setwd("/Users/michelesantana/Documents/IGPA/Sage Kim Lung Cancer/Rcode")
lung <- read_csv('lungEMRChicago-3-18-2023-Alex.csv') Eligibility criteria: Aged 50 to 80, 20 pack year smoking history, and no prior history of lung cancer
# total count of all participants
all_n = lung %>%
select(PATIENT_ID) %>%
count()
all_n
# for this calculation we make an assumption that those with missing values have no history of lung cancer
n_elig = lung %>%
filter(agecat >= 2, packyear20 == "1.00", historyca == "0.00" | historyca == "#NULL!")
n_elig %>%
filter(smokingstatus >= 2) %>%
count() / all_n * 100
count(n_elig)
# n = 304
######### create a new variable to indicate patient is lung cancer screening eligible
lung <- lung %>%
mutate(screen_elig = ifelse(agecat >= 2 & packyear20 == "1.00" & (historyca == "0.00" | historyca == "#NULL!"), 1, 0))
lung %>%
filter(screen_elig == 1) %>%
count()
# n = 304, this matches so the variable is correctly createdThe total count of participants in the study is 7,198 patients. 304 patients (4.22%) undergoing diagnostic screening/testing met the eligibility requirements for LDCT lung cancer screening.
Expectation 1 = Yes for racial differences Expectation 2 = Yes, there is an interaction based on gender with Black men and women less likely to meet screening eligibility criteria.
lung <- lung %>%
mutate(raceethnic_cat = ifelse(raceethnic == 1, "White",
ifelse(raceethnic == 2, "Black",
"Hispanic")))
print(
lung %>%
group_by(raceethnic_cat) %>%
count())## # A tibble: 3 × 2
## # Groups: raceethnic_cat [3]
## raceethnic_cat n
## <chr> <int>
## 1 Black 4622
## 2 Hispanic 1619
## 3 White 957lung <- lung %>%
mutate(raceethnic_cat = ifelse(raceethnic_cat == "Hispanic", "Latinx", raceethnic_cat))elig_gender_table <- lung %>%
filter(gender %in% c("Female", "Male")) %>%
group_by(gender) %>%
summarize(Total = n(),
Eligible_Count = sum(screen_elig == 1),
Percent_Eligible = Eligible_Count / Total * 100)
colnames(elig_gender_table) <- c("Gender", "Total Patients", "Screening Eligible Count", "Percent Screening Eligible")
elig_gender_table %>%
kable(align = "lllll",
caption = "Lung Cancer Screening Eligible Patients by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Total Patients | Screening Eligible Count | Percent Screening Eligible |
|---|---|---|---|
| Female | 4,044 | 146 | 3.61 |
| Male | 3,151 | 158 | 5.01 |
elig_race_table =
lung %>%
group_by(raceethnic_cat) %>%
summarize(Total = n(),
Eligible_Count = sum(screen_elig == 1),
Percent_Eligible = Eligible_Count / Total * 100)
colnames(elig_race_table) <- c("Race/Ethnicity", "Total Patients", "Screening Eligible Count", "Percent Screening Eligible")
elig_race_table %>%
kable(align = "lllll",
caption = "Lung Cancer Screening Eligible Patients by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Total Patients | Screening Eligible Count | Percent Screening Eligible |
|---|---|---|---|
| Black | 4,622 | 212 | 4.59 |
| Latinx | 1,619 | 39 | 2.41 |
| White | 957 | 53 | 5.54 |
elig_racegen_table =
lung %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(Total = n(),
Eligible_Count = sum(screen_elig == 1),
Percent_Eligible = Eligible_Count / Total * 100)
colnames(elig_racegen_table) <- c("Gender", "Race/Ethnicity", "Total Patients", "Screening Eligible Count", "Percent Screening Eligible")
# table
elig_racegen_table %>%
kable(align = "lllll",
caption = "Lung Cancer Screening Eligible Patients by Gender and Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Total Patients | Screening Eligible Count | Percent Screening Eligible |
|---|---|---|---|---|
| Female | Black | 2,808 | 114 | 4.06 |
| Female | Latinx | 805 | 11 | 1.37 |
| Female | White | 431 | 21 | 4.87 |
| Male | Black | 1,812 | 98 | 5.41 |
| Male | Latinx | 813 | 28 | 3.44 |
| Male | White | 526 | 32 | 6.08 |
# CREATE A DF WITH ALL SMOKERS
n_smoker =
lung %>%
filter(smokingstatus >= 2)
count(n_smoker)## # A tibble: 1 × 1
## n
## <int>
## 1 4138# n = 4,138
count(n_smoker) / count(lung) * 100## n
## 1 57.48819Of the 7,198 patients in the study, 4,138 (57.49%) are current or former smokers.
Counts of current or former smokers by gender
# patients who are smokers by gender
smoker_gender_table =
lung %>%
filter(gender %in% c("Female", "Male")) %>% # only include Female or Male genders
group_by(gender) %>%
summarize(Total = n(),
Smoker_Count = sum(smokingstatus >= 2),
Percent_Smoker = Smoker_Count / Total * 100)
colnames(smoker_gender_table) <- c("Gender", "Total Patients", "Current or Former Smoker Count", "Percent Smokers")
# table
smoker_gender_table %>%
kable(align = "lllll",
caption = "Patients who are Current or Former Smokers by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Total Patients | Current or Former Smoker Count | Percent Smokers |
|---|---|---|---|
| Female | 4,044 | 2,076 | 51.34 |
| Male | 3,151 | 2,061 | 65.41 |
What percentage of current or former smokers within each gender group are eligible for the lung cancer screening?
smoker_gender_per_table <- lung %>%
filter(smokingstatus >= 2) %>%
filter(gender %in% c("Female", "Male")) %>%
group_by(gender) %>%
summarize("Current or Former Smoker Count" = n(),
"Smokers Screening Eligible Count" = sum(screen_elig == 1, na.rm = TRUE),
"Percent Smokers Screening Eligible" = mean(screen_elig == 1, na.rm = TRUE) * 100)
colnames(smoker_gender_per_table) <- c("Gender", "Current or Former Smoker Count", "Smokers Screening Eligible Count", "Percent Smokers Screening Eligible")
# table
smoker_gender_per_table %>%
kable(align = "lllll",
caption = "Percentage of Current and Former Smokers Eligible for the Lung Cancer Screening by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Current or Former Smoker Count | Smokers Screening Eligible Count | Percent Smokers Screening Eligible |
|---|---|---|---|
| Female | 2,076 | 146 | 7.03 |
| Male | 2,061 | 158 | 7.67 |
Counts of current or former smokers by race
# patients who are smokers by race/ethnicity
smoker_race_table =
lung %>%
group_by(raceethnic_cat) %>%
summarize(Total = n(),
Smoker_Count = sum(smokingstatus >= 2),
Percent_Smoker = Smoker_Count / Total * 100)
colnames(smoker_race_table) <- c("Race/Ethnicity", "Total Patients", "Current or Former Smoker Count", "Percent Smokers")
# table
smoker_race_table %>%
kable(align = "lllll",
caption = "Patients who are Current or Former Smokers by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Total Patients | Current or Former Smoker Count | Percent Smokers |
|---|---|---|---|
| Black | 4,622 | 2,850 | 61.66 |
| Latinx | 1,619 | 717 | 44.29 |
| White | 957 | 571 | 59.67 |
What percentage of current or former smokers of within each racial/ethnic group are eligible for the lung cancer screening?
smoker_race_per_table =
lung %>%
group_by(raceethnic_cat) %>%
summarize(
Total = n(),
Smoker_Count = sum(smokingstatus >= 2),
Smoker_Eligible_Count = sum(screen_elig == 1, na.rm = TRUE),
per_eligible = Smoker_Eligible_Count / Smoker_Count * 100)
colnames(smoker_race_per_table) <- c("Race/Ethnicity", "Total Patients", "Current or Former Smoker Count", "Smokers Screening Eligible Count", "Percent Smokers Screening Eligible")
# table
smoker_race_per_table %>%
kable(align = "lllll",
caption = "Percentage of Current and Former Smokers Eligible for the Lung Cancer Screening by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Total Patients | Current or Former Smoker Count | Smokers Screening Eligible Count | Percent Smokers Screening Eligible |
|---|---|---|---|---|
| Black | 4,622 | 2,850 | 212 | 7.44 |
| Latinx | 1,619 | 717 | 39 | 5.44 |
| White | 957 | 571 | 53 | 9.28 |
Counts of current or former smokers by gender and race
smoker_racegen_table =
lung %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total = n(),
Smoker_Count = sum(smokingstatus >= 2),
per_smoker = Smoker_Count / Total * 100)
colnames(smoker_racegen_table) <- c("Gender", "Race/Ethnicity", "Total Patients", "Current or Former Smoker Count", "Percent Smokers")
# table
smoker_racegen_table %>%
kable(
align = "lllll",
caption = "Patients who are Current or Former Smokers by Gender and Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Total Patients | Current or Former Smoker Count | Percent Smokers |
|---|---|---|---|---|
| Female | Black | 2,808 | 1,582 | 56.34 |
| Female | Latinx | 805 | 255 | 31.68 |
| Female | White | 431 | 239 | 55.45 |
| Male | Black | 1,812 | 1,267 | 69.92 |
| Male | Latinx | 813 | 462 | 56.83 |
| Male | White | 526 | 332 | 63.12 |
What percentage of current or former smokers of within each racial/ethnic and gender group are eligible for the lung cancer screening?
smoker_racegen_per_table =
lung %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total = n(),
Smoker_Count = sum(smokingstatus >= 2),
Smoker_Eligible_Count = sum(screen_elig == 1, na.rm = TRUE),
per_eligible = Smoker_Eligible_Count / Smoker_Count * 100)
colnames(smoker_racegen_per_table) <- c("Gender", "Race/Ethnicity", "Total Patients", "Current or Former Smoker Count", "Smokers Screening Eligible Count", "Percent Smokers Screening Eligible")
#table
smoker_racegen_per_table %>%
kable(align = "lllll",
caption = "Percentage of Current and Former Smokers Eligible for the Lung Cancer Screening by Gender & Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Total Patients | Current or Former Smoker Count | Smokers Screening Eligible Count | Percent Smokers Screening Eligible |
|---|---|---|---|---|---|
| Female | Black | 2,808 | 1,582 | 114 | 7.21 |
| Female | Latinx | 805 | 255 | 11 | 4.31 |
| Female | White | 431 | 239 | 21 | 8.79 |
| Male | Black | 1,812 | 1,267 | 98 | 7.73 |
| Male | Latinx | 813 | 462 | 28 | 6.06 |
| Male | White | 526 | 332 | 32 | 9.64 |
# VARIABLE = malignanto (0 = no; 1 = yes)
diag_n =
lung %>%
filter(malignanto == 1)
count(diag_n)## # A tibble: 1 × 1
## n
## <int>
## 1 707# in total, 707 patients were diagnosed with lung cancer
lung %>%
filter(screen_elig == 1 & malignanto == 1) %>%
count()## # A tibble: 1 × 1
## n
## <int>
## 1 33# Of those eligible for the screening, 33 were diagnosed with lung cancer out of the 304 eligible in total.
# 10.85% of patients who met lung cancer screening guidelines were diagnosed with lung cancer.In total, 707 patients were diagnosed with lung cancer. Of those eligible for the screening, 10.85% (33 patients) were diagnosed with lung cancer.
