The original project included two aims: 1- investigating the frequency and distribution of GAS and 2- the surgical complication of GAS among TM and TF individuals enrolled in STRONG as a function of KP site and patient sociodemographic characteristics. Given the scope of a master’s thesis, the decision was made to pursue aim 1 exclusively.
The primary outcome of aim 1 is receipt of any gender-affirming procedure (including both surgical and non-surgical procedures). The secondary outcome is receipt of gender-affirming surgery (GAS).
GAS includes:
Procedures not considered GAS:
# List of non-surgical procedures
code_lookup <- read_excel("Code_Details.xlsx")
code_lookup[code_lookup$GAS_surgery == "No", ] %>%
tbl_summary(include="code_description",
sort = code_description ~ "frequency",
label = list(code_description = "Procedures not included in GAS")) %>%
modify_header(label ~ "") %>%
bold_labels() %>%
modify_column_hide(column = stat_0)
# List of surgical procedures
code_lookup[code_lookup$GAS_surgery == "Yes", ] %>%
tbl_summary(include="code_description",
sort = code_description ~ "frequency",
label = list(code_description = "List of Gender-Affirming Surgery")) %>%
modify_header(label ~ "") %>%
bold_labels() %>%
modify_column_hide(column = stat_0)
Independent variables include KP site location as well as patient age, race/ethnicity, insurance type, TM vs TF status, and area-based measures of socioeconomic status (SES).
The original data is read in and copied to a new data frame. Data type is then confirmed for all character, factor, and date variables.
# Read in the data
Original_data <- read_excel("Original_data.xlsx")
# Pre-process the data to handle '#NULL!' values by replacing them with NA
Original_data <- Original_data %>%
mutate(across(where(is.character), ~na_if(.x, "#NULL!")))
# Now ensure that all the data types are correct
data <- Original_data %>%
mutate(
# Converting character columns
studyid = as.character(studyid),
site = as.character(site),
CODE = as.character(CODE),
CODETYPE = as.character(CODETYPE),
ENCTYPE = as.character(ENCTYPE),
ENCOUNTER_SUBTYPE = as.character(ENCOUNTER_SUBTYPE),
DEPT = as.character(DEPT),
# Converting categorical columns to factors
transgender = factor(transgender),
procedure = factor(procedure),
sex_natal = factor(sex_natal),
RACE1 = factor(RACE1),
RACE2 = factor(RACE2),
HISPANIC = factor(HISPANIC),
INS_MEDICAID = factor(INS_MEDICAID),
# Converting date columns
index_date = ymd(index_date),
birth_date = ymd(birth_date),
TRANS_CODE_ADATE = ymd(TRANS_CODE_ADATE),
TRANS_CODE_PROCDATE = ymd(TRANS_CODE_PROCDATE),
ENR_START = ymd(ENR_START),
ENR_END = ymd(ENR_END),
)
Existing categorical variables including KP site, transgender status, natal sex, race/ethnicity, and insurance are re-coded for ease of readability.
New variables are then created based on existing variables. Transgender type (TM vs TF) is created based on natal sex. A binary GAS variable is created based on the procedure variable. Age at index is transformed into a new categorical variable. Finally, a categorical poverty variable is created.
A new combined race_ethnicity variable was also created using the original RACE1 and HISPANIC variables. All individuals with HISPANIC = Yes are coded as “Hispanic” in new race/ethnicity variable. The remaining individuals (HISPANIC = “No” or “Unknown”) are coded as Non-Hispanic X based on race (i.e., Non-Hispanic Black).
data <- data %>%
mutate(
site = case_when(
site == "GA" ~ "Georgia",
site == "NC" ~ "Northern California",
site == "SC" ~ "Southern California",
TRUE ~ as.character(site) # Keeps the original value if none of the above conditions are met
),
transgender = if_else(transgender == 1, "Yes", "No"),
sex_natal = case_when(
sex_natal == "M" ~ "Male",
sex_natal == "F" ~ "Female",
TRUE ~ as.character(sex_natal)
),
RACE1 = case_when(
RACE1 == "AS" ~ "Asian",
RACE1 == "BA" ~ "Black/African American",
RACE1 == "HP" ~ "Hispanic/Latino- Native Hawaiian or Pacific Islander",
RACE1 == "IN" ~ "American Indian or Alaskan Native",
RACE1 == "MU" ~ "Multi-racial",
RACE1 == "UN" ~ "Unknown",
RACE1 == "WH" ~ "White",
TRUE ~ as.character(RACE1)
),
RACE2 = case_when(
RACE2 == "AS" ~ "Asian",
RACE2 == "BA" ~ "Black/African American",
RACE2 == "IN" ~ "American Indian or Alaskan Native", # not in original data dictionary
RACE2 == "UN" ~ "Unknown",
RACE2 == "WH" ~ "White",
RACE2 == "OT" ~ "Other",
TRUE ~ as.character(RACE2)
),
HISPANIC = case_when(
HISPANIC == "N" ~ "No",
HISPANIC == "Y" ~ "Yes",
HISPANIC == "U" ~ "Unknown",
TRUE ~ as.character(HISPANIC)
),
INS_MEDICAID = case_when(
INS_MEDICAID == "Y" ~ "Medicaid",
is.na(INS_MEDICAID) ~ "Commercial",
TRUE ~ as.character(INS_MEDICAID)
)
)
# check coding
table(data$site, Original_data$site)
table(data$transgender, Original_data$transgender)
table(data$RACE1, Original_data$RACE1)
table(data$RACE2, Original_data$RACE2)
table(data$HISPANIC, Original_data$HISPANIC)
table(data$INS_MEDICAID, Original_data$INS_MEDICAID)
# trans_type, age_at_index_group, poverty, poverty_cat
data <- data %>%
mutate(
trans_type = case_when(
sex_natal == "Male" ~ "Transfeminine",
sex_natal == "Female" ~ "Transmasculine",
TRUE ~ NA_character_
),
GAS_any = case_when(
procedure == 1 ~ "Yes",
procedure == 0 ~ "No",
TRUE ~ NA_character_
),
age_at_index_group = case_when(
age_at_index < 18 ~ "<18",
age_at_index >= 18 & age_at_index <= 34 ~ "18-34",
age_at_index >= 35 & age_at_index <= 64 ~ "35-64",
age_at_index >= 65 ~ "65+",
TRUE ~ NA_character_
),
poverty = pov_lt_50 + pov_50_74 + pov_75_99,
poverty_cat = case_when(
poverty < 0.1 ~ "<10%",
poverty >= 0.1 & poverty < 0.2 ~ "10-20%",
poverty >= 0.2 ~ ">20%",
TRUE ~ NA_character_
),
race_ethnicity = case_when(
HISPANIC == "Yes" ~ "Hispanic",
HISPANIC != "Yes" & RACE1 == "White" ~ "Non-Hispanic White",
HISPANIC != "Yes" & RACE1 == "Black/African American" ~ "Non-Hispanic Black",
HISPANIC != "Yes" & RACE1 == "Asian" ~ "Non-Hispanic Asian",
HISPANIC != "Yes" & RACE1 == "Hispanic/Latino- Native Hawaiian or Pacific Islander" ~ "Other/Unknown",
HISPANIC != "Yes" & RACE1 == "American Indian or Alaskan Native" ~ "Other/Unknown",
HISPANIC != "Yes" & RACE1 == "Multi-racial" ~ "Other/Unknown",
HISPANIC != "Yes" & RACE1 == "Unknown" ~ "Other/Unknown",
TRUE ~ NA_character_
)
)
# Set race_ethnicity to "Other/Unknown" if empty
data$race_ethnicity <- ifelse(is.na(data$race_ethnicity), "Other/Unknown", data$race_ethnicity)
# Check coding
# table(data$trans_type, data$sex_natal)
# table(data$procedure, data$GAS_any)
# table(data$poverty_cat)
# table(data$race_ethnicity, data$RACE1)
A code lookup sheet is read in and used to create code description and GAS type variables based on code. GAS type includes top, bottom, and other. An additional GAS_surgery variable is created to specifically identify gender-affirming surgeries (includes top, bottom, bony facial surgeries; excludes soft tissue face/body procedures (ie. blepharoplasties, rhytidectomies, liposuction/lipectomies), fillers, and hair removal). Finally, a binary GAS_bottom variable is created.
