signs
Difficulty: Intermediate.
Show solution
RInteractive R
hr <- c(70, 72, 75, 68, 130, 71, 30)
hr[hr < 50 | hr > 120]
Exercise 20: Compute days between visits
Difficulty: Intermediate.
Show solution
RInteractive R
visits <- as.Date(c("2024-01-15","2024-02-20","2024-04-05"))
diff(visits)
What to do next
- R-for-Biostatistics-Exercises (coming), statistical methods deep.
- Linear-Regression-Exercises (shipped), risk modeling.