Counts of patients who met screening guidelines who were diagnosed with lung cancer.
# by gender
diag_eligg_table =
lung %>%
filter(screen_elig == 1) %>%
group_by(gender) %>%
summarize(Total = n(),
diag_screenelig = sum(malignanto == 1, na.rm = TRUE),
per_diagse = diag_screenelig / Total * 100)
colnames(diag_eligg_table) <- c("Gender", "Screening Eligible Count", "Diagnosed Screening Eligible Count", "Percent Screening Eligible Diagnosed")# table
diag_eligg_table %>%
kable(align = "lllll",
caption = "Screening Eligible Patients Diagnosed with Lung Cancer by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Screening Eligible Count | Diagnosed Screening Eligible Count | Percent Screening Eligible Diagnosed |
|---|---|---|---|
| Female | 146 | 19 | 13.01 |
| Male | 158 | 14 | 8.86 |
diag_eligr_table =
lung %>%
filter(screen_elig == 1) %>%
group_by(raceethnic_cat) %>%
summarize(Total = n(),
diag_screenelig = sum(malignanto == 1, na.rm = TRUE),
per_diagse = diag_screenelig / Total * 100)
colnames(diag_eligr_table) <- c("Race/Ethnicity", "Screening Eligible Count", "Diagnosed Screening Eligible Count", "Percent Screening Eligible Diagnosed")diag_eligr_table %>%
kable(align = "lllll",
caption = "Screening Eligible Patients Diagnosed with Lung Cancer by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Screening Eligible Count | Diagnosed Screening Eligible Count | Percent Screening Eligible Diagnosed |
|---|---|---|---|
| Black | 212 | 25 | 11.79 |
| Latinx | 39 | 5 | 12.82 |
| White | 53 | 3 | 5.66 |
diag_elig_genra_table =
lung %>%
filter(screen_elig == 1) %>%
group_by(gender, raceethnic_cat) %>%
summarize(Total = n(),
diag_screenelig = sum(malignanto == 1, na.rm = TRUE),
per_diagse = diag_screenelig / Total * 100)
colnames(diag_elig_genra_table) <- c("Gender", "Race/Ethnicity", "Screening Eligible Count", "Diagnosed Screening Eligible Count", "Percent Screening Eligible Diagnosed")
diag_elig_genra_table %>%
kable(align = "lllll",
caption = "Screening Eligible Patients Diagnosed with Lung Cancer by Gender & Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Screening Eligible Count | Diagnosed Screening Eligible Count | Percent Screening Eligible Diagnosed |
|---|---|---|---|---|
| Female | Black | 114 | 14 | 12.28 |
| Female | Latinx | 11 | 3 | 27.27 |
| Female | White | 21 | 2 | 9.52 |
| Male | Black | 98 | 11 | 11.22 |
| Male | Latinx | 28 | 2 | 7.14 |
| Male | White | 32 | 1 | 3.12 |
Count of patients who are current or former smokers who did not meet screening guidelines who were diagnosed with lung cancer.
n_inelig_diag =
lung %>%
filter(screen_elig == 0 & smokingstatus >= 2 & malignanto == 1)
count(n_inelig_diag)## # A tibble: 1 × 1
## n
## <int>
## 1 492492 current or former smoker patients who did not meet the screening criteria were diagnosed with lung cancer.
% of patients who did not meet the criteria were diagnosed with lung cancer.
count(n_inelig_diag)/count(n_smoker) * 100## n
## 1 11.889811.89% of current or former patients who did NOT meet screening eligibility guidelines were diagnosed with lung cancer.
# ineligible smokers by race
inelig_smoker_race_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(raceethnic_cat) %>%
summarise(Total = n(),
screenINelig_smoker = sum(screen_elig == 0, na.rm = TRUE),
per_ineligsmokers = screenINelig_smoker / Total * 100)
colnames(inelig_smoker_race_count) <- c("Race/Ethnicity", "Smokers Count", "Screening Ineligible Current or Former Smoker Count", "Percent Screening Ineligible Smokers")
inelig_smoker_race_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Smokers Count | Screening Ineligible Current or Former Smoker Count | Percent Screening Ineligible Smokers |
|---|---|---|---|
| Black | 2,850 | 2,638 | 92.56 |
| Latinx | 717 | 678 | 94.56 |
| White | 571 | 518 | 90.72 |
# ineligible diagnosed smokers by race
ineligible_cancerr_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(raceethnic_cat) %>%
summarise(Total = n(),
diag_n = sum(malignanto == 1, na.rm = TRUE),
per_diag = (diag_n / Total * 100),
screenINelig_smoker = sum(screen_elig == 0 & smokingstatus >= 2, na.rm = TRUE),
diag_screenINelig = sum(screen_elig == 0 & smokingstatus >= 2 & malignanto == 1, na.rm = TRUE),
per_diagse = diag_screenINelig / screenINelig_smoker * 100)
colnames(ineligible_cancerr_count) <- c("Race/Ethnicity", "Smoker Count", "Smokers Diagnosed with Lung Cancer Count", "Percent Diagnosed", "Screening Ineligible Smoker Count", "Screening Ineligible Smokers Diagnosed", "Percent Screening Ineligible Smokers Diagnosed")
ineligible_cancerr_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers Diagnosed with Lung Cancer by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Smoker Count | Smokers Diagnosed with Lung Cancer Count | Percent Diagnosed | Screening Ineligible Smoker Count | Screening Ineligible Smokers Diagnosed | Percent Screening Ineligible Smokers Diagnosed |
|---|---|---|---|---|---|---|
| Black | 2,850 | 387 | 13.58 | 2,638 | 362 | 13.72 |
| Latinx | 717 | 59 | 8.23 | 678 | 54 | 7.96 |
| White | 571 | 79 | 13.84 | 518 | 76 | 14.67 |
# ineligible smokers by gender
inelig_smoker_g_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender) %>%
filter(gender %in% c("Female", "Male")) %>%
summarise(Total = n(),
screenINelig_smoker = sum(screen_elig == 0, na.rm = TRUE),
per_ineligsmokers = screenINelig_smoker / Total * 100)
colnames(inelig_smoker_g_count) <- c("Gender", "Smokers Count", "Screening Ineligible Current or Former Smoker Count", "Percent Screening Ineligible Smokers")
inelig_smoker_g_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Smokers Count | Screening Ineligible Current or Former Smoker Count | Percent Screening Ineligible Smokers |
|---|---|---|---|
| Female | 2,076 | 1,930 | 92.97 |
| Male | 2,061 | 1,903 | 92.33 |
# ineligible diagnosed smokers by gender
ineligible_cancerg_count =
lung %>%
group_by(gender) %>%
filter(smokingstatus >= 2) %>%
filter(gender %in% c("Female", "Male")) %>%
summarise(Total = n(),
diag_n = sum(malignanto == 1, na.rm = TRUE),
per_diag = (diag_n / Total * 100),
screenINelig_smoker = sum(screen_elig == 0 & smokingstatus >= 2, na.rm = TRUE),
diag_screenINelig = sum(screen_elig == 0 & smokingstatus >= 2 & malignanto == 1, na.rm = TRUE),
per_diagse = diag_screenINelig / screenINelig_smoker * 100)
colnames(ineligible_cancerg_count) <- c("Gender", "Smoker Count", "Smokers Diagnosed with Lung Cancer Count", "Percent Smokers Diagnosed", "Screening Ineligible Smokers Count", "Screening Ineligible Smokers Diagnosed", "Percent Screening Ineligible Smokers Diagnosed")
ineligible_cancerg_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers Diagnosed with Lung Cancer by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Smoker Count | Smokers Diagnosed with Lung Cancer Count | Percent Smokers Diagnosed | Screening Ineligible Smokers Count | Screening Ineligible Smokers Diagnosed | Percent Screening Ineligible Smokers Diagnosed |
|---|---|---|---|---|---|---|
| Female | 2,076 | 264 | 12.72 | 1,930 | 245 | 12.69 |
| Male | 2,061 | 261 | 12.66 | 1,903 | 247 | 12.98 |
# ineligible smokers by gender and race
inelig_smoker_rg_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarise(Total = n(),
screenINelig_smoker = sum(screen_elig == 0 & smokingstatus >= 2, na.rm = TRUE),
per_ineligsmokers = screenINelig_smoker / Total * 100)
colnames(inelig_smoker_rg_count) <- c("Gender", "Race/Ethnicity", "Smoker Count", "Screening Ineligible Smokers Count", "Percent Screening Ineligible Smokers")
inelig_smoker_rg_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers by Gender & Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Smoker Count | Screening Ineligible Smokers Count | Percent Screening Ineligible Smokers |
|---|---|---|---|---|
| Female | Black | 1,582 | 1,468 | 92.79 |
| Female | Latinx | 255 | 244 | 95.69 |
| Female | White | 239 | 218 | 91.21 |
| Male | Black | 1,267 | 1,169 | 92.27 |
| Male | Latinx | 462 | 434 | 93.94 |
| Male | White | 332 | 300 | 90.36 |
# ineligible diagnosed smokers by gender and race
ineligible_cancerg_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarise(Total = n(),
diag_n = sum(malignanto == 1, na.rm = TRUE),
per_diag = (diag_n / Total * 100),
screenINelig_smoker = sum(screen_elig == 0 & smokingstatus >= 2, na.rm = TRUE),
diag_screenINelig = sum(screen_elig == 0 & smokingstatus >= 2 & malignanto == 1, na.rm = TRUE),
per_diagse = diag_screenINelig / screenINelig_smoker * 100)
colnames(ineligible_cancerg_count) <- c("Gender", "Race/Ethnicity", "Smoker Count", "Smokers Diagnosed with Lung Cancer Count", "Percent Smokers Diagnosed", "Screening Ineligible Smoker Count", "Screening Ineligible Smokers Diagnosed", "Percent Screening Ineligible Smokers Diagnosed")
ineligible_cancerg_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers Diagnosed with Lung Cancer by Gender & Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Smoker Count | Smokers Diagnosed with Lung Cancer Count | Percent Smokers Diagnosed | Screening Ineligible Smoker Count | Screening Ineligible Smokers Diagnosed | Percent Screening Ineligible Smokers Diagnosed |
|---|---|---|---|---|---|---|---|
| Female | Black | 1,582 | 206 | 13.02 | 1,468 | 192 | 13.08 |
| Female | Latinx | 255 | 24 | 9.41 | 244 | 21 | 8.61 |
| Female | White | 239 | 34 | 14.23 | 218 | 32 | 14.68 |
| Male | Black | 1,267 | 181 | 14.29 | 1,169 | 170 | 14.54 |
| Male | Latinx | 462 | 35 | 7.58 | 434 | 33 | 7.60 |
| Male | White | 332 | 45 | 13.55 | 300 | 44 | 14.67 |
elig_smoker_lowvio_r_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(raceethnic_cat) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_elig = sum(screen_elig == 1),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
lowexpose_vio = sum(homicidegtmean2 == "0", na.rm = TRUE),