# Create list of all unique values for the CODE variable
code_list <- data.frame(unique(data$CODE))
# Read in procedure lookup table
code_lookup <- read_excel("Code_Details.xlsx")
# view(code_lookup)
# Ensure that the 'CODE' column in both data frames are of the same type
data$CODE <- as.character(data$CODE)
code_lookup$CODE <- as.character(code_lookup$CODE)
# Join the lookup table with main data frame using a left join
data <- data %>%
left_join(code_lookup, by = "CODE")
# New GAS_bottom variable
data <- data %>%
mutate(
GAS_bottom = case_when(
GAS_type == "Bottom" ~ "Yes",
!is.na(GAS_type) & GAS_type != "Bottom" ~ "No",
is.na(GAS_type) ~ NA_character_
)
)
# Set GAS_surgery to "No" if empty
unique(data$GAS_surgery) # variable has Yes No and NA
data$GAS_surgery <- ifelse(is.na(data$GAS_surgery), "No", data$GAS_surgery) # change NA's to No
unique(data$GAS_surgery) # check only Yes and No
table(data$GAS_surgery) # check number in each
# make new binary variable for GAS_any coded as 0 and 1
data$GAS_any_binary <- ifelse(data$GAS_any == "Yes", 1, 0)
# make new binary variable for GAS_surgery coded as 0 and 1
data$GAS_surgery_binary <- ifelse(data$GAS_surgery == "Yes", 1, 0)
Labels are added to all variables to improve formatting and readability.
label(data$studyid) <- "Participant study ID"
label(data$site) <- "KP site"
label(data$transgender) <- "Transgender Status"
label(data$procedure) <- "Gender Affirming Procedure"
label(data$index_date) <- "Index Date"
label(data$age_at_index) <- "Age at Index"
label(data$birth_date) <- "Date of Birth"
label(data$sex_natal) <- "Natal Sex"
label(data$RACE1) <- "Race 1 (if known)"
label(data$RACE2) <- "Race 2 (if known)"
label(data$HISPANIC) <- "Hispanic origin (ethnicity)"
label(data$trans_type) <- "Transgender Group"
label(data$age_at_index_group) <- "Age at Index Group"
label(data$TRANS_CODE_ADATE) <- "Admission date of the encounter where the transition procedure code was recorded"
label(data$TRANS_CODE_PROCDATE) <- "Actual date the procedure was performed (if available)"
label(data$CODE) <- "Code identifying the transition procedure"
label(data$CODETYPE) <- "Type of code (CPT, HCPCS, ICD9, ICD10, etc) of the transition procedure"
label(data$PXCNT) <- "Number of times that the procedure was performed"
label(data$ENCTYPE) <- "Type of encounter where the procedure was performed"
label(data$ENCOUNTER_SUBTYPE) <- "Subtype of encounter where the procedure was performed"
label(data$DEPT) <- "Department where the procedure was performed"
label(data$GAS_type) <- "Type of GAS"
label(data$GAS_bottom) <- "Received Genital Surgery"
label(data$ENR_START) <- "Medicaid Enrollment Start Date"
label(data$ENR_END) <- "Medicaid Enrollment End Date"
label(data$INS_MEDICAID) <- "Type of Insurance"
label(data$LOC_START) <- "LOC_START"
label(data$LOC_END) <- "LOC_END"
label(data$GEOCODE_BOUNDARY_YEAR) <- "GEOCODE_BOUNDARY_YEAR"
label(data$location_days_from_index) <- "DAYS_DIFF"
label(data$CENSUS_YEAR) <- "CENSUS_YEAR"
label(data$education1) <- "EDUCATION1"
label(data$education2) <- "EDUCATION2"
label(data$education3) <- "EDUCATION3"
label(data$education4) <- "EDUCATION4"
label(data$education5) <- "EDUCATION5"
label(data$education6) <- "EDUCATION6"
label(data$education7) <- "EDUCATION7"
label(data$education8) <- "EDUCATION8"
label(data$fampoverty) <- "FAMPOVERTY"
label(data$houspoverty) <- "HOUSPOVERTY"
label(data$pov_lt_50) <- "Poverty less than 5%"
label(data$pov_50_74) <- "Poverty 5-7.5%"
label(data$pov_75_99) <- "Poverty 7.5-9.9%"
label(data$pov_100_124) <- "Poverty 10-12.4%"
label(data$pov_125_149) <- "Poverty 12.5-14.9%"
label(data$pov_150_174) <- "Poverty 15-17.4%"
label(data$pov_175_184) <- "Poverty 17.5-18.4%"
label(data$pov_185_199) <- "Poverty 18.5-19.9%"
label(data$pov_gt_200) <- "Poverty greater than 20%"
label(data$poverty) <- "Poverty Sum (sum of 5%-9.9%)"
label(data$poverty_cat) <- "Percent living below poverty"
label(data$GAS_any) <- "Received GAS (*any procedure*)"
label(data$code_description) <- "Procedure code description"
label(data$GAS_surgery) <- "Received Gender Affirming Surgery (top, bottom, or bony face)"
label(data$race_ethnicity) <- "Race/Ethnicity"
# Check labels
# cbind(label(data))
table1 <- data %>%
select(age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_any, GAS_surgery, trans_type) %>%
mutate(GAS_any = factor(GAS_any, labels = c("No procedures", "Procedures"))) %>%
mutate(GAS_surgery = factor(GAS_surgery, labels = c("No surgery", "Surgery"))) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
tbl_summary(
missing = "no",
type = list(where(is.logical) ~ "categorical"),
sort = race_ethnicity ~ "frequency",
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty",
GAS_any = "Procedure History",
GAS_surgery = "Surgery History")) %>%
bold_labels() %>%
modify_header(label ~ "") %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Table 1. Descriptive Statistics</div>") %>%
as_gt() %>%
cols_width(everything()~px(250))
table1
| N = 15,5641 | |
|---|---|
| Age at Index | 24 (17, 35) |
| Age at Index Group | |
| Â Â Â Â <18 | 3,974 (26%) |
| Â Â Â Â 18-34 | 7,672 (49%) |
| Â Â Â Â 35-64 | 3,654 (23%) |
| Â Â Â Â 65+ | 264 (1.7%) |
