library(survival)
library(readxl)
#Change according to your data path
data1 <- read_excel("E:/UCSI/MyNotes/AS305 Survival Analysis/Chapter 3/data1.xlsx")
View(data1)
#Example 1
tt <- c(7,6,6,5,2,4)
cens <- c(0,1,0,0,1,1)
Surv(tt, cens)
## [1] 7+ 6 6+ 5+ 2 4
result.km <- survfit(Surv(tt, cens) ~ 1, conf.type="log-log")
summary(result.km)
## Call: survfit(formula = Surv(tt, cens) ~ 1, conf.type = "log-log")
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 2 6 1 0.833 0.152 0.2731 0.975
## 4 5 1 0.667 0.192 0.1946 0.904
## 6 3 1 0.444 0.222 0.0662 0.785
plot(result.km)
result.fh<-survfit(Surv(tt,cens)~1, conf.type="log-log", type="fh")
summary(result.fh)
## Call: survfit(formula = Surv(tt, cens) ~ 1, conf.type = "log-log",
## type = "fh")
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 2 6 1 0.846 0.141 0.306 0.977
## 4 5 1 0.693 0.180 0.229 0.913
## 6 3 1 0.497 0.210 0.101 0.807
#Remark: #survfit: This is a function from the “survival” package in R used for fitting survival curves.
#Surv(tt, cens) ~ 1: This specifies the survival formula. In this case, it’s a simple survival formula with tt representing the survival times and cens representing censoring information. The ~ 1 part indicates that we are fitting a survival curve without considering any specific covariates.
#conf.type = “log-log”: This argument specifies the type of confidence intervals to be computed. In this case, it’s set to “log-log,” which is one of the methods for calculating confidence intervals in survival analysis.
#type = “fh”: This argument specifies the type of survival curve to be computed. In this case, it’s set to “fh,” which stands for Fleming-Harrington. The Fleming-Harrington estimator is used to emphasize early differences in survival curves.
#Example
# Sample data (replace with your own data)
data_group1 <- c(10, 15, 20, 25, 30, 35, 40, 45)
data_group2 <- c(5, 10, 15, 20, 25, 30, 35)
# Create survival objects for each group
surv_obj_group1 <- Surv(data_group1)
surv_obj_group2 <- Surv(data_group2)
# Fit Kaplan-Meier survival curves
fit_group1 <- survfit(surv_obj_group1 ~ 1, data = data.frame(time = data_group1))
fit_group2 <- survfit(surv_obj_group2 ~ 1, data = data.frame(time = data_group2))
# Plot Kaplan-Meier curves
plot(fit_group1, col = "blue", lty = 1, main = "Kaplan-Meier Curves for Group 1 and Group 2")
lines(fit_group2, col = "red", lty = 2)
# Add legend
legend("topright", legend = c("Group 1", "Group 2"), col = c("blue", "red"), lty = 1:2)
# Add labels
xlabel <- "Time"
ylabel <- "Survival Probability"
title(main = "Kaplan-Meier Curves for Group 1 and Group 2", xlab = xlabel, ylab = ylabel)
#Example 3
tt <- c(6,6,6,6,7, 9, 10, 10, 11, 13, 16, 17, 19, 20, 22, 23, 25, 32, 32, 34, 35)
cens <- c(1,1,1,0,1,0,1,0,0,1,1,0,0,0,1,1,0,0,0,0,0)
dataG1<-Surv(tt, cens)
result1<-survfit(dataG1 ~ 1, conf.type="log-log")
summary(result1)
## Call: survfit(formula = dataG1 ~ 1, conf.type = "log-log")
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 6 21 3 0.857 0.0764 0.620 0.952