lowexpose_vio_diag = sum(homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_ldiag = (lowexpose_vio_diag / lowexpose_vio * 100),
lowelig_vio = sum(screen_elig == 1 & homicidegtmean2 == "0", na.rm = TRUE),
elig_expose_lowvio_diag = sum(screen_elig == 1 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_lowelig_vio = elig_expose_lowvio_diag / lowelig_vio * 100)
colnames(elig_smoker_lowvio_r_count) <- c(
"Race/Ethnicity",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Eligible",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Smokers Screening Eligible with Low Exposure to Violence",
"Smokers Screening Eligible with Low Exposure to Violence Diagnosed",
"% Smokers Screening Eligible with Low Exposure to Violence
Diagnosed")
# table
elig_smoker_lowvio_r_count %>%
kable(
align = "lllll",
caption = "Screening Eligible Current or Former Smokers Diagnosed with Lung Cancer by Race with Low Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Eligible | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with Low Exposure to Violence | Smokers with Low Exposure to Violence Diagnosed | % Smokers with Low Exposure to Violence Diagnosed | Smokers Screening Eligible with Low Exposure to Violence | Smokers Screening Eligible with Low Exposure to Violence Diagnosed | % Smokers Screening Eligible with Low Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 2,850 | 387 | 13.58 | 212 | 25 | 11.79 | 1,283 | 148 | 11.54 | 101 | 8 | 7.92 |
| Latinx | 717 | 59 | 8.23 | 39 | 5 | 12.82 | 662 | 55 | 8.31 | 37 | 4 | 10.81 |
| White | 571 | 79 | 13.84 | 53 | 3 | 5.66 | 532 | 73 | 13.72 | 51 | 3 | 5.88 |
# ineligible smokers by race with high exposure to violence
inelig_smokervio_race_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(raceethnic_cat) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_inelig = sum(screen_elig == 0, na.rm = TRUE),
smoker_inelig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_diag2 = (smoker_inelig_diag / total_smoker_inelig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_ldiag = (expose_vio_diag / expose_vio * 100),
inelig_vio = sum(screen_elig == 0 & homicidegtmean2 == "1", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokervio_race_count) <- c("Race/Ethnicity",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Ineligible",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Smokers Screening Ineligible with High Exposure to Violence",
"Smokers Screening Ineligible with High Exposure to Violence Diagnosed",
"% Smokers Screening Ineligible with High Exposure to Violence
Diagnosed")
# table
inelig_smokervio_race_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers Diagnosed with Lung Cancer by Race with High Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Ineligible | Smokers Screening Ineligible Diagnosed | % Ineligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Smokers Screening Ineligible with High Exposure to Violence | Smokers Screening Ineligible with High Exposure to Violence Diagnosed | % Smokers Screening Ineligible with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 2,850 | 387 | 13.58 | 2,638 | 362 | 13.72 | 1,565 | 239 | 15.27 | 1,454 | 222 | 15.27 |
| Latinx | 717 | 59 | 8.23 | 678 | 54 | 7.96 | 54 | 4 | 7.41 | 52 | 3 | 5.77 |
| White | 571 | 79 | 13.84 | 518 | 76 | 14.67 | 36 | 6 | 16.67 | 35 | 6 | 17.14 |
elig_smoker_lowvio_g_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
lowexpose_vio = sum(homicidegtmean2 == "0", na.rm = TRUE),
lowexpose_vio_diag = sum(homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_ldiag = (lowexpose_vio_diag / lowexpose_vio * 100),
lowelig_vio = sum(screen_elig == 1 & homicidegtmean2 == "0", na.rm = TRUE),
elig_expose_lowvio_diag = sum(screen_elig == 1 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_lowelig_vio = elig_expose_lowvio_diag / lowelig_vio * 100)
colnames(elig_smoker_lowvio_g_count) <- c(
"Gender",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Eligible",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Smokers Screening Eligible with Low Exposure to Violence",
"Smokers Screening Eligible with Low Exposure to Violence Diagnosed",
"% Smokers Screening Eligible with Low Exposure to Violence
Diagnosed")
# table
elig_smoker_lowvio_g_count %>%
kable(
align = "lllll",
caption = "Screening Eligible Current or Former Smokers Diagnosed with Lung Cancer by Gender with Low Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Eligible | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with Low Exposure to Violence | Smokers with Low Exposure to Violence Diagnosed | % Smokers with Low Exposure to Violence Diagnosed | Smokers Screening Eligible with Low Exposure to Violence | Smokers Screening Eligible with Low Exposure to Violence Diagnosed | % Smokers Screening Eligible with Low Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Female | 2,076 | 264 | 12.72 | 146 | 19 | 13.01 | 1,154 | 126 | 10.92 | 84 | 8 | 9.52 |
| Male | 2,061 | 261 | 12.66 | 158 | 14 | 8.86 | 1,322 | 150 | 11.35 | 105 | 7 | 6.67 |
# ineligible smokers by gender with high exposure to violence
inelig_smokervio_gender_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_inelig = sum(screen_elig == 0, na.rm = TRUE),
smoker_inelig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_inelig_diag / total_smoker_inelig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_ldiag = (expose_vio_diag / expose_vio * 100),
inelig_vio = sum(screen_elig == 0 & homicidegtmean2 == "1", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokervio_gender_count) <- c("Gender",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Ineligible",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Smokers Screening Ineligible with High Exposure to Violence",
"Smokers Screening Ineligible with High Exposure to Violence Diagnosed",
"% Smokers Screening Ineligible with High Exposure to Violence
Diagnosed")
# table
inelig_smokervio_gender_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers Diagnosed with Lung Cancer by Gender with High Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Ineligible | Smokers Screening Ineligible Diagnosed | % Ineligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Smokers Screening Ineligible with High Exposure to Violence | Smokers Screening Ineligible with High Exposure to Violence Diagnosed | % Smokers Screening Ineligible with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Female | 2,076 | 264 | 12.72 | 1,930 | 245 | 12.69 | 920 | 138 | 15.0 | 858 | 127 | 14.80 |
| Male | 2,061 | 261 | 12.66 | 1,903 | 247 | 12.98 | 735 | 111 | 15.1 | 683 | 104 | 15.23 |
elig_smoker_lowvio_gr_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
lowexpose_vio = sum(homicidegtmean2 == "0", na.rm = TRUE),
lowexpose_vio_diag = sum(homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_ldiag = (lowexpose_vio_diag / lowexpose_vio * 100),
lowelig_vio = sum(screen_elig == 1 & homicidegtmean2 == "0", na.rm = TRUE),
elig_expose_lowvio_diag = sum(screen_elig == 1 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_lowelig_vio = elig_expose_lowvio_diag / lowelig_vio * 100)
colnames(elig_smoker_lowvio_gr_count) <- c(
"Gender",
"Race/Ethnicity",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Eligible",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Smokers Screening Eligible with Low Exposure to Violence",
"Smokers Screening Eligible with Low Exposure to Violence Diagnosed",
"% Smokers Screening Eligible with Low Exposure to Violence
Diagnosed")
# table
elig_smoker_lowvio_gr_count %>%
kable(
align = "lllll",
caption = "Screening Eligible Current or Former Smokers Diagnosed with Lung Cancer by Gender & Race with Low Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Eligible | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with Low Exposure to Violence | Smokers with Low Exposure to Violence Diagnosed | % Smokers with Low Exposure to Violence Diagnosed | Smokers Screening Eligible with Low Exposure to Violence | Smokers Screening Eligible with Low Exposure to Violence Diagnosed | % Smokers Screening Eligible with Low Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Female | Black | 1,582 | 206 | 13.02 | 114 | 14 | 12.28 | 693 | 72 | 10.39 | 53 | 4 | 7.55 |
| Female | Latinx | 255 | 24 | 9.41 | 11 | 3 | 27.27 | 235 | 21 | 8.94 | 10 | 2 | 20.00 |
| Female | White | 239 | 34 | 14.23 | 21 | 2 | 9.52 | 226 | 33 | 14.60 | 21 | 2 | 9.52 |
| Male | Black | 1,267 | 181 | 14.29 | 98 | 11 | 11.22 | 589 | 76 | 12.90 | 48 | 4 | 8.33 |
| Male | Latinx | 462 | 35 | 7.58 | 28 | 2 | 7.14 | 427 | 34 | 7.96 | 27 | 2 | 7.41 |
| Male | White | 332 | 45 | 13.55 | 32 | 1 | 3.12 | 306 | 40 | 13.07 | 30 | 1 | 3.33 |
elig_smokervio_gender_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_vdiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 1 & homicidegtmean2 == "1", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100)
colnames(elig_smokervio_gender_count) <- c("Gender",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Eligible",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Smokers Screening Eligible with High Exposure to Violence",
"Smokers Screening Eligible with High Exposure to Violence Diagnosed",
"% Smokers Screening Eligible with High Exposure to Violence
Diagnosed")
# table
elig_smokervio_gender_count %>%
kable(
align = "lllll",
caption = "Screening Eligible Current or Former Smokers Diagnosed with Lung Cancer by Gender with High Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Eligible | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Smokers Screening Eligible with High Exposure to Violence | Smokers Screening Eligible with High Exposure to Violence Diagnosed | % Smokers Screening Eligible with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Female | 2,076 | 264 | 12.72 | 146 | 19 | 13.01 | 920 | 138 | 15.0 | 62 | 11 | 17.74 |
| Male | 2,061 | 261 | 12.66 | 158 | 14 | 8.86 | 735 | 111 | 15.1 | 52 | 7 | 13.46 |