| Race/Ethnicity | |
| Â Â Â Â Non-Hispanic White | 8,507 (55%) |
| Â Â Â Â Hispanic | 3,503 (23%) |
| Â Â Â Â Non-Hispanic Asian | 1,506 (9.7%) |
| Â Â Â Â Non-Hispanic Black | 1,066 (6.8%) |
| Â Â Â Â Other/Unknown | 982 (6.3%) |
| KP site | |
| Â Â Â Â Georgia | 168 (1.1%) |
| Â Â Â Â Northern California | 10,055 (65%) |
| Â Â Â Â Southern California | 5,341 (34%) |
| Type of Insurance | |
| Â Â Â Â Commercial | 11,998 (77%) |
| Â Â Â Â Medicaid | 3,566 (23%) |
| Percent living below poverty | |
| Â Â Â Â <10% | 9,793 (65%) |
| Â Â Â Â 10-20% | 3,473 (23%) |
| Â Â Â Â >20% | 1,883 (12%) |
| Procedure History | |
| Â Â Â Â No procedures | 8,639 (56%) |
| Â Â Â Â Procedures | 6,925 (44%) |
| Surgery History | |
| Â Â Â Â No surgery | 11,426 (73%) |
| Â Â Â Â Surgery | 4,138 (27%) |
| Transgender Group | |
| Â Â Â Â Transfeminine | 7,278 (47%) |
| Â Â Â Â Transmasculine | 8,286 (53%) |
| 1 Median (IQR); n (%) | |
table1 %>% gtsave(filename = "table1.png")
table1a <- data %>%
select(age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_any, GAS_surgery, trans_type) %>%
mutate(GAS_any = factor(GAS_any, labels = c("No procedures", "Procedures"))) %>%
mutate(GAS_surgery = factor(GAS_surgery, labels = c("No surgery", "Surgery"))) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
tbl_summary(
by = trans_type,
missing = "no",
type = list(where(is.logical) ~ "categorical"),
sort = race_ethnicity ~ "frequency",
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty",
GAS_any = "Procedure History",
GAS_surgery = "Surgery History")) %>%
bold_labels() %>%
modify_header(label ~ "") %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Table 1a. Descriptive Statistics by Transgender Group</div>") %>%
as_gt() %>%
cols_width(everything()~px(250))
table1a
| Transfeminine, N = 7,2781 | Transmasculine, N = 8,2861 | |
|---|---|---|
| Age at Index | 28 (20, 42) | 22 (16, 30) |
| Age at Index Group | ||
| Â Â Â Â <18 | 1,188 (16%) | 2,786 (34%) |
| Â Â Â Â 18-34 | 3,517 (48%) | 4,155 (50%) |
| Â Â Â Â 35-64 | 2,355 (32%) | 1,299 (16%) |
| Â Â Â Â 65+ | 218 (3.0%) | 46 (0.6%) |
| Race/Ethnicity | ||
| Â Â Â Â Non-Hispanic White | 4,007 (55%) | 4,500 (54%) |
| Â Â Â Â Hispanic | 1,556 (21%) | 1,947 (23%) |
| Â Â Â Â Non-Hispanic Asian | 817 (11%) | 689 (8.3%) |
| Â Â Â Â Non-Hispanic Black | 428 (5.9%) | 638 (7.7%) |
| Â Â Â Â Other/Unknown | 470 (6.5%) | 512 (6.2%) |
| KP site | ||
| Â Â Â Â Georgia | 92 (1.3%) | 76 (0.9%) |
| Â Â Â Â Northern California | 4,692 (64%) | 5,363 (65%) |
| Â Â Â Â Southern California | 2,494 (34%) | 2,847 (34%) |
| Type of Insurance | ||
| Â Â Â Â Commercial | 5,699 (78%) | 6,299 (76%) |
| Â Â Â Â Medicaid | 1,579 (22%) | 1,987 (24%) |
| Percent living below poverty | ||
| Â Â Â Â <10% | 4,581 (66%) | 5,212 (64%) |
| Â Â Â Â 10-20% | 1,574 (23%) | 1,899 (23%) |
| Â Â Â Â >20% | 831 (12%) | 1,052 (13%) |
| Procedure History | ||
| Â Â Â Â No procedures | 3,790 (52%) | 4,849 (59%) |
| Â Â Â Â Procedures | 3,488 (48%) | 3,437 (41%) |
| Surgery History | ||
| Â Â Â Â No surgery | 5,908 (81%) | 5,518 (67%) |
| Â Â Â Â Surgery | 1,370 (19%) | 2,768 (33%) |
| 1 Median (IQR); n (%) | ||
table1a %>% gtsave(filename = "table1a.png")
table1b <- data %>%
select(age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_any, trans_type) %>%
mutate(GAS_any = factor(GAS_any, labels = c("No procedures", "Procedures"))) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
tbl_summary(
by = GAS_any,
missing = "no",
type = list(where(is.logical) ~ "categorical"),
sort = race_ethnicity ~ "frequency",
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty",
GAS_any = "Procedure History",
GAS_surgery = "Surgery History")) %>%
bold_labels() %>%
modify_header(label ~ "") %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Table 1b. Descriptive Statistics by Procedure History</div>") %>%
as_gt() %>%
cols_width(everything()~px(250))
table1b
| No procedures, N = 8,6391 | Procedures, N = 6,9251 | |
|---|---|---|
| Age at Index | 22 (16, 32) | 27 (20, 37) |
| Age at Index Group | ||
| Â Â Â Â <18 | 2,969 (34%) | 1,005 (15%) |
| Â Â Â Â 18-34 | 3,793 (44%) | 3,879 (56%) |
| Â Â Â Â 35-64 | 1,737 (20%) | 1,917 (28%) |
| Â Â Â Â 65+ | 140 (1.6%) | 124 (1.8%) |
| Race/Ethnicity | ||
| Â Â Â Â Non-Hispanic White | 4,530 (52%) | 3,977 (57%) |
| Â Â Â Â Hispanic | 2,018 (23%) | 1,485 (21%) |
| Â Â Â Â Non-Hispanic Asian | 828 (9.6%) | 678 (9.8%) |
| Â Â Â Â Non-Hispanic Black | 567 (6.6%) | 499 (7.2%) |
| Â Â Â Â Other/Unknown | 696 (8.1%) | 286 (4.1%) |
| KP site | ||
| Â Â Â Â Georgia | 125 (1.4%) | 43 (0.6%) |
| Â Â Â Â Northern California | 5,475 (63%) | 4,580 (66%) |
| Â Â Â Â Southern California | 3,039 (35%) | 2,302 (33%) |
| Type of Insurance | ||
| Â Â Â Â Commercial | 6,743 (78%) | 5,255 (76%) |
| Â Â Â Â Medicaid | 1,896 (22%) | 1,670 (24%) |
| Percent living below poverty | ||
| Â Â Â Â <10% | 5,501 (65%) | 4,292 (64%) |
| Â Â Â Â 10-20% | 1,884 (22%) | 1,589 (24%) |
| Â Â Â Â >20% | 1,023 (12%) | 860 (13%) |
| Transgender Group | ||
| Â Â Â Â Transfeminine | 3,790 (44%) | 3,488 (50%) |
| Â Â Â Â Transmasculine | 4,849 (56%) | 3,437 (50%) |
| 1 Median (IQR); n (%) | ||
table1b %>% gtsave(filename = "table1b.png")