## 7 17 1 0.807 0.0869 0.563 0.923
## 10 15 1 0.753 0.0963 0.503 0.889
## 13 12 1 0.690 0.1068 0.432 0.849
## 16 11 1 0.627 0.1141 0.368 0.805
## 22 7 1 0.538 0.1282 0.268 0.747
## 23 6 1 0.448 0.1346 0.188 0.680
tt2 <- c(1,1,2,2,3,4,4,5,5,8,8,8,8,11,11,12,12,15,17,22,23)
cens2 <- c(1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1)
dataG2<-Surv(tt2, cens2)
result2<-survfit(dataG2 ~ 1, conf.type="log-log")
summary(result2)
## Call: survfit(formula = dataG2 ~ 1, conf.type = "log-log")
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 1 21 2 0.9048 0.0641 0.67005 0.975
## 2 19 2 0.8095 0.0857 0.56891 0.924
## 3 17 1 0.7619 0.0929 0.51939 0.893
## 4 16 2 0.6667 0.1029 0.42535 0.825
## 5 14 2 0.5714 0.1080 0.33798 0.749
## 8 12 4 0.3810 0.1060 0.18307 0.578
## 11 8 2 0.2857 0.0986 0.11656 0.482
## 12 6 2 0.1905 0.0857 0.05948 0.377
## 15 4 1 0.1429 0.0764 0.03566 0.321
## 17 3 1 0.0952 0.0641 0.01626 0.261
## 22 2 1 0.0476 0.0465 0.00332 0.197
## 23 1 1 0.0000 NaN NA NA
plot(result1, col = "blue", lty = 1, main = "Kaplan-Meier Curves for with treatment and placebo")
lines(result2, col = "red", lty = 1)
#plot(result)
#Example 4: smoking
group<-as.factor(data1$Group)
status<-as.factor(data1$status)
day<-as.factor(data1$day)
data1
surv.object <- with(data1, Surv(day,status))
surv.object
## [1] 4+ 7 8+ 29+ 29 31+ 40 65 69 78+ 79+ 106 107+ 129 130+
## [16] 140+ 142+ 149 158+ 160 161 162+ 187 188+ 197 204+ 208+ 221 228 231+
fit<-survival::survfit(Surv(day,status) ~ Group, data=data1)
fit<-survival::survfit(surv.object ~ Group, data=data1)
summary(fit)
## Call: survfit(formula = surv.object ~ Group, data = data1)
##
## Group=1
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 7 16 1 0.938 0.0605 0.826 1.000
## 29 14 1 0.871 0.0856 0.718 1.000
## 65 12 1 0.798 0.1048 0.617 1.000
## 149 7 1 0.684 0.1386 0.460 1.000
## 160 5 1 0.547 0.1651 0.303 0.989
## 187 3 1 0.365 0.1852 0.135 0.987
## 221 1 1 0.000 NaN NA NA
##
## Group=2
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 40 12 1 0.917 0.0798 0.7729 1.000
## 69 11 1 0.833 0.1076 0.6470 1.000
## 106 8 1 0.729 0.1355 0.5066 1.000
## 129 7 1 0.625 0.1510 0.3893 1.000
## 161 6 1 0.521 0.1577 0.2877 0.943
## 197 5 1 0.417 0.1568 0.1993 0.871
## 228 2 1 0.208 0.1669 0.0433 1.000
plot(fit, xlab="Survival Time in Days", ylab="% Surviving", yscale=100, col=c("red", "blue"), main="Survival distribution by group")
legend("topright", title="Group", c("smokers", "non-smokers"), fill = c("red", "blue"))
#Example 5: Generating survival data
# Set a seed for reproducibility
set.seed(123)
# Number of observations
n <- 100
# Generate covariate data (optional)
covariate_data <- data.frame(
age = rnorm(n, mean = 50, sd = 10),
sex = sample(c("Male", "Female"), size = n, replace = TRUE)
)
# Generate survival times
survival_times <- rexp(n, rate = 0.02) # Exponential distribution with a hazard rate of 0.02
# Generate censoring indicator (0 for event, 1 for censored)
censoring_indicator <- rbinom(n, size = 1, prob = 0.2)
# Combine survival times and censoring indicator into a survival object
survival_data <- Surv(time = survival_times, event = 1 - censoring_indicator)