elig_smokervio_race_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(raceethnic_cat) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_ldiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 1 & homicidegtmean2 == "1", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100)
colnames(elig_smokervio_race_count) <- c("Race/Ethnicity",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Eligible",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Smokers Screening Eligible with High Exposure to Violence",
"Smokers Screening Eligible with High Exposure to Violence Diagnosed",
"% Smokers Screening Eligible with High Exposure to Violence
Diagnosed")
# table
elig_smokervio_race_count %>%
kable(
align = "lllll",
caption = "Screening Eligible Current or Former Smokers Diagnosed with Lung Cancer by Race with High Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Eligible | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Smokers Screening Eligible with High Exposure to Violence | Smokers Screening Eligible with High Exposure to Violence Diagnosed | % Smokers Screening Eligible with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 2,850 | 387 | 13.58 | 212 | 25 | 11.79 | 1,565 | 239 | 15.27 | 111 | 17 | 15.32 |
| Latinx | 717 | 59 | 8.23 | 39 | 5 | 12.82 | 54 | 4 | 7.41 | 2 | 1 | 50.00 |
| White | 571 | 79 | 13.84 | 53 | 3 | 5.66 | 36 | 6 | 16.67 | 1 | 0 | 0.00 |
elig_smokervio_genderr_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_hdiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 1 & homicidegtmean2 == "1", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100)
colnames(elig_smokervio_genderr_count) <- c("Gender",
"Race/Ethnicity",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Eligible",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Smokers Screening Eligible with High Exposure to Violence",
"Smokers Screening Eligible with High Exposure to Violence Diagnosed",
"% Smokers Screening Eligible with High Exposure to Violence
Diagnosed")
# table
elig_smokervio_genderr_count %>%
kable(
align = "lllll",
caption = "Screening Eligible Current or Former Smokers Diagnosed with Lung Cancer by Gender & Race with High Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Eligible | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Smokers Screening Eligible with High Exposure to Violence | Smokers Screening Eligible with High Exposure to Violence Diagnosed | % Smokers Screening Eligible with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Female | Black | 1,582 | 206 | 13.02 | 114 | 14 | 12.28 | 888 | 134 | 15.09 | 61 | 10 | 16.39 |
| Female | Latinx | 255 | 24 | 9.41 | 11 | 3 | 27.27 | 19 | 3 | 15.79 | 1 | 1 | 100.00 |
| Female | White | 239 | 34 | 14.23 | 21 | 2 | 9.52 | 13 | 1 | 7.69 | 0 | 0 | NaN |
| Male | Black | 1,267 | 181 | 14.29 | 98 | 11 | 11.22 | 677 | 105 | 15.51 | 50 | 7 | 14.00 |
| Male | Latinx | 462 | 35 | 7.58 | 28 | 2 | 7.14 | 35 | 1 | 2.86 | 1 | 0 | 0.00 |
| Male | White | 332 | 45 | 13.55 | 32 | 1 | 3.12 | 23 | 5 | 21.74 | 1 | 0 | 0.00 |
inelig_smokervio_genderr_count =
lung %>%
filter(smokingstatus >= 2) %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarize(
Total_smoker = n(),
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
total_smoker_inelig = sum(screen_elig == 0, na.rm = TRUE),
smoker_inelig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_inelig_diag = (smoker_inelig_diag / total_smoker_inelig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_hdiag = (expose_vio_diag / expose_vio * 100),
inelig_vio = sum(screen_elig == 0 & homicidegtmean2 == "1", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokervio_genderr_count) <- c("Gender",
"Race/Ethnicity",
"Current or Former Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed",
"Smokers Screening Ineligible",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Smokers Screening Ineligible with High Exposure to Violence",
"Smokers Screening Ineligible with High Exposure to Violence Diagnosed",
"% Smokers Screening Ineligible with High Exposure to Violence
Diagnosed")
# table
inelig_smokervio_genderr_count %>%
kable(
align = "lllll",
caption = "Screening Ineligible Current or Former Smokers Diagnosed with Lung Cancer by Gender & Race with High Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Current or Former Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed | Smokers Screening Ineligible | Smokers Screening Ineligible Diagnosed | % Ineligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Smokers Screening Ineligible with High Exposure to Violence | Smokers Screening Ineligible with High Exposure to Violence Diagnosed | % Smokers Screening Ineligible with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Female | Black | 1,582 | 206 | 13.02 | 1,468 | 192 | 13.08 | 888 | 134 | 15.09 | 827 | 124 | 14.99 |
| Female | Latinx | 255 | 24 | 9.41 | 244 | 21 | 8.61 | 19 | 3 | 15.79 | 18 | 2 | 11.11 |
| Female | White | 239 | 34 | 14.23 | 218 | 32 | 14.68 | 13 | 1 | 7.69 | 13 | 1 | 7.69 |
| Male | Black | 1,267 | 181 | 14.29 | 1,169 | 170 | 14.54 | 677 | 105 | 15.51 | 627 | 98 | 15.63 |
| Male | Latinx | 462 | 35 | 7.58 | 434 | 33 | 7.60 | 35 | 1 | 2.86 | 34 | 1 | 2.94 |
| Male | White | 332 | 45 | 13.55 | 300 | 44 | 14.67 | 23 | 5 | 21.74 | 22 | 5 | 22.73 |
By race/ethnicity and by homicide
nonsmoker_diag_r =
lung %>%
filter(smokingstatus == "1.00", na.rm = TRUE) %>%
group_by(raceethnic_cat) %>%
summarize(
Total_nonsmoker = n(),
Total_nonsmoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_nondiag = Total_nonsmoker_diag / Total_nonsmoker * 100)
colnames(nonsmoker_diag_r) <- c("Race/Ethnicity",
"Nonsmoker Count",
"Nonsmokers Diagnosed with Lung Cancer",
"Percent Nonsmokers Diagnosed")
# table
nonsmoker_diag_r %>%
kable(
align = "lllll",
caption = "Nonsmokers Diagnosed with Lung Cancer by Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Nonsmoker Count | Nonsmokers Diagnosed with Lung Cancer | Percent Nonsmokers Diagnosed |
|---|---|---|---|
| Black | 1,268 | 53 | 4.18 |
| Latinx | 692 | 27 | 3.90 |
| White | 257 | 10 | 3.89 |
nonsmoker_diag_rvio =
lung %>%
filter(smokingstatus == "1.00", na.rm = TRUE) %>%
group_by(raceethnic_cat) %>%
summarize(
Total_nonsmoker = n(),
Total_nonsmoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_non_diag = (Total_nonsmoker_diag / Total_nonsmoker * 100),
expose_lvio = sum(homicidegtmean2 == "0", na.rm = TRUE),
expose_lvio_diag = sum(homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_lvio = (expose_lvio_diag / expose_lvio * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = expose_vio_diag / expose_vio * 100)
colnames(nonsmoker_diag_rvio) <- c("Race/Ethnicity",
"Nonsmoker Count",
"Nonsmokers Diagnosed with Lung Cancer",
"% Nonsmokers Diagnosed",
"Nonsmokers with Low Exposure to Violence",
"Nonsmokers with Low Exposure to Violence Diagnosed",
"% Nonsmokers with Low Exposure to Violence Diagnosed",
"Nonsmokers with High Exposure to Violence",
"Nonsmokers with High Exposure to Violence Diagnosed",
"% Nonsmokers with High Exposure to Violence Diagnosed")
# table
nonsmoker_diag_rvio %>%
kable(
align = "lllll",
caption = "Nonsmokers Diagnosed with Lung Cancer by Race Considering Exposure to Violence",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Nonsmoker Count | Nonsmokers Diagnosed with Lung Cancer | % Nonsmokers Diagnosed | Nonsmokers with Low Exposure to Violence | Nonsmokers with Low Exposure to Violence Diagnosed | % Nonsmokers with Low Exposure to Violence Diagnosed | Nonsmokers with High Exposure to Violence | Nonsmokers with High Exposure to Violence Diagnosed | % Nonsmokers with High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|
| Black | 1,268 | 53 | 4.18 | 578 | 22 | 3.81 | 689 | 31 | 4.50 |
| Latinx | 692 | 27 | 3.90 | 652 | 25 | 3.83 | 40 | 2 | 5.00 |
| White | 257 | 10 | 3.89 | 243 | 8 | 3.29 | 12 | 1 | 8.33 |
Looking at smoking never (0) versus smoking ever (1)
# create a new variable
lung$smoker_status_binary = ifelse(lung$smokingstatus >= 2, 1, 0)
# check is correct
lung %>%
group_by(smoker_status_binary) %>%
select(smokingstatus, smoker_status_binary) ## # A tibble: 7,198 × 2
## # Groups: smoker_status_binary [2]
## smokingstatus smoker_status_binary
## <chr> <dbl>
## 1 1.00 0
## 2 1.00 0
## 3 3.00 1
## 4 2.00 1
## 5 1.00 0
## 6 3.00 1
## 7 3.00 1
## 8 1.00 0
## 9 1.00 0
## 10 2.00 1
## # ℹ 7,188 more rows# looks goodsmokerstat_diag_r =
lung %>%
filter(malignanto == 1, na.rm = TRUE) %>%
group_by(raceethnic_cat) %>%
summarise(
Total = n(),
nonsmoker_count = sum(smoker_status_binary == 0, na.rm = TRUE),
nonsmoker_percent = mean(smoker_status_binary == 0) * 100,
smoker_count = sum(smoker_status_binary == 1, na.rm = TRUE),
smoker_percent = mean(smoker_status_binary == 1) * 100
)
colnames(smokerstat_diag_r) <- c("Race/Ethnicity",
"Patients Diagnosed with Lung Cancer",
"Never Smoked Diagnosed Count",
"% Never Smoked Diagnosed with Lung Cancer",
"Ever Smoked Diagnosed Count",
"% Ever Smoked Diagnosed with Lung Cancer")
# table
smokerstat_diag_r %>%
kable(
align = "lllll",
caption = "Smoking Status and Lung Cancer Diagnosis by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Patients Diagnosed with Lung Cancer | Never Smoked Diagnosed Count | % Never Smoked Diagnosed with Lung Cancer | Ever Smoked Diagnosed Count | % Ever Smoked Diagnosed with Lung Cancer |
|---|---|---|---|---|---|
| Black | 509 | 122 | 23.97 | 387 | 76.03 |
| Latinx | 99 | 40 | 40.40 | 59 | 59.60 |
| White | 99 | 20 | 20.20 | 79 | 79.80 |
smokerstat_diag_g =
lung %>%
filter(malignanto == 1, na.rm = TRUE) %>%
group_by(gender) %>%
summarise(
Total = n(),
nonsmoker_count = sum(smoker_status_binary == 0, na.rm = TRUE),
nonsmoker_percent = mean(smoker_status_binary == 0) * 100,
smoker_count = sum(smoker_status_binary == 1, na.rm = TRUE),
smoker_percent = mean(smoker_status_binary == 1) * 100