table1c <- data %>%
select(age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_surgery, trans_type) %>%
mutate(GAS_surgery = factor(GAS_surgery, labels = c("No surgery", "Surgery"))) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
tbl_summary(
by = GAS_surgery,
missing = "no",
type = list(where(is.logical) ~ "categorical"),
sort = race_ethnicity ~ "frequency",
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty",
GAS_surgery = "Surgery History")) %>%
bold_labels() %>%
modify_header(label ~ "") %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Table 1c. Descriptive Statistics by Surgery History</div>") %>%
as_gt() %>%
cols_width(everything()~px(250))
table1c
| No surgery, N = 11,4261 | Surgery, N = 4,1381 | |
|---|---|---|
| Age at Index | 23 (17, 34) | 27 (20, 38) |
| Age at Index Group | ||
| Â Â Â Â <18 | 3,294 (29%) | 680 (16%) |
| Â Â Â Â 18-34 | 5,467 (48%) | 2,205 (53%) |
| Â Â Â Â 35-64 | 2,492 (22%) | 1,162 (28%) |
| Â Â Â Â 65+ | 173 (1.5%) | 91 (2.2%) |
| Race/Ethnicity | ||
| Â Â Â Â Non-Hispanic White | 6,135 (54%) | 2,372 (57%) |
| Â Â Â Â Hispanic | 2,641 (23%) | 862 (21%) |
| Â Â Â Â Non-Hispanic Asian | 1,092 (9.6%) | 414 (10%) |
| Â Â Â Â Non-Hispanic Black | 737 (6.5%) | 329 (8.0%) |
| Â Â Â Â Other/Unknown | 821 (7.2%) | 161 (3.9%) |
| KP site | ||
| Â Â Â Â Georgia | 128 (1.1%) | 40 (1.0%) |
| Â Â Â Â Northern California | 7,213 (63%) | 2,842 (69%) |
| Â Â Â Â Southern California | 4,085 (36%) | 1,256 (30%) |
| Type of Insurance | ||
| Â Â Â Â Commercial | 8,831 (77%) | 3,167 (77%) |
| Â Â Â Â Medicaid | 2,595 (23%) | 971 (23%) |
| Percent living below poverty | ||
| Â Â Â Â <10% | 7,293 (65%) | 2,500 (62%) |
| Â Â Â Â 10-20% | 2,513 (23%) | 960 (24%) |
| Â Â Â Â >20% | 1,330 (12%) | 553 (14%) |
| Transgender Group | ||
| Â Â Â Â Transfeminine | 5,908 (52%) | 1,370 (33%) |
| Â Â Â Â Transmasculine | 5,518 (48%) | 2,768 (67%) |
| 1 Median (IQR); n (%) | ||
table1c %>% gtsave(filename = "table1c.png")
table2a <- data %>%
select(age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_any, trans_type) %>%
mutate(GAS_any = factor(GAS_any, labels = c("No procedures", "Procedures"))) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
tbl_strata(strata = trans_type, .tbl_fun = ~ .x %>%
tbl_summary(by = GAS_any,
missing = "no",
type = list(where(is.logical) ~ "categorical"),
sort = race_ethnicity ~ "frequency",
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty",
GAS_any = "Procedure History")),
.header = "**{strata}**, (N = {n})") %>%
bold_labels() %>%
modify_header(all_stat_cols() ~ "**{level}**") %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Table 2a. Procedure History by Transgender Group</div>") %>%
as_gt() %>%
cols_width(label ~ px(250), everything()~px(175))
table2a
| Characteristic | Transfeminine, (N = 7278) | Transmasculine, (N = 8286) | ||
|---|---|---|---|---|
| No procedures1 | Procedures1 | No procedures1 | Procedures1 | |
| Age at Index | 25 (18, 41) | 30 (23, 42) | 19 (15, 28) | 24 (18, 32) |
| Age at Index Group | ||||
| Â Â Â Â <18 | 935 (25%) | 253 (7.3%) | 2,034 (42%) | 752 (22%) |
| Â Â Â Â 18-34 | 1,612 (43%) | 1,905 (55%) | 2,181 (45%) | 1,974 (57%) |
| Â Â Â Â 35-64 | 1,126 (30%) | 1,229 (35%) | 611 (13%) | 688 (20%) |
| Â Â Â Â 65+ | 117 (3.1%) | 101 (2.9%) | 23 (0.5%) | 23 (0.7%) |
| Race/Ethnicity | ||||
| Â Â Â Â Non-Hispanic White | 2,000 (53%) | 2,007 (58%) | 2,530 (52%) | 1,970 (57%) |
| Â Â Â Â Hispanic | 826 (22%) | 730 (21%) | 1,192 (25%) | 755 (22%) |
| Â Â Â Â Non-Hispanic Asian | 428 (11%) | 389 (11%) | 400 (8.2%) | 289 (8.4%) |
| Â Â Â Â Other/Unknown | 312 (8.2%) | 158 (4.5%) | 384 (7.9%) | 128 (3.7%) |
| Â Â Â Â Non-Hispanic Black | 224 (5.9%) | 204 (5.8%) | 343 (7.1%) | 295 (8.6%) |
| KP site | ||||
| Â Â Â Â Georgia | 67 (1.8%) | 25 (0.7%) | 58 (1.2%) | 18 (0.5%) |
| Â Â Â Â Northern California | 2,369 (63%) | 2,323 (67%) | 3,106 (64%) | 2,257 (66%) |
| Â Â Â Â Southern California | 1,354 (36%) | 1,140 (33%) | 1,685 (35%) | 1,162 (34%) |
| Type of Insurance | ||||
| Â Â Â Â Commercial | 3,044 (80%) | 2,655 (76%) | 3,699 (76%) | 2,600 (76%) |
| Â Â Â Â Medicaid | 746 (20%) | 833 (24%) | 1,150 (24%) | 837 (24%) |
| Percent living below poverty | ||||
| Â Â Â Â <10% | 2,395 (66%) | 2,186 (65%) | 3,106 (65%) | 2,106 (62%) |
| Â Â Â Â 10-20% | 812 (22%) | 762 (23%) | 1,072 (22%) | 827 (24%) |
| Â Â Â Â >20% | 419 (12%) | 412 (12%) | 604 (13%) | 448 (13%) |
| 1 Median (IQR); n (%) | ||||
table2a %>% gtsave(filename = "table2a.png")
table2b <- data %>%
select(age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_surgery, trans_type) %>%
mutate(GAS_surgery = factor(GAS_surgery, labels = c("No surgery", "Surgery"))) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
tbl_strata(strata = trans_type, .tbl_fun = ~ .x %>%
tbl_summary(by = GAS_surgery,
missing = "no",
type = list(where(is.logical) ~ "categorical"),
sort = race_ethnicity ~ "frequency",
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty",
GAS_surgery = "Surgery History")),
.header = "**{strata}**, (N = {n})") %>%
bold_labels() %>%
modify_header(label ~ "") %>%