# Combine covariate data and survival data into a dataframe
survival_df <- data.frame(survival_data, covariate_data)
# Display the first few rows of the dataset
head(survival_df)
survival_df
#Example 6: Lung data
# install.packages(c("lubridate", "ggsurvfit", "gtsummary", "tidycmprsk"))
library(lubridate)
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
library(ggsurvfit)
## Loading required package: ggplot2
library(gtsummary)
## #StandWithUkraine
library(tidycmprsk)
##
## Attaching package: 'tidycmprsk'
## The following object is masked from 'package:gtsummary':
##
## trial
# devtools::install_github("zabore/condsurv")
library(condSURV)
## Warning in .recacheSubclasses(def@className, def, env): undefined subclass
## "ndiMatrix" of class "replValueSp"; definition not updated
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
lung <-
lung %>%
mutate(
status = recode(status, `1` = 0, `2` = 1)
)
head(lung[, c("time", "status", "sex")])
Surv(lung$time, lung$status)[1:10]
## [1] 306 455 1010+ 210 883 1022+ 310 361 218 166
s1 <- survfit(Surv(time, status) ~ 1, data = lung)
str(s1)
## List of 16
## $ n : int 228
## $ time : num [1:186] 5 11 12 13 15 26 30 31 53 54 ...
## $ n.risk : num [1:186] 228 227 224 223 221 220 219 218 217 215 ...
## $ n.event : num [1:186] 1 3 1 2 1 1 1 1 2 1 ...
## $ n.censor : num [1:186] 0 0 0 0 0 0 0 0 0 0 ...
## $ surv : num [1:186] 0.996 0.982 0.978 0.969 0.965 ...
## $ std.err : num [1:186] 0.0044 0.00885 0.00992 0.01179 0.01263 ...
## $ cumhaz : num [1:186] 0.00439 0.0176 0.02207 0.03103 0.03556 ...
## $ std.chaz : num [1:186] 0.00439 0.0088 0.00987 0.01173 0.01257 ...
## $ type : chr "right"
## $ logse : logi TRUE
## $ conf.int : num 0.95
## $ conf.type: chr "log"
## $ lower : num [1:186] 0.987 0.966 0.959 0.947 0.941 ...
## $ upper : num [1:186] 1 1 0.997 0.992 0.989 ...
## $ call : language survfit(formula = Surv(time, status) ~ 1, data = lung)
## - attr(*, "class")= chr "survfit"
survfit2(Surv(time, status) ~ 1, data = lung) %>%
ggsurvfit() +
labs(
x = "Days",
y = "Overall survival probability"
)
survfit2(Surv(time, status) ~ 1, data = lung) %>%
ggsurvfit() +
labs(
x = "Days",
y = "Overall survival probability"
) +
add_confidence_interval()
survfit2(Surv(time, status) ~ 1, data = lung) %>%
ggsurvfit() +
labs(
x = "Days",
y = "Overall survival probability"
) +
add_confidence_interval() +
add_risktable()
#Example 7: Estimating x years of survival
summary(survfit(Surv(time, status) ~ 1, data = lung), times = 365.25)
## Call: survfit(formula = Surv(time, status) ~ 1, data = lung)
##
## time n.risk n.event survival std.err lower 95% CI upper 95% CI
## 365 65 121 0.409 0.0358 0.345 0.486
survfit(Surv(time, status) ~ 1, data = lung) %>%
tbl_survfit(
times = 365.25,
label_header = "**1-year survival (95% CI)**"
)
| Characteristic | 1-year survival (95% CI) |
|---|---|
| Overall | 41% (34%, 49%) |
#Example 8: Estimating median survival time
survfit(Surv(time, status) ~ 1, data = lung)
## Call: survfit(formula = Surv(time, status) ~ 1, data = lung)
##
## n events median 0.95LCL 0.95UCL
## [1,] 228 165 310 285 363