)
colnames(smokerstat_diag_g) <- c("Gender",
"Patients Diagnosed with Lung Cancer",
"Never Smoked Diagnosed Count",
"% Never Smoked Diagnosed with Lung Cancer",
"Ever Smoked Diagnosed Count",
"% Ever Smoked Diagnosed with Lung Cancer")
# table
smokerstat_diag_g %>%
kable(
align = "lllll",
caption = "Smoking Status and Lung Cancer Diagnosis by Gender",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Patients Diagnosed with Lung Cancer | Never Smoked Diagnosed Count | % Never Smoked Diagnosed with Lung Cancer | Ever Smoked Diagnosed Count | % Ever Smoked Diagnosed with Lung Cancer |
|---|---|---|---|---|---|
| Female | 380 | 116 | 30.53 | 264 | 69.47 |
| Male | 327 | 66 | 20.18 | 261 | 79.82 |
smokerstat_diag_gr =
lung %>%
filter(malignanto == 1, na.rm = TRUE) %>%
group_by(gender, raceethnic_cat) %>%
filter(gender %in% c("Female", "Male")) %>%
summarise(
Total = n(),
nonsmoker_count = sum(smoker_status_binary == 0, na.rm = TRUE),
nonsmoker_percent = mean(smoker_status_binary == 0) * 100,
smoker_count = sum(smoker_status_binary == 1, na.rm = TRUE),
smoker_percent = mean(smoker_status_binary == 1) * 100
)
colnames(smokerstat_diag_gr) <- c("Gender",
"Race/Ethnicity",
"Patients Diagnosed with Lung Cancer",
"Never Smoked Diagnosed Count",
"% Never Smoked Diagnosed with Lung Cancer",
"Ever Smoked Diagnosed Count",
"% Ever Smoked Diagnosed with Lung Cancer")
# table
smokerstat_diag_gr %>%
kable(
align = "lllll",
caption = "Smoking Status and Lung Cancer Diagnosis by Gender & Race",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Race/Ethnicity | Patients Diagnosed with Lung Cancer | Never Smoked Diagnosed Count | % Never Smoked Diagnosed with Lung Cancer | Ever Smoked Diagnosed Count | % Ever Smoked Diagnosed with Lung Cancer |
|---|---|---|---|---|---|---|
| Female | Black | 283 | 77 | 27.21 | 206 | 72.79 |
| Female | Latinx | 51 | 27 | 52.94 | 24 | 47.06 |
| Female | White | 46 | 12 | 26.09 | 34 | 73.91 |
| Male | Black | 226 | 45 | 19.91 | 181 | 80.09 |
| Male | Latinx | 48 | 13 | 27.08 | 35 | 72.92 |
| Male | White | 53 | 8 | 15.09 | 45 | 84.91 |
# Convert column to numeric and leave NAs
lung$packyear2 <- as.numeric(lung$packyear)
lung$packyear2[is.na(lung$packyear2)] <- NA# create new variables
lung$packyear_range <- cut(
lung$packyear2,
breaks = c(-Inf, 9.9999, 19.9999, Inf),
labels = c("0-10", "10-20", "20+"),
include.lowest = TRUE
)
# check is correct
lung %>%
group_by(smokingstatus) %>%
select(smokingstatus, packyear2, packyear_range) ## # A tibble: 7,198 × 3
## # Groups: smokingstatus [4]
## smokingstatus packyear2 packyear_range
## <chr> <dbl> <fct>
## 1 1.00 NA <NA>
## 2 1.00 NA <NA>
## 3 3.00 9.2 0-10
## 4 2.00 21 20+
## 5 1.00 NA <NA>
## 6 3.00 3.3 0-10
## 7 3.00 13.3 10-20
## 8 1.00 NA <NA>
## 9 1.00 NA <NA>
## 10 2.00 NA <NA>
## # ℹ 7,188 more rows# looks good# create new variables
lung$packyear_range5 <- cut(
lung$packyear2,
breaks = c(-Inf, 4.9999, 9.9999, 14.9999, 19.9999, Inf),
labels = c("0-5", "5-10", "10-15", "15-20", "20+"),
include.lowest = TRUE
)
# check is correct
lung %>%
group_by(smokingstatus) %>%
select(smokingstatus, packyear2, packyear_range5) ## # A tibble: 7,198 × 3
## # Groups: smokingstatus [4]
## smokingstatus packyear2 packyear_range5
## <chr> <dbl> <fct>
## 1 1.00 NA <NA>
## 2 1.00 NA <NA>
## 3 3.00 9.2 5-10
## 4 2.00 21 20+
## 5 1.00 NA <NA>
## 6 3.00 3.3 0-5
## 7 3.00 13.3 10-15
## 8 1.00 NA <NA>
## 9 1.00 NA <NA>
## 10 2.00 NA <NA>
## # ℹ 7,188 more rows# looks goodpy_screenelig_gender_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(gender %in% c("Female", "Male")) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(gender, packyear_range) %>%
summarize("Patient Count" = n(),
"Screening Eligible Count" = sum(screen_elig == 1, na.rm = TRUE),
"Percent Screening Eligible" = mean(screen_elig == 1, na.rm = TRUE) * 100)
colnames(py_screenelig_gender_table) <- c("Gender", "Pack Year Range", "Patient Count", "Screening Eligible Count", "Percent Screening Eligible")
# table
py_screenelig_gender_table %>%
kable(align = "lllll",
caption = "Percentage of Smokers Eligible for the Lung Cancer Screening by Gender by Pack Year Avg",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Pack Year Range | Patient Count | Screening Eligible Count | Percent Screening Eligible |
|---|---|---|---|---|
| Female | 0-10 | 250 | 0 | 0.00 |
| Female | 10-20 | 123 | 0 | 0.00 |
| Female | 20+ | 167 | 146 | 87.43 |
| Male | 0-10 | 221 | 0 | 0.00 |
| Male | 10-20 | 127 | 0 | 0.00 |
| Male | 20+ | 181 | 158 | 87.29 |
py_screeninelig_gender_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(gender %in% c("Female", "Male")) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(gender, packyear_range) %>%
summarize("Patient Count" = n(),
"Screening Eligible Count" = sum(screen_elig == 0, na.rm = TRUE),
"Percent Screening Eligible" = mean(screen_elig == 0, na.rm = TRUE) * 100)
colnames(py_screeninelig_gender_table) <- c("Gender", "Pack Year Range", "Patient Count", "Screening Ineligible Count", "Percent Screening Ineligible")
# table
py_screeninelig_gender_table %>%
kable(align = "lllll",
caption = "Percentage of Smokers Ineligible for the Lung Cancer Screening by Gender by Pack Year Avg",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Pack Year Range | Patient Count | Screening Ineligible Count | Percent Screening Ineligible |
|---|---|---|---|---|
| Female | 0-10 | 250 | 250 | 100.00 |
| Female | 10-20 | 123 | 123 | 100.00 |
| Female | 20+ | 167 | 21 | 12.57 |
| Male | 0-10 | 221 | 221 | 100.00 |
| Male | 10-20 | 127 | 127 | 100.00 |
| Male | 20+ | 181 | 23 | 12.71 |
py_screeneligdiag_gender_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(gender %in% c("Female", "Male")) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(gender, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 1, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100))
colnames(py_screeneligdiag_gender_table) <- c("Gender", "Pack Year Range", "Patient Count", "Screening Eligible", "% Screening Eligible", "Diagnosed with Lung Cancer", "% Diagnosed with Lung Cancer", "Screening Eligible Diagnosed", "% Screening Eligible Diagnosed")
# table
py_screeneligdiag_gender_table %>%
kable(align = "lllll",
caption = "Patient Counts, Screening Eligibility and Lung Cancer Diagnosis by Gender and Pack Year Avg Ranges",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Pack Year Range | Patient Count | Screening Eligible | % Screening Eligible | Diagnosed with Lung Cancer | % Diagnosed with Lung Cancer | Screening Eligible Diagnosed | % Screening Eligible Diagnosed |
|---|---|---|---|---|---|---|---|---|
| Female | 0-10 | 250 | 0 | 0.00 | 27 | 10.80 | 0 | NaN |
| Female | 10-20 | 123 | 0 | 0.00 | 12 | 9.76 | 0 | NaN |
| Female | 20+ | 167 | 146 | 87.43 | 29 | 17.37 | 19 | 13.01 |
| Male | 0-10 | 221 | 0 | 0.00 | 14 | 6.33 | 0 | NaN |
| Male | 10-20 | 127 | 0 | 0.00 | 23 | 18.11 | 0 | NaN |
| Male | 20+ | 181 | 158 | 87.29 | 27 | 14.92 | 14 | 8.86 |
py_screenieligdiag_gender_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(gender %in% c("Female", "Male")) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(gender, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 0, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 0, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100))
colnames(py_screenieligdiag_gender_table) <- c("Gender", "Pack Year Range", "Patient Count", "Screening Ineligible", "% Screening Ineligible", "Diagnosed with Lung Cancer", "% Diagnosed with Lung Cancer", "Screening Ineligible Diagnosed", "% Screening Ineligible Diagnosed")
# table
py_screenieligdiag_gender_table %>%
kable(align = "lllll",
caption = "Patient Counts, Screening Ineligibility and Lung Cancer Diagnosis by Gender and Pack Year Avg Ranges",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Gender | Pack Year Range | Patient Count | Screening Ineligible | % Screening Ineligible | Diagnosed with Lung Cancer | % Diagnosed with Lung Cancer | Screening Ineligible Diagnosed | % Screening Ineligible Diagnosed |
|---|---|---|---|---|---|---|---|---|
| Female | 0-10 | 250 | 250 | 100.00 | 27 | 10.80 | 27 | 10.80 |
| Female | 10-20 | 123 | 123 | 100.00 | 12 | 9.76 | 12 | 9.76 |
| Female | 20+ | 167 | 21 | 12.57 | 29 | 17.37 | 10 | 47.62 |
| Male | 0-10 | 221 | 221 | 100.00 | 14 | 6.33 | 14 | 6.33 |
| Male | 10-20 | 127 | 127 | 100.00 | 23 | 18.11 | 23 | 18.11 |
| Male | 20+ | 181 | 23 | 12.71 | 27 | 14.92 | 13 | 56.52 |
py_screenelig_r_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize("Patient Count" = n(),
"Screening Eligible Patient Count" = sum(screen_elig == 1, na.rm = TRUE),
"Percent Screening Eligible" = mean(screen_elig == 1, na.rm = TRUE) * 100) %>%
mutate("Percent Patients in Pack Year Range" = prop.table(`Patient Count`) * 100)
colnames(py_screenelig_r_table) <- c("Race/Ethnicity", "Pack Year Range", "Patient Count", "Screening Eligible Patient Count", "Percent Screening Eligible", "Percent Patients in Pack Year Range by Race/Ethnicity")
col_order <- c("Race/Ethnicity", "Pack Year Range", "Patient Count", "Percent Patients in Pack Year Range by Race/Ethnicity", "Screening Eligible Patient Count", "Percent Screening Eligible")
py_screenelig_r_table <- py_screenelig_r_table[, col_order]
# table
py_screenelig_r_table %>%
kable(align = "llllll",
caption = "Percentage of Smokers Eligible for the Lung Cancer Screening by Race/Ethnicity and Pack Year Avg Range",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Percent Patients in Pack Year Range by Race/Ethnicity | Screening Eligible Patient Count | Percent Screening Eligible |
|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 0 | 0.00 |
| Black | 10-20 | 170 | 22.28 | 0 | 0.00 |
| Black | 20+ | 238 | 31.19 | 212 | 89.08 |
| Latinx | 0-10 | 78 | 49.37 | 0 | 0.00 |
| Latinx | 10-20 | 36 | 22.78 | 0 | 0.00 |
| Latinx | 20+ | 44 | 27.85 | 39 | 88.64 |
| White | 0-10 | 38 | 25.68 | 0 | 0.00 |
| White | 10-20 | 44 | 29.73 | 0 | 0.00 |
| White | 20+ | 66 | 44.59 | 53 | 80.30 |
py_screenielig_r_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize("Patient Count" = n(),
"Screening Ineligible Patient Count" = sum(screen_elig == 0, na.rm = TRUE),
"Percent Screening Ineligible" = mean(screen_elig == 0, na.rm = TRUE) * 100) %>%
mutate("Percent Patients in Pack Year Range" = prop.table(`Patient Count`) * 100)
colnames(py_screenielig_r_table) <- c("Race/Ethnicity", "Pack Year Range", "Patient Count", "Screening Ineligible Patient Count", "Percent Screening Ineligible", "Percent Patients in Pack Year Range by Race/Ethnicity")
col_order2 <- c("Race/Ethnicity", "Pack Year Range", "Patient Count", "Percent Patients in Pack Year Range by Race/Ethnicity", "Screening Ineligible Patient Count", "Percent Screening Ineligible")
py_screenielig_r_table <- py_screenielig_r_table[, col_order2]
# table
py_screenielig_r_table %>%
kable(align = "llllll",
caption = "Percentage of Smokers Ineligible for the Lung Cancer Screening by Race/Ethnicity and Pack Year Avg Range",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Percent Patients in Pack Year Range by Race/Ethnicity | Screening Ineligible Patient Count | Percent Screening Ineligible |
|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 355 | 100.00 |
| Black | 10-20 | 170 | 22.28 | 170 | 100.00 |
| Black | 20+ | 238 | 31.19 | 26 | 10.92 |
| Latinx | 0-10 | 78 | 49.37 | 78 | 100.00 |
| Latinx | 10-20 | 36 | 22.78 | 36 | 100.00 |
| Latinx | 20+ | 44 | 27.85 | 5 | 11.36 |
| White | 0-10 | 38 | 25.68 | 38 | 100.00 |
| White | 10-20 | 44 | 29.73 | 44 | 100.00 |
| White | 20+ | 66 | 44.59 | 13 | 19.70 |
py_screeneligdiag_race_table <-
lung %>%
filter(smokingstatus >= 2, na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 1, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100)) %>%
mutate("% Patients in Pack Year Range by Race/Ethnicity" = Total_smoker / sum(Total_smoker) * 100)
# Reorder columns
colnames(py_screeneligdiag_race_table) <- c("Race/Ethnicity", "Pack Year Range", "Patient Count", "Screening Eligible Patients", "% Screening Eligible", "Patients Diagnosed with Lung Cancer", "% Diagnosed with Lung Cancer", "Screening Eligible Diagnosed", "% Screening Eligible Diagnosed", "% Patients in Pack Year Range by Race/Ethnicity")
col_order3 <- c("Race/Ethnicity", "Pack Year Range", "Patient Count", "% Patients in Pack Year Range by Race/Ethnicity", "Screening Eligible Patients", "% Screening Eligible", "Patients Diagnosed with Lung Cancer", "% Diagnosed with Lung Cancer", "Screening Eligible Diagnosed", "% Screening Eligible Diagnosed")
py_screeneligdiag_race_table <- py_screeneligdiag_race_table[, col_order3]
# Replace NaN values with 0 in "% Screening Eligible Diagnosed" column
py_screeneligdiag_race_table$`% Screening Eligible Diagnosed` <- replace(py_screeneligdiag_race_table$`% Screening Eligible Diagnosed`, !is.finite(py_screeneligdiag_race_table$`% Screening Eligible Diagnosed`), 0)
py_screeneligdiag_race_table %>%
kable(align = "llllllll",
caption = "Patient Counts, Screening Eligibility and Lung Cancer Diagnosis by Race/Ethnicity and Pack Year Avg Ranges",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | % Patients in Pack Year Range by Race/Ethnicity | Screening Eligible Patients | % Screening Eligible | Patients Diagnosed with Lung Cancer | % Diagnosed with Lung Cancer | Screening Eligible Diagnosed | % Screening Eligible Diagnosed |
|---|---|---|---|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 0 | 0.00 | 37 | 10.42 | 0 | 0.00 |
| Black | 10-20 | 170 | 22.28 | 0 | 0.00 | 23 | 13.53 | 0 | 0.00 |
| Black | 20+ | 238 | 31.19 | 212 | 89.08 | 42 | 17.65 | 25 | 11.79 |
| Latinx | 0-10 | 78 | 49.37 | 0 | 0.00 | 3 | 3.85 | 0 | 0.00 |
| Latinx | 10-20 | 36 | 22.78 | 0 | 0.00 | 5 | 13.89 | 0 | 0.00 |
| Latinx | 20+ | 44 | 27.85 | 39 | 88.64 | 7 | 15.91 | 5 | 12.82 |
| White | 0-10 | 38 | 25.68 | 0 | 0.00 | 1 | 2.63 | 0 | 0.00 |
| White | 10-20 | 44 | 29.73 | 0 | 0.00 | 7 | 15.91 | 0 | 0.00 |
| White | 20+ | 66 | 44.59 | 53 | 80.30 | 7 | 10.61 | 3 | 5.66 |
py_screenieligdiag_race_table <-
lung %>%
filter(smokingstatus >= 2, na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_inelig = sum(screen_elig == 0, na.rm = TRUE),
per_screen_inelig = mean(screen_elig == 0, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 0, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_inelig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_inelig_diag / total_smoker_inelig * 100)) %>%
mutate("% Smokers in Pack Year Range by Race/Ethnicity" = Total_smoker / sum(Total_smoker) * 100)
# Reorder columns
colnames(py_screenieligdiag_race_table) <- c("Race/Ethnicity", "Pack Year Range", "Former or Current Smoker Count", "Screening Ineligible Smoker Count", "% Screening Ineligible Smokers", "Smokers Diagnosed with Lung Cancer", "% Smokers Diagnosed with Lung Cancer", "Screening Ineligible Smokers Diagnosed", "% Screening Ineligible Smokers Diagnosed", "% Smokers in Pack Year Range by Race/Ethnicity")
col_order4 <- c("Race/Ethnicity", "Pack Year Range", "Former or Current Smoker Count", "% Smokers in Pack Year Range by Race/Ethnicity", "Screening Ineligible Smoker Count", "% Screening Ineligible Smokers", "Smokers Diagnosed with Lung Cancer", "% Smokers Diagnosed with Lung Cancer", "Screening Ineligible Smokers Diagnosed", "% Screening Ineligible Smokers Diagnosed")
py_screenieligdiag_race_table <- py_screenieligdiag_race_table[, col_order4]
py_screenieligdiag_race_table %>%
kable(align = "llllllll",
caption = "Patient Counts, Screening Ineligibility and Lung Cancer Diagnosis by Race/Ethnicity and Pack Year Avg Ranges",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Former or Current Smoker Count | % Smokers in Pack Year Range by Race/Ethnicity | Screening Ineligible Smoker Count | % Screening Ineligible Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed with Lung Cancer | Screening Ineligible Smokers Diagnosed | % Screening Ineligible Smokers Diagnosed |
|---|---|---|---|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 355 | 100.00 | 318 | 89.58 | 37 | 10.42 |
| Black | 10-20 | 170 | 22.28 | 170 | 100.00 | 147 | 86.47 | 23 | 13.53 |
| Black | 20+ | 238 | 31.19 | 26 | 10.92 | 196 | 82.35 | 17 | 65.38 |
| Latinx | 0-10 | 78 | 49.37 | 78 | 100.00 | 75 | 96.15 | 3 | 3.85 |
| Latinx | 10-20 | 36 | 22.78 | 36 | 100.00 | 31 | 86.11 | 5 | 13.89 |
| Latinx | 20+ | 44 | 27.85 | 5 | 11.36 | 37 | 84.09 | 2 | 40.00 |
| White | 0-10 | 38 | 25.68 | 38 | 100.00 | 37 | 97.37 | 1 | 2.63 |
| White | 10-20 | 44 | 29.73 | 44 | 100.00 | 37 | 84.09 | 7 | 15.91 |
| White | 20+ | 66 | 44.59 | 13 | 19.70 | 59 | 89.39 | 4 | 30.77 |
py_screenelig_grhivio_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 1, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_hdiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 1 & homicidegtmean2 == "1", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100) %>%
mutate("% Smokers in Pack Year Range by Race/Ethnicity" = Total_smoker / sum(Total_smoker) * 100)
colnames(py_screenelig_grhivio_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"Screening Eligible Smokers",
"% Screening Eligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Screening Eligible Smokers High Exposure to Violence",
"Screening Eligible Smokers High Exposure to Violence Diagnosed",
"% Screening Eligible Smokers High Exposure to Violence Diagnosed",
"% Smokers in Pack Year Range by Race/Ethnicity")
col_order5 <- c("Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"% Smokers in Pack Year Range by Race/Ethnicity",
"Screening Eligible Smokers",
"% Screening Eligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Eligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Screening Eligible Smokers High Exposure to Violence",
"Screening Eligible Smokers High Exposure to Violence Diagnosed",
"% Screening Eligible Smokers High Exposure to Violence Diagnosed")
py_screenelig_grhivio_table <- py_screenelig_grhivio_table[, col_order5]
# Replace NaN values with 0 in "% Eligible Smokers Diagnosed" column
py_screenelig_grhivio_table$`% Eligible Smokers Diagnosed` <- replace(py_screenelig_grhivio_table$`% Eligible Smokers Diagnosed`, !is.finite(py_screenelig_grhivio_table$`% Eligible Smokers Diagnosed`), 0)
# Replace NaN values with 0 in "% Screening Eligible Smokers High Exposure to Violence Diagnosed" column
py_screenelig_grhivio_table$`% Screening Eligible Smokers High Exposure to Violence Diagnosed` <- replace(py_screenelig_grhivio_table$`% Screening Eligible Smokers High Exposure to Violence Diagnosed`, !is.finite(py_screenelig_grhivio_table$`% Screening Eligible Smokers High Exposure to Violence Diagnosed`), 0)
# table
py_screenelig_grhivio_table %>%
kable(
align = "lllll",
caption = "Exploring Screening Eligible Smokers Diagnosed with Lung Cancer by Race/Ethnicity with High Exposure to Violence (by avg pack year range)",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Smoker Count | % Smokers in Pack Year Range by Race/Ethnicity | Screening Eligible Smokers | % Screening Eligible Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed with Lung Cancer | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Screening Eligible Smokers High Exposure to Violence | Screening Eligible Smokers High Exposure to Violence Diagnosed | % Screening Eligible Smokers High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 0 | 0.00 | 37 | 10.42 | 0 | 0.00 | 194 | 20 | 10.31 | 0 | 0 | 0.00 |
| Black | 10-20 | 170 | 22.28 | 0 | 0.00 | 23 | 13.53 | 0 | 0.00 | 95 | 13 | 13.68 | 0 | 0 | 0.00 |
| Black | 20+ | 238 | 31.19 | 212 | 89.08 | 42 | 17.65 | 25 | 11.79 | 130 | 27 | 20.77 | 111 | 17 | 15.32 |
| Latinx | 0-10 | 78 | 49.37 | 0 | 0.00 | 3 | 3.85 | 0 | 0.00 | 9 | 1 | 11.11 | 0 | 0 | 0.00 |
| Latinx | 10-20 | 36 | 22.78 | 0 | 0.00 | 5 | 13.89 | 0 | 0.00 | 2 | 1 | 50.00 | 0 | 0 | 0.00 |
| Latinx | 20+ | 44 | 27.85 | 39 | 88.64 | 7 | 15.91 | 5 | 12.82 | 3 | 1 | 33.33 | 2 | 1 | 50.00 |
| White | 0-10 | 38 | 25.68 | 0 | 0.00 | 1 | 2.63 | 0 | 0.00 | 3 | 0 | 0.00 | 0 | 0 | 0.00 |
| White | 10-20 | 44 | 29.73 | 0 | 0.00 | 7 | 15.91 | 0 | 0.00 | 3 | 1 | 33.33 | 0 | 0 | 0.00 |
| White | 20+ | 66 | 44.59 | 53 | 80.30 | 7 | 10.61 | 3 | 5.66 | 3 | 0 | 0.00 | 1 | 0 | 0.00 |
py_screenelig_grlowvio_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 1, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 1, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "0", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_hdiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 1 & homicidegtmean2 == "0", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100) %>%
mutate("% Smokers in Pack Year Range by Race/Ethnicity" = Total_smoker / sum(Total_smoker) * 100)
colnames(py_screenelig_grlowvio_table) <- c("Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"Screening Eligible Smokers",
"% Screening Eligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Ineligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Screening Eligible Smokers Low Exposure to Violence",
"Screening Eligible Smokers Low Exposure to Violence Diagnosed",
"% Screening Eligible Smokers Low Exposure to Violence Diagnosed",
"% Smokers in Pack Year Range by Race/Ethnicity")
col_order6 <- c("Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"% Smokers in Pack Year Range by Race/Ethnicity",
"Screening Eligible Smokers",
"% Screening Eligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Ineligible Diagnosed",
"% Eligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Screening Eligible Smokers Low Exposure to Violence",
"Screening Eligible Smokers Low Exposure to Violence Diagnosed",
"% Screening Eligible Smokers Low Exposure to Violence Diagnosed")
py_screenelig_grlowvio_table <- py_screenelig_grlowvio_table[, col_order6]
# Replace NaN values with 0 in "% Eligible Smokers Diagnosed" column
py_screenelig_grlowvio_table$`% Eligible Smokers Diagnosed` <- replace(py_screenelig_grlowvio_table$`% Eligible Smokers Diagnosed`, !is.finite(py_screenelig_grlowvio_table$`% Eligible Smokers Diagnosed`), 0)
# Replace NaN values with 0 in "% Screening Eligible Smokers Low Exposure to Violence Diagnosed" column
py_screenelig_grlowvio_table$`% Screening Eligible Smokers Low Exposure to Violence Diagnosed` <- replace(py_screenelig_grlowvio_table$`% Screening Eligible Smokers Low Exposure to Violence Diagnosed`, !is.finite(py_screenelig_grlowvio_table$`% Screening Eligible Smokers Low Exposure to Violence Diagnosed`), 0)
# table
py_screenelig_grlowvio_table %>%
kable(
align = "lllll",
caption = "Exploring Screening Eligible Smokers Diagnosed with Lung Cancer by Race/Ethnicity with Low Exposure to Violence (by avg pack year range)",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Smoker Count | % Smokers in Pack Year Range by Race/Ethnicity | Screening Eligible Smokers | % Screening Eligible Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed with Lung Cancer | Smokers Screening Ineligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with Low Exposure to Violence | Smokers with Low Exposure to Violence Diagnosed | % Smokers with Low Exposure to Violence Diagnosed | Screening Eligible Smokers Low Exposure to Violence | Screening Eligible Smokers Low Exposure to Violence Diagnosed | % Screening Eligible Smokers Low Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 0 | 0.00 | 37 | 10.42 | 0 | 0.00 | 161 | 17 | 10.56 | 0 | 0 | 0.00 |
| Black | 10-20 | 170 | 22.28 | 0 | 0.00 | 23 | 13.53 | 0 | 0.00 | 75 | 10 | 13.33 | 0 | 0 | 0.00 |
| Black | 20+ | 238 | 31.19 | 212 | 89.08 | 42 | 17.65 | 25 | 11.79 | 108 | 15 | 13.89 | 101 | 8 | 7.92 |
| Latinx | 0-10 | 78 | 49.37 | 0 | 0.00 | 3 | 3.85 | 0 | 0.00 | 69 | 2 | 2.90 | 0 | 0 | 0.00 |
| Latinx | 10-20 | 36 | 22.78 | 0 | 0.00 | 5 | 13.89 | 0 | 0.00 | 34 | 4 | 11.76 | 0 | 0 | 0.00 |
| Latinx | 20+ | 44 | 27.85 | 39 | 88.64 | 7 | 15.91 | 5 | 12.82 | 41 | 6 | 14.63 | 37 | 4 | 10.81 |
| White | 0-10 | 38 | 25.68 | 0 | 0.00 | 1 | 2.63 | 0 | 0.00 | 35 | 1 | 2.86 | 0 | 0 | 0.00 |
| White | 10-20 | 44 | 29.73 | 0 | 0.00 | 7 | 15.91 | 0 | 0.00 | 40 | 6 | 15.00 | 0 | 0 | 0.00 |
| White | 20+ | 66 | 44.59 | 53 | 80.30 | 7 | 10.61 | 3 | 5.66 | 62 | 7 | 11.29 | 51 | 3 | 5.88 |
py_screeninelig_grhivio_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 0, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 0, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "1", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_hdiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 0 & homicidegtmean2 == "1", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100) %>%
mutate("% Smokers in Pack Year Range by Race/Ethnicity" = Total_smoker / sum(Total_smoker) * 100)
colnames(py_screeninelig_grhivio_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"% Smokers in Pack Year Range by Race/Ethnicity",
"Screening Ineligible Smokers",
"% Screening Ineligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Screening Ineligible Smokers High Exposure to Violence",
"Screening Ineligible Smokers High Exposure to Violence Diagnosed",
"% Screening Ineligible Smokers High Exposure to Violence Diagnosed")
col_order7 <- c("Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"% Smokers in Pack Year Range by Race/Ethnicity",
"Screening Ineligible Smokers",
"% Screening Ineligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with High Exposure to Violence",
"Smokers with High Exposure to Violence Diagnosed",
"% Smokers with High Exposure to Violence Diagnosed",
"Screening Ineligible Smokers High Exposure to Violence",
"% Screening Ineligible Smokers High Exposure to Violence Diagnosed")
py_screeninelig_grhivio_table <- py_screeninelig_grhivio_table[, col_order7]
# Replace NaN values with 0 in "% Ineligible Smokers Diagnosed" column
py_screeninelig_grhivio_table$`% Ineligible Smokers Diagnosed` <- replace(py_screeninelig_grhivio_table$`% Ineligible Smokers Diagnosed`, !is.finite(py_screeninelig_grhivio_table$`% Ineligible Smokers Diagnosed`), 0)
# Replace NaN values with 0 in "% Smokers Screening Ineligible with High Exposure to Violence Diagnosed" column
py_screeninelig_grhivio_table$`% Screening Ineligible Smokers High Exposure to Violence Diagnosed` <- replace(py_screeninelig_grhivio_table$`% Screening Ineligible Smokers High Exposure to Violence Diagnosed`, !is.finite(py_screeninelig_grhivio_table$`% Screening Ineligible Smokers High Exposure to Violence Diagnosed`), 0)
# table
py_screenelig_grhivio_table %>%
kable(
align = "lllll",
caption = "Exploring Screening Ineligible Smokers Diagnosed with Lung Cancer by Race/Ethnicity with High Exposure to Violence (by avg pack year range)",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Smoker Count | % Smokers in Pack Year Range by Race/Ethnicity | Screening Eligible Smokers | % Screening Eligible Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed with Lung Cancer | Smokers Screening Eligible Diagnosed | % Eligible Smokers Diagnosed | Smokers with High Exposure to Violence | Smokers with High Exposure to Violence Diagnosed | % Smokers with High Exposure to Violence Diagnosed | Screening Eligible Smokers High Exposure to Violence | Screening Eligible Smokers High Exposure to Violence Diagnosed | % Screening Eligible Smokers High Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 0 | 0.00 | 37 | 10.42 | 0 | 0.00 | 194 | 20 | 10.31 | 0 | 0 | 0.00 |
| Black | 10-20 | 170 | 22.28 | 0 | 0.00 | 23 | 13.53 | 0 | 0.00 | 95 | 13 | 13.68 | 0 | 0 | 0.00 |
| Black | 20+ | 238 | 31.19 | 212 | 89.08 | 42 | 17.65 | 25 | 11.79 | 130 | 27 | 20.77 | 111 | 17 | 15.32 |
| Latinx | 0-10 | 78 | 49.37 | 0 | 0.00 | 3 | 3.85 | 0 | 0.00 | 9 | 1 | 11.11 | 0 | 0 | 0.00 |
| Latinx | 10-20 | 36 | 22.78 | 0 | 0.00 | 5 | 13.89 | 0 | 0.00 | 2 | 1 | 50.00 | 0 | 0 | 0.00 |
| Latinx | 20+ | 44 | 27.85 | 39 | 88.64 | 7 | 15.91 | 5 | 12.82 | 3 | 1 | 33.33 | 2 | 1 | 50.00 |
| White | 0-10 | 38 | 25.68 | 0 | 0.00 | 1 | 2.63 | 0 | 0.00 | 3 | 0 | 0.00 | 0 | 0 | 0.00 |
| White | 10-20 | 44 | 29.73 | 0 | 0.00 | 7 | 15.91 | 0 | 0.00 | 3 | 1 | 33.33 | 0 | 0 | 0.00 |
| White | 20+ | 66 | 44.59 | 53 | 80.30 | 7 | 10.61 | 3 | 5.66 | 3 | 0 | 0.00 | 1 | 0 | 0.00 |
py_screeninelig_grlvio_table <-
lung %>%
filter(smokingstatus >= 2 , na.rm = TRUE) %>%
filter(packyear_range %in% c("0-10", "10-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range) %>%
summarize(Total_smoker = n(),
total_smoker_elig = sum(screen_elig == 0, na.rm = TRUE),
per_screen_elig = mean(screen_elig == 0, na.rm = TRUE) * 100,
Total_smoker_diag = sum(malignanto == 1, na.rm = TRUE),
per_diag = (Total_smoker_diag / Total_smoker * 100),
smoker_elig_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_Sdiag = (smoker_elig_diag / total_smoker_elig * 100),
expose_vio = sum(homicidegtmean2 == "0", na.rm = TRUE),
expose_vio_diag = sum(homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_hdiag = (expose_vio_diag / expose_vio * 100),
elig_vio = sum(screen_elig == 0 & homicidegtmean2 == "0", na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100) %>%
mutate("% Smokers in Pack Year Range by Race/Ethnicity" = Total_smoker / sum(Total_smoker) * 100)
colnames(py_screeninelig_grlvio_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"Screening Ineligible Smokers",
"% Screening Ineligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Screening Ineligible Smokers Low Exposure to Violence",
"Screening Ineligible Smokers Low Exposure to Violence Diagnosed",
"% Screening Ineligible Smokers Low Exposure to Violence Diagnosed",
"% Smokers in Pack Year Range by Race/Ethnicity")
col_order8 <- c("Race/Ethnicity",
"Pack Year Range",
"Smoker Count",
"% Smokers in Pack Year Range by Race/Ethnicity",
"Screening Ineligible Smokers",
"% Screening Ineligible Smokers",
"Smokers Diagnosed with Lung Cancer",
"% Smokers Diagnosed with Lung Cancer",
"Smokers Screening Ineligible Diagnosed",
"% Ineligible Smokers Diagnosed",
"Smokers with Low Exposure to Violence",
"Smokers with Low Exposure to Violence Diagnosed",
"% Smokers with Low Exposure to Violence Diagnosed",
"Screening Ineligible Smokers Low Exposure to Violence",
"Screening Ineligible Smokers Low Exposure to Violence Diagnosed",
"% Screening Ineligible Smokers Low Exposure to Violence Diagnosed")
py_screeninelig_grlvio_table <- py_screeninelig_grlvio_table[, col_order8]
# table
py_screeninelig_grlvio_table %>%
kable(
align = "lllll",
caption = "Exploring Screening Ineligible Smokers Diagnosed with Lung Cancer by Race/Ethnicity with Low Exposure to Violence (by avg pack year range)",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Smoker Count | % Smokers in Pack Year Range by Race/Ethnicity | Screening Ineligible Smokers | % Screening Ineligible Smokers | Smokers Diagnosed with Lung Cancer | % Smokers Diagnosed with Lung Cancer | Smokers Screening Ineligible Diagnosed | % Ineligible Smokers Diagnosed | Smokers with Low Exposure to Violence | Smokers with Low Exposure to Violence Diagnosed | % Smokers with Low Exposure to Violence Diagnosed | Screening Ineligible Smokers Low Exposure to Violence | Screening Ineligible Smokers Low Exposure to Violence Diagnosed | % Screening Ineligible Smokers Low Exposure to Violence Diagnosed |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Black | 0-10 | 355 | 46.53 | 355 | 100.00 | 37 | 10.42 | 37 | 10.42 | 161 | 17 | 10.56 | 161 | 17 | 10.56 |
| Black | 10-20 | 170 | 22.28 | 170 | 100.00 | 23 | 13.53 | 23 | 13.53 | 75 | 10 | 13.33 | 75 | 10 | 13.33 |
| Black | 20+ | 238 | 31.19 | 26 | 10.92 | 42 | 17.65 | 17 | 65.38 | 108 | 15 | 13.89 | 7 | 7 | 100.00 |
| Latinx | 0-10 | 78 | 49.37 | 78 | 100.00 | 3 | 3.85 | 3 | 3.85 | 69 | 2 | 2.90 | 69 | 2 | 2.90 |
| Latinx | 10-20 | 36 | 22.78 | 36 | 100.00 | 5 | 13.89 | 5 | 13.89 | 34 | 4 | 11.76 | 34 | 4 | 11.76 |
| Latinx | 20+ | 44 | 27.85 | 5 | 11.36 | 7 | 15.91 | 2 | 40.00 | 41 | 6 | 14.63 | 4 | 2 | 50.00 |
| White | 0-10 | 38 | 25.68 | 38 | 100.00 | 1 | 2.63 | 1 | 2.63 | 35 | 1 | 2.86 | 35 | 1 | 2.86 |
| White | 10-20 | 44 | 29.73 | 44 | 100.00 | 7 | 15.91 | 7 | 15.91 | 40 | 6 | 15.00 | 40 | 6 | 15.00 |
| White | 20+ | 66 | 44.59 | 13 | 19.70 | 7 | 10.61 | 4 | 30.77 | 62 | 7 | 11.29 | 11 | 4 | 36.36 |
# ineligible smokers diagnosed
inelig_smokerdx =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("0-5", "5-10", "10-15", "15-20", "20+")) %>%
group_by(packyear_range5) %>%
summarize(
inelig_vio = sum(screen_elig == 0, na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokerdx) <- c(
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
inelig_smokerdx %>%
kable(
align = "lllll",
caption = "Screening Ineligible Smokers Dx Lung Cancer",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|
| 0-5 | 279 | 24 | 8.60 |
| 5-10 | 192 | 17 | 8.85 |
| 10-15 | 143 | 18 | 12.59 |
| 15-20 | 107 | 17 | 15.89 |
| 20+ | 44 | 23 | 52.27 |
# eligible smokers diagnosed
elig_smokerdx =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("20+")) %>%
group_by(packyear_range5) %>%
summarize(
elig_vio = sum(screen_elig == 1, na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100)
colnames(elig_smokerdx) <- c(
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
elig_smokerdx %>%
kable(
align = "lllll",
caption = "Screening Eligible Smokers Dx Lung Cancer",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|
| 20+ | 304 | 33 | 10.86 |
# ineligible smokers by race diagnosed
inelig_smokerdx5 =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("0-5", "5-10", "10-15", "15-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range5) %>%
summarize(
inelig_vio = sum(screen_elig == 0, na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokerdx5) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
inelig_smokerdx5 %>%
kable(
align = "lllll",
caption = "Screening Ineligible Smokers Dx Lung Cancer by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|---|
| Black | 0-5 | 203 | 20 | 9.85 |
| Black | 5-10 | 152 | 17 | 11.18 |
| Black | 10-15 | 99 | 10 | 10.10 |
| Black | 15-20 | 71 | 13 | 18.31 |
| Black | 20+ | 26 | 17 | 65.38 |
| Latinx | 0-5 | 52 | 3 | 5.77 |
| Latinx | 5-10 | 26 | 0 | 0.00 |
| Latinx | 10-15 | 24 | 3 | 12.50 |
| Latinx | 15-20 | 12 | 2 | 16.67 |
| Latinx | 20+ | 5 | 2 | 40.00 |
| White | 0-5 | 24 | 1 | 4.17 |
| White | 5-10 | 14 | 0 | 0.00 |
| White | 10-15 | 20 | 5 | 25.00 |
| White | 15-20 | 24 | 2 | 8.33 |
| White | 20+ | 13 | 4 | 30.77 |
# eligible smokers by race diagnosed
elig_smokerdx5 =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("20+")) %>%
group_by(raceethnic_cat, packyear_range5) %>%
summarize(
elig_vio = sum(screen_elig == 1, na.rm = TRUE),
elig_expose_vio_diag = sum(screen_elig == 1 & malignanto == 1, na.rm = TRUE),
per_diag_elig_vio = elig_expose_vio_diag / elig_vio * 100)
colnames(elig_smokerdx5) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
elig_smokerdx5 %>%
kable(
align = "lllll",
caption = "Screening Eligible Smokers Dx Lung Cancer by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|---|
| Black | 20+ | 212 | 25 | 11.79 |
| Latinx | 20+ | 39 | 5 | 12.82 |
| White | 20+ | 53 | 3 | 5.66 |
# ineligible smokers by race diagnosed with high exposure to violence
inelig_smokerhvio_race_count_table =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("0-5", "5-10", "10-15", "15-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range5) %>%
summarize(
inelig_vio = sum(screen_elig == 0 & homicidegtmean2 == "1", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokerhvio_race_count_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
inelig_smokerhvio_race_count_table %>%
kable(
align = "lllll",
caption = "Screening Ineligible Smokers with High Violence Exposure Dx Lung Cancer by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|---|
| Black | 0-5 | 112 | 11 | 9.82 |
| Black | 5-10 | 82 | 9 | 10.98 |
| Black | 10-15 | 64 | 6 | 9.38 |
| Black | 15-20 | 31 | 7 | 22.58 |
| Black | 20+ | 19 | 10 | 52.63 |
| Latinx | 0-5 | 7 | 1 | 14.29 |
| Latinx | 5-10 | 2 | 0 | 0.00 |
| Latinx | 10-15 | 1 | 0 | 0.00 |
| Latinx | 15-20 | 1 | 1 | 100.00 |
| Latinx | 20+ | 1 | 0 | 0.00 |
| White | 0-5 | 2 | 0 | 0.00 |
| White | 5-10 | 1 | 0 | 0.00 |
| White | 10-15 | 2 | 1 | 50.00 |
| White | 15-20 | 1 | 0 | 0.00 |
| White | 20+ | 2 | 0 | 0.00 |
# eligible smokers by race diagnosed with high exposure to violence
elig_smokerhvio_race_count_table =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("20+")) %>%
group_by(raceethnic_cat, packyear_range5) %>%
summarize(
inelig_vio = sum(screen_elig == 1 & homicidegtmean2 == "1", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "1" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(elig_smokerhvio_race_count_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
elig_smokerhvio_race_count_table %>%
kable(
align = "lllll",
caption = "Screening Eligible Smokers with High Violence Exposure Dx Lung Cancer by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|---|
| Black | 20+ | 111 | 17 | 15.32 |
| Latinx | 20+ | 2 | 1 | 50.00 |
| White | 20+ | 1 | 0 | 0.00 |
# ineligible smokers by race diagnosed with low exposure to violence
inelig_smokerlow_race_count_table =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("0-5", "5-10", "10-15", "15-20", "20+")) %>%
group_by(raceethnic_cat, packyear_range5) %>%
summarize(
inelig_vio = sum(screen_elig == 0 & homicidegtmean2 == "0", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 0 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(inelig_smokerlow_race_count_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
inelig_smokerlow_race_count_table %>%
kable(
align = "lllll",
caption = "Screening Ineligible Smokers with Low Violence Exposure Dx Lung Cancer by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|---|
| Black | 0-5 | 91 | 9 | 9.89 |
| Black | 5-10 | 70 | 8 | 11.43 |
| Black | 10-15 | 35 | 4 | 11.43 |
| Black | 15-20 | 40 | 6 | 15.00 |
| Black | 20+ | 7 | 7 | 100.00 |
| Latinx | 0-5 | 45 | 2 | 4.44 |
| Latinx | 5-10 | 24 | 0 | 0.00 |
| Latinx | 10-15 | 23 | 3 | 13.04 |
| Latinx | 15-20 | 11 | 1 | 9.09 |
| Latinx | 20+ | 4 | 2 | 50.00 |
| White | 0-5 | 22 | 1 | 4.55 |
| White | 5-10 | 13 | 0 | 0.00 |
| White | 10-15 | 17 | 4 | 23.53 |
| White | 15-20 | 23 | 2 | 8.70 |
| White | 20+ | 11 | 4 | 36.36 |
# eligible smokers by race diagnosed with low exposure to violence
elig_smokerlowvio_race_count_table =
lung %>%
filter(smokingstatus >= 2) %>%
filter(packyear_range5 %in% c("20+")) %>%
group_by(raceethnic_cat, packyear_range5) %>%
summarize(
inelig_vio = sum(screen_elig == 1 & homicidegtmean2 == "0", na.rm = TRUE),
inelig_expose_vio_diag = sum(screen_elig == 1 & homicidegtmean2 == "0" & malignanto == 1, na.rm = TRUE),
per_diag_inelig_vio = inelig_expose_vio_diag / inelig_vio * 100)
colnames(elig_smokerlowvio_race_count_table) <- c(
"Race/Ethnicity",
"Pack Year Range",
"Patient Count",
"Dx Lung Cancer",
"% Dx Lung Cancer")
# table
elig_smokerlowvio_race_count_table %>%
kable(
align = "lllll",
caption = "Screening Eligible Smokers with Low Violence Exposure Dx Lung Cancer by Race/Ethnicity",
digits = 2,
format.args = list(big.mark = ",")) %>%
kable_classic(font_size = 15,
full_width = F,
html_font = "Cambria") %>%
kable_styling(bootstrap_options = "striped", full_width = F, position = "left")| Race/Ethnicity | Pack Year Range | Patient Count | Dx Lung Cancer | % Dx Lung Cancer |
|---|---|---|---|---|
| Black | 20+ | 101 | 8 | 7.92 |
| Latinx | 20+ | 37 | 4 | 10.81 |
| White | 20+ | 51 | 3 | 5.88 |