modify_header(all_stat_cols() ~ "**{level}**, N = {n}") %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Table 2b. Surgery History by Transgender Group</div>")%>%
as_gt() %>%
cols_width(label ~ px(250), starts_with("stat_1") ~ px(225), everything()~px(175))
table2b
| Transfeminine, (N = 7278) | Transmasculine, (N = 8286) | |||
|---|---|---|---|---|
| No surgery, N = 59081 | Surgery, N = 13701 | No surgery, N = 55181 | Surgery, N = 27681 | |
| Age at Index | 27 (19, 39) | 34 (24, 48) | 20 (15, 28) | 25 (18, 33) |
| Age at Index Group | ||||
| Â Â Â Â <18 | 1,093 (19%) | 95 (6.9%) | 2,201 (40%) | 585 (21%) |
| Â Â Â Â 18-34 | 2,906 (49%) | 611 (45%) | 2,561 (46%) | 1,594 (58%) |
| Â Â Â Â 35-64 | 1,763 (30%) | 592 (43%) | 729 (13%) | 570 (21%) |
| Â Â Â Â 65+ | 146 (2.5%) | 72 (5.3%) | 27 (0.5%) | 19 (0.7%) |
| Race/Ethnicity | ||||
| Â Â Â Â Non-Hispanic White | 3,240 (55%) | 767 (56%) | 2,895 (52%) | 1,605 (58%) |
| Â Â Â Â Hispanic | 1,295 (22%) | 261 (19%) | 1,346 (24%) | 601 (22%) |
| Â Â Â Â Non-Hispanic Asian | 639 (11%) | 178 (13%) | 453 (8.2%) | 236 (8.5%) |
| Â Â Â Â Other/Unknown | 401 (6.8%) | 69 (5.0%) | 420 (7.6%) | 92 (3.3%) |
| Â Â Â Â Non-Hispanic Black | 333 (5.6%) | 95 (6.9%) | 404 (7.3%) | 234 (8.5%) |
| KP site | ||||
| Â Â Â Â Georgia | 68 (1.2%) | 24 (1.8%) | 60 (1.1%) | 16 (0.6%) |
| Â Â Â Â Northern California | 3,762 (64%) | 930 (68%) | 3,451 (63%) | 1,912 (69%) |
| Â Â Â Â Southern California | 2,078 (35%) | 416 (30%) | 2,007 (36%) | 840 (30%) |
| Type of Insurance | ||||
| Â Â Â Â Commercial | 4,644 (79%) | 1,055 (77%) | 4,187 (76%) | 2,112 (76%) |
| Â Â Â Â Medicaid | 1,264 (21%) | 315 (23%) | 1,331 (24%) | 656 (24%) |
| Percent living below poverty | ||||
| Â Â Â Â <10% | 3,763 (66%) | 818 (64%) | 3,530 (65%) | 1,682 (62%) |
| Â Â Â Â 10-20% | 1,282 (22%) | 292 (23%) | 1,231 (23%) | 668 (25%) |
| Â Â Â Â >20% | 653 (11%) | 178 (14%) | 677 (12%) | 375 (14%) |
| 1 Median (IQR); n (%) | ||||
table2b %>% gtsave(filename = "table2b.png", vwidth = 1500, vheight = 1000)
#redo the TM / TF dataframes so they are updated
data_TF <- data[data$trans_type == "Transfeminine", ]
data_TM <- data[data$trans_type == "Transmasculine", ]
multi_proc_tm <- data_TM %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(formula = GAS_any_binary ~ age_at_index_group + race_ethnicity + site + INS_MEDICAID + poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis - Any Procedure (Transmasculine)") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
multi_proc_tm
| aOR | 95% CI | |
|---|---|---|
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 2.50 | 2.25, 2.78 |
| Â Â Â Â 35-64 | 3.09 | 2.68, 3.57 |
| Â Â Â Â 65+ | 2.82 | 1.52, 5.22 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.86 | 0.76, 0.97 |
| Â Â Â Â Non-Hispanic Asian | 0.93 | 0.79, 1.10 |
| Â Â Â Â Non-Hispanic Black | 1.03 | 0.87, 1.23 |
| Â Â Â Â Other/Unknown | 0.41 | 0.33, 0.50 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 2.70 | 1.60, 4.78 |
| Â Â Â Â Southern California | 2.69 | 1.58, 4.78 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.11 | 1.00, 1.24 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.07 | 0.96, 1.20 |
| Â Â Â Â >20% | 0.98 | 0.85, 1.13 |
multi_proc_tm %>% gtsave(filename = "multi_proc_tm.png")
multi_proc_tf <- data_TF %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(formula = GAS_any_binary ~ age_at_index_group + race_ethnicity + site + INS_MEDICAID + poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis - Any Procedure (Transfeminine)") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
multi_proc_tf
| aOR | 95% CI | |
|---|---|---|
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 4.68 | 4.01, 5.49 |
| Â Â Â Â 35-64 | 4.40 | 3.73, 5.20 |
| Â Â Â Â 65+ | 3.26 | 2.38, 4.45 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.95 | 0.83, 1.08 |
| Â Â Â Â Non-Hispanic Asian | 0.86 | 0.73, 1.01 |
| Â Â Â Â Non-Hispanic Black | 0.89 | 0.72, 1.11 |
| Â Â Â Â Other/Unknown | 0.48 | 0.39, 0.60 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 2.41 | 1.51, 3.94 |
| Â Â Â Â Southern California | 2.00 | 1.25, 3.30 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.41 | 1.25, 1.60 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 0.98 | 0.87, 1.11 |
| Â Â Â Â >20% | 0.99 | 0.84, 1.15 |
multi_proc_tf %>% gtsave(filename = "multi_proc_tf.png")
multi_surg_tm <- data_TM %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(formula = GAS_surgery_binary ~ age_at_index_group + race_ethnicity + site + INS_MEDICAID + poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis - Any Surgery (Transmasculine)") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
multi_surg_tm
| aOR | 95% CI | |
|---|---|---|
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 2.38 | 2.13, 2.67 |
| Â Â Â Â 35-64 | 2.89 | 2.50, 3.36 |
| Â Â Â Â 65+ | 2.86 | 1.52, 5.30 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.91 | 0.80, 1.02 |
| Â Â Â Â Non-Hispanic Asian | 0.94 | 0.79, 1.12 |
| Â Â Â Â Non-Hispanic Black | 0.97 | 0.81, 1.17 |
| Â Â Â Â Other/Unknown | 0.38 | 0.30, 0.48 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 2.35 | 1.37, 4.29 |
| Â Â Â Â Southern California | 1.81 | 1.04, 3.31 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.05 | 0.94, 1.18 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.10 | 0.98, 1.24 |
| Â Â Â Â >20% | 1.09 | 0.94, 1.26 |
multi_surg_tm %>% gtsave(filename = "multi_surg_tm.png")
multi_surg_tf <- data_TF %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(formula = GAS_surgery_binary ~ age_at_index_group + race_ethnicity + site + INS_MEDICAID + poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis - Any Surgery (Transfeminine)") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
multi_surg_tf
| aOR | 95% CI | |
|---|---|---|
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 2.45 | 1.95, 3.10 |
| Â Â Â Â 35-64 | 3.79 | 3.01, 4.83 |
| Â Â Â Â 65+ | 5.55 | 3.84, 8.00 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.97 | 0.82, 1.14 |
| Â Â Â Â Non-Hispanic Asian | 1.27 | 1.05, 1.53 |
| Â Â Â Â Non-Hispanic Black | 1.22 | 0.94, 1.57 |
| Â Â Â Â Other/Unknown | 0.73 | 0.55, 0.96 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 0.69 | 0.43, 1.14 |
| Â Â Â Â Southern California | 0.50 | 0.31, 0.83 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.27 | 1.09, 1.47 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.02 | 0.88, 1.19 |
| Â Â Â Â >20% | 1.19 | 0.98, 1.43 |
multi_surg_tf %>% gtsave(filename = "multi_surg_tf.png")
univariate_proc <- data %>%
select (age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_any_binary, trans_type) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
tbl_uvregression(method = glm,
y = GAS_any_binary,
exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**OR**", label ~ "") %>%
modify_column_hide(columns = c(stat_n, p.value)) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Univariate Analysis for Receipt of Any Procedure") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250),
everything()~px(100))
univariate_proc
| OR | 95% CI | |
|---|---|---|
| Age at Index | 1.01 | 1.01, 1.01 |
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 1.29 | 1.26, 1.31 |
| Â Â Â Â 35-64 | 1.31 | 1.28, 1.34 |
| Â Â Â Â 65+ | 1.24 | 1.17, 1.32 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.96 | 0.94, 0.98 |
| Â Â Â Â Non-Hispanic Asian | 0.98 | 0.96, 1.01 |
| Â Â Â Â Non-Hispanic Black | 1.00 | 0.97, 1.03 |
| Â Â Â Â Other/Unknown | 0.84 | 0.81, 0.87 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 1.22 | 1.13, 1.32 |
| Â Â Â Â Southern California | 1.19 | 1.10, 1.29 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.03 | 1.01, 1.05 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.02 | 1.00, 1.04 |
| Â Â Â Â >20% | 1.02 | 0.99, 1.04 |
| Transgender Group | ||
|     Transfeminine | — | — |
| Â Â Â Â Transmasculine | 0.94 | 0.92, 0.95 |
univariate_proc %>% gtsave(filename = "univariate_proc.png")
univariate_surg <- data %>%
select (age_at_index, age_at_index_group, race_ethnicity, site,
INS_MEDICAID, poverty_cat, GAS_surgery_binary, trans_type) %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
tbl_uvregression(method = glm,
y = GAS_surgery_binary,
exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**OR**", label ~ "") %>%
modify_column_hide(columns = c(stat_n, p.value)) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Univariate Analysis for Receipt of Any Surgery") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
univariate_surg
| OR | 95% CI | |
|---|---|---|
| Age at Index | 1.00 | 1.00, 1.00 |
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 1.12 | 1.10, 1.14 |
| Â Â Â Â 35-64 | 1.16 | 1.14, 1.18 |
| Â Â Â Â 65+ | 1.19 | 1.13, 1.26 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.97 | 0.95, 0.98 |
| Â Â Â Â Non-Hispanic Asian | 1.00 | 0.97, 1.02 |
| Â Â Â Â Non-Hispanic Black | 1.03 | 1.00, 1.06 |
| Â Â Â Â Other/Unknown | 0.89 | 0.87, 0.92 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 1.05 | 0.98, 1.12 |
| Â Â Â Â Southern California | 1.00 | 0.93, 1.07 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.01 | 0.99, 1.03 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.02 | 1.00, 1.04 |
| Â Â Â Â >20% | 1.04 | 1.02, 1.06 |
| Transgender Group | ||
|     Transfeminine | — | — |
| Â Â Â Â Transmasculine | 1.16 | 1.14, 1.17 |
univariate_surg %>% gtsave(filename = "univariate_surg.png")
multi_proc <- data %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(formula = GAS_any_binary ~ age_at_index_group + race_ethnicity + site + trans_type + INS_MEDICAID + poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis for Receipt of Any Procedure") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
multi_proc
| aOR | 95% CI | |
|---|---|---|
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 3.10 | 2.84, 3.38 |
| Â Â Â Â 35-64 | 3.32 | 3.00, 3.68 |
| Â Â Â Â 65+ | 2.46 | 1.89, 3.21 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.90 | 0.82, 0.98 |
| Â Â Â Â Non-Hispanic Asian | 0.90 | 0.80, 1.01 |
| Â Â Â Â Non-Hispanic Black | 0.97 | 0.85, 1.11 |
| Â Â Â Â Other/Unknown | 0.45 | 0.38, 0.52 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 2.51 | 1.77, 3.62 |
| Â Â Â Â Southern California | 2.30 | 1.62, 3.34 |
| Transgender Group | ||
|     Transfeminine | — | — |
| Â Â Â Â Transmasculine | 0.90 | 0.84, 0.97 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.23 | 1.14, 1.34 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.03 | 0.95, 1.12 |
| Â Â Â Â >20% | 0.98 | 0.88, 1.09 |
multi_proc %>% gtsave(filename = "multi_proc.png")
multi_surg <- data %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(formula = GAS_surgery_binary ~ age_at_index_group + race_ethnicity + site + trans_type + INS_MEDICAID + poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis for Receipt of Any Surgery") %>%
as_gt() %>%
rm_footnotes() %>%
cols_width(label ~ px(250), everything()~px(100))
multi_surg
| aOR | 95% CI | |
|---|---|---|
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 2.35 | 2.13, 2.60 |
| Â Â Â Â 35-64 | 3.21 | 2.85, 3.61 |
| Â Â Â Â 65+ | 4.38 | 3.27, 5.82 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.93 | 0.84, 1.03 |
| Â Â Â Â Non-Hispanic Asian | 1.07 | 0.94, 1.22 |
| Â Â Â Â Non-Hispanic Black | 1.04 | 0.89, 1.20 |
| Â Â Â Â Other/Unknown | 0.49 | 0.40, 0.58 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 1.26 | 0.87, 1.86 |
| Â Â Â Â Southern California | 0.95 | 0.66, 1.40 |
| Transgender Group | ||
|     Transfeminine | — | — |
| Â Â Â Â Transmasculine | 2.79 | 2.57, 3.02 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.13 | 1.03, 1.23 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.07 | 0.98, 1.17 |
| Â Â Â Â >20% | 1.12 | 1.00, 1.26 |
multi_surg %>% gtsave(filename = "multi_surg.png")
Explore all two-way interactions between TM/TF status and other variables (outcome = any PROCEDURE)
interaction_proc <- data %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(GAS_any_binary ~ trans_type * age_at_index_group + trans_type * race_ethnicity +
trans_type * site + trans_type * INS_MEDICAID + trans_type * poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis with Interaction Terms (Procedures) ") %>%
as_gt() %>%
rm_footnotes()
interaction_proc
| aOR | 95% CI | |
|---|---|---|
| Transgender Group | ||
|     Transfeminine | — | — |
| Â Â Â Â Transmasculine | 1.24 | 0.58, 2.59 |
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 4.68 | 4.01, 5.49 |
| Â Â Â Â 35-64 | 4.40 | 3.73, 5.20 |
| Â Â Â Â 65+ | 3.26 | 2.38, 4.45 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.95 | 0.83, 1.08 |
| Â Â Â Â Non-Hispanic Asian | 0.86 | 0.73, 1.01 |
| Â Â Â Â Non-Hispanic Black | 0.89 | 0.72, 1.11 |
| Â Â Â Â Other/Unknown | 0.48 | 0.39, 0.60 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 2.41 | 1.51, 3.94 |
| Â Â Â Â Southern California | 2.00 | 1.25, 3.30 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.41 | 1.25, 1.60 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 0.98 | 0.87, 1.11 |
| Â Â Â Â >20% | 0.99 | 0.84, 1.15 |
| Transgender Group * Age at Index Group | ||
| Â Â Â Â Transmasculine * 18-34 | 0.53 | 0.44, 0.65 |
| Â Â Â Â Transmasculine * 35-64 | 0.70 | 0.56, 0.88 |
| Â Â Â Â Transmasculine * 65+ | 0.86 | 0.43, 1.73 |
| Transgender Group * Race/Ethnicity | ||
| Â Â Â Â Transmasculine * Hispanic | 0.91 | 0.76, 1.08 |
| Â Â Â Â Transmasculine * Non-Hispanic Asian | 1.08 | 0.86, 1.36 |
| Â Â Â Â Transmasculine * Non-Hispanic Black | 1.16 | 0.88, 1.53 |
| Â Â Â Â Transmasculine * Other/Unknown | 0.84 | 0.62, 1.14 |
| Transgender Group * KP site | ||
| Â Â Â Â Transmasculine * Northern California | 1.12 | 0.55, 2.34 |
| Â Â Â Â Transmasculine * Southern California | 1.34 | 0.65, 2.82 |
| Transgender Group * Type of Insurance | ||
| Â Â Â Â Transmasculine * Medicaid | 0.78 | 0.67, 0.92 |
| Transgender Group * Percent living below poverty | ||
| Â Â Â Â Transmasculine * 10-20% | 1.09 | 0.93, 1.28 |
| Â Â Â Â Transmasculine * >20% | 0.99 | 0.80, 1.22 |
interaction_proc %>% gtsave(filename = "interaction_proc.png")
Explore all two-way interactions between TM/TF status and other variables (outcome = any SURGERY)
interaction_surg <- data %>%
mutate(poverty_cat = factor(poverty_cat, levels = c("<10%", "10-20%", ">20%"))) %>%
mutate(race_ethnicity = factor(race_ethnicity, levels = c("Non-Hispanic White", "Hispanic", "Non-Hispanic Asian",
"Non-Hispanic Black", "Other/Unknown"))) %>%
glm(GAS_surgery_binary ~ trans_type * age_at_index_group + trans_type * race_ethnicity + trans_type * site +
trans_type * INS_MEDICAID + trans_type * poverty_cat,
data = ., family = binomial(link = "logit")) %>%
tbl_regression(exponentiate = TRUE,
label = list(race_ethnicity = "Race/Ethnicity",
poverty_cat = "Percent living below poverty")) %>%
add_global_p() %>%
bold_labels() %>%
modify_header(estimate ~ "**aOR**", label ~ "") %>%
modify_column_hide(columns = p.value) %>%
modify_caption("<div style='text-align: left; font-weight: bold; color: grey'>
Multivariate Analysis with Interaction Terms (Surgeries) ") %>%
as_gt() %>%
rm_footnotes()
interaction_surg
| aOR | 95% CI | |
|---|---|---|
| Transgender Group | ||
|     Transfeminine | — | — |
| Â Â Â Â Transmasculine | 1.03 | 0.47, 2.24 |
| Age at Index Group | ||
|     <18 | — | — |
| Â Â Â Â 18-34 | 2.45 | 1.95, 3.10 |
| Â Â Â Â 35-64 | 3.79 | 3.01, 4.83 |
| Â Â Â Â 65+ | 5.55 | 3.84, 8.00 |
| Race/Ethnicity | ||
|     Non-Hispanic White | — | — |
| Â Â Â Â Hispanic | 0.97 | 0.82, 1.14 |
| Â Â Â Â Non-Hispanic Asian | 1.27 | 1.05, 1.53 |
| Â Â Â Â Non-Hispanic Black | 1.22 | 0.94, 1.57 |
| Â Â Â Â Other/Unknown | 0.73 | 0.55, 0.96 |
| KP site | ||
|     Georgia | — | — |
| Â Â Â Â Northern California | 0.69 | 0.43, 1.14 |
| Â Â Â Â Southern California | 0.50 | 0.31, 0.83 |
| Type of Insurance | ||
|     Commercial | — | — |
| Â Â Â Â Medicaid | 1.27 | 1.09, 1.47 |
| Percent living below poverty | ||
|     <10% | — | — |
| Â Â Â Â 10-20% | 1.02 | 0.88, 1.19 |
| Â Â Â Â >20% | 1.19 | 0.98, 1.43 |
| Transgender Group * Age at Index Group | ||
| Â Â Â Â Transmasculine * 18-34 | 0.97 | 0.75, 1.25 |
| Â Â Â Â Transmasculine * 35-64 | 0.76 | 0.58, 1.00 |
| Â Â Â Â Transmasculine * 65+ | 0.52 | 0.25, 1.06 |
| Transgender Group * Race/Ethnicity | ||
| Â Â Â Â Transmasculine * Hispanic | 0.94 | 0.76, 1.15 |
| Â Â Â Â Transmasculine * Non-Hispanic Asian | 0.74 | 0.57, 0.96 |
| Â Â Â Â Transmasculine * Non-Hispanic Black | 0.80 | 0.58, 1.10 |
| Â Â Â Â Transmasculine * Other/Unknown | 0.51 | 0.36, 0.74 |
| Transgender Group * KP site | ||
| Â Â Â Â Transmasculine * Northern California | 3.40 | 1.62, 7.28 |
| Â Â Â Â Transmasculine * Southern California | 3.63 | 1.71, 7.84 |
| Transgender Group * Type of Insurance | ||
| Â Â Â Â Transmasculine * Medicaid | 0.83 | 0.69, 1.00 |
| Transgender Group * Percent living below poverty | ||
| Â Â Â Â Transmasculine * 10-20% | 1.08 | 0.89, 1.31 |
| Â Â Â Â Transmasculine * >20% | 0.92 | 0.72, 1.16 |
interaction_surg %>% gtsave(filename = "interaction_surg.png")
Make new variable equal to the number of days between index date and admission date.
Check distribution of time to surgery …. NOTE: there are 319 cases where time is < 0 and 302 cases where time is equal to zero.
# summarize new variable ... look at min and number of NA's
summary(data$diff_adate) # ...min = -10675
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## -10675.0 175.0 482.0 713.6 1066.0 6210.0 8639
# histogram of time (years)
ggplot(data, aes(x = diff_adate)) +
geom_histogram(binwidth = 0.5, fill = "skyblue", color = "black") +
labs(title = "Histogram of diff_adate", x = "Difference", y = "Frequency")
Make new time_days variable that only includes cases were time to surgery is greater than 0. Duplicate this variable and convert to years. Look at time to surgery distribution
# new variable that sets dates <= 0 to NA
data <- data %>% mutate(time_days = ifelse(diff_adate <= 0, NA, diff_adate))
# convert to years
data <- data %>% mutate(time_years = time_days/365)
# histogram of time (years)
ggplot(data, aes(x = time_years)) +
geom_histogram(binwidth = 0.5, fill = "skyblue", color = "black") +
labs(title = "Histogram of time_years", x = "Difference", y = "Frequency")
Make Kaplan-Meier survival plots for time in years to any procedure and any surgery
# make survival objects for any PROCEDURE and any SURGERY
surv_obj_proc <- Surv(time = data$time_years, event = data$GAS_any_binary)
surv_obj_surg <- Surv(time = data$time_years, event = data$GAS_surgery_binary)
# Create survival curve
s1_proc <- survfit(surv_obj_proc ~ 1, data = data)
s1_surg <- survfit(surv_obj_surg ~ 1, data = data)
# Plot survival curve for PROCEDURES
km_curve_proc <- ggsurvfit(s1_proc, linewidth = 1) +
labs(title = "Kaplan-Meier Survival Plot for Procedures", x = 'Years', y = 'Overall survival') +
add_confidence_interval() +
add_risktable() +
scale_ggsurvfit()
km_curve_proc
# Plot survival curve for SURGERY
km_curve_surg <- ggsurvfit(s1_surg, linewidth = 1) +
labs(title = "Kaplan-Meier Survival Plot for Surgeries", x = 'Years', y = 'Overall survival') +
add_confidence_interval() +
add_risktable() +
scale_ggsurvfit()
km_curve_surg
Compare Kaplan-Meier survival plots by transgender group
# Log rank test by trans type for PROCEDURES
s2_proc <- survfit(surv_obj_proc ~ trans_type, data = data)
ggsurvplot(s2_proc, data = data,
size = 1,
censor.shape = '|', censor.size = 4,
conf.int = TRUE,
pval = TRUE,
risk.table = TRUE,
risk.table.height = 0.25,
ggtheme = theme_bw(),
title = "Log-Rank Test for Procedures by Transgender Group")
# Log rank test by trans type for PROCEDURES
s2_surg <- survfit(surv_obj_surg ~ trans_type, data = data)
ggsurvplot(s2_surg, data = data,
size = 1,
censor.shape = '|', censor.size = 4,
conf.int = TRUE,
pval = TRUE,
risk.table = TRUE,
risk.table.height = 0.25,
ggtheme = theme_bw(),
title = "Log-Rank Test for Surgeries by Transgender Group")
# plot cumulative event
ggsurvplot(fit_proc,
data = data,
conf.int = TRUE,
risk.table.col = "strata", # Change risk table color by groups
ggtheme = theme_bw(), # Change ggplot2 theme
fun = "event",
title = "Cumulative Event by Transgender Group (Procedures)")
ggsurvplot(fit_surg,
data = data,
conf.int = TRUE,
risk.table.col = "strata", # Change risk table color by groups
ggtheme = theme_bw(), # Change ggplot2 theme
fun = "event",
title = "Cumulative Event by Transgender Group (Surgery)")
# plot cumulative hazard
ggsurvplot(fit_proc,
data = data,
conf.int = TRUE,
risk.table.col = "strata", # Change risk table color by groups
ggtheme = theme_bw(), # Change ggplot2 theme
fun = "cumhaz",
title = "Cumulative Hazard by Transgender Group (Procedures)")
ggsurvplot(fit_surg,
data = data,
conf.int = TRUE,
risk.table.col = "strata", # Change risