library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.2.1 ✔ readr 2.2.0
## ✔ forcats 1.0.1 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.3 ✔ tibble 3.3.1
## ✔ lubridate 1.9.5 ✔ tidyr 1.3.2
## ✔ purrr 1.2.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(janitor)
##
## Attaching package: 'janitor'
##
## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.test
library(survival)
library(gtsummary)
lung2 <- survival::lung %>%
clean_names()
lung3 <- lung2 %>%
mutate(
status = as_factor(case_match(status, 1 ~ "Censored", 2 ~ "Death")),
sex = as_factor(case_match(sex, 1 ~ "Male", 2 ~ "Female")),
ph_ecog = as_factor(ph_ecog),
ph_karno = as.numeric(ph_karno),
pat_karno = as.numeric(pat_karno)
)
## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `status = as_factor(case_match(status, 1 ~ "Censored", 2 ~
## "Death"))`.
## Caused by warning:
## ! `case_match()` was deprecated in dplyr 1.2.0.
## ℹ Please use `recode_values()` instead.
nrow(lung3)
## [1] 228
lung3 %>%
select(time, age, meal_cal, wt_loss) %>%
summary()
## time age meal_cal wt_loss
## Min. : 5.0 Min. :39.00 Min. : 96.0 Min. :-24.000
## 1st Qu.: 166.8 1st Qu.:56.00 1st Qu.: 635.0 1st Qu.: 0.000
## Median : 255.5 Median :63.00 Median : 975.0 Median : 7.000
## Mean : 305.2 Mean :62.45 Mean : 928.8 Mean : 9.832
## 3rd Qu.: 396.5 3rd Qu.:69.00 3rd Qu.:1150.0 3rd Qu.: 15.750
## Max. :1022.0 Max. :82.00 Max. :2600.0 Max. : 68.000
## NAs :47 NAs :14
The overall N = 228. Age’s median and mean are practically identical given the age range of 39 to 82 years old. Time and age have no missing values, however mean_cal has 47 missing values and wt_loss has 14 missing values.
The grouping variable I am choosing to analyze is sex.
tbl1_bysex <- lung3 %>%
dplyr::select(sex, age, time, status, ph_ecog, ph_karno, pat_karno, meal_cal, wt_loss) %>%
tbl_summary(
by = sex,
statistic = all_continuous() ~ '{median} [{p25}. {p75}]',
digits = all_continuous() ~ 1,
label = list(
age ~ 'Age (years)',
time ~ 'Follow-up Time (days)',
status ~ 'Vital Status',
ph_ecog ~ 'Physician-Rated ECOG Performance Status',
ph_karno ~ 'Physician-Rated Karnofsky Score (0-100)',
pat_karno ~ 'Patient-Rated Karnofsky Score (0-100)',
meal_cal ~ 'Calories Consumed at Meals (kcal)',
wt_loss ~ 'Weight Lost in the Last 6 Months (6 lbs)'
),
missing = 'ifany'
) %>%
add_overall() %>%
bold_labels
tbl1_bysex
| Characteristic | Overall N = 2281 |
Male N = 1381 |
Female N = 901 |
|---|---|---|---|
| Age (years) | 63.0 [56.0. 69.0] | 64.0 [57.0. 70.0] | 61.0 [55.0. 68.0] |
| Follow-up Time (days) | 255.5 [166.5. 399.0] | 224.0 [144.0. 371.0] | 292.5 [194.0. 450.0] |
| Vital Status | |||
| Death | 165 (72%) | 112 (81%) | 53 (59%) |
| Censored | 63 (28%) | 26 (19%) | 37 (41%) |
| Physician-Rated ECOG Performance Status | |||
| 0 | 63 (28%) | 36 (26%) | 27 (30%) |
| 1 | 113 (50%) | 71 (52%) | 42 (47%) |
| 2 | 50 (22%) | 29 (21%) | 21 (23%) |
| 3 | 1 (0.4%) | 1 (0.7%) | 0 (0%) |
| Unknown | 1 | 1 | 0 |
| Physician-Rated Karnofsky Score (0-100) | |||
| 50 | 6 (2.6%) | 4 (2.9%) | 2 (2.2%) |
| 60 | 19 (8.4%) | 11 (8.0%) | 8 (8.9%) |
| 70 | 32 (14%) | 20 (15%) | 12 (13%) |
| 80 | 67 (30%) | 40 (29%) | 27 (30%) |
| 90 | 74 (33%) | 45 (33%) | 29 (32%) |
| 100 | 29 (13%) | 17 (12%) | 12 (13%) |
| Unknown | 1 | 1 | 0 |
| Patient-Rated Karnofsky Score (0-100) | |||
| 30 | 2 (0.9%) | 1 (0.7%) | 1 (1.1%) |
| 40 | 2 (0.9%) | 1 (0.7%) | 1 (1.1%) |
| 50 | 4 (1.8%) | 2 (1.5%) | 2 (2.2%) |
| 60 | 30 (13%) | 18 (13%) | 12 (13%) |
| 70 | 41 (18%) | 30 (22%) | 11 (12%) |
| 80 | 51 (23%) | 32 (24%) | 19 (21%) |
| 90 | 60 (27%) | 31 (23%) | 29 (33%) |
| 100 | 35 (16%) | 21 (15%) | 14 (16%) |
| Unknown | 3 | 2 | 1 |
| Calories Consumed at Meals (kcal) | 975.0 [635.0. 1,150.0] | 1,025.0 [768.0. 1,175.0] | 925.0 [588.0. 1,075.0] |
| Unknown | 47 | 24 | 23 |
| Weight Lost in the Last 6 Months (6 lbs) | 7.0 [0.0. 16.0] | 8.0 [0.5. 19.0] | 4.0 [0.0. 11.0] |
| Unknown | 14 | 10 | 4 |
| 1 Median [Q1. Q3]; n (%) | |||
fig1_AgevsTime <- ggplot(lung3, aes(x = age, y = time, color = sex)) +
geom_point(alpha = 0.6) +
geom_smooth(method = 'lm', se = FALSE) +
scale_color_brewer(palette = 'Set2') +
labs(title = 'Survival Time vs Age based on Sex',
x = 'Age (years)',
y = 'Survival Time (days)',
color = 'Sex') +
theme_minimal(base_size = 12) +
theme(legend.position = 'bottom',
plot.title = element_text(face = 'bold', hjust = 0.5))
fig1_AgevsTime
## `geom_smooth()` using formula = 'y ~ x'
The overall study included 228 patients (138 male and 90 female) with median age of 63 years. The scatterplot shows little relationship between age and survival time. The fitted line declines slightly with men, however, it is mostly flat across women, Survival times span from near 0 to over 1000 days at nearly every age. The female line sits at or above the male line for most of the age range, which matches the sex difference described in Table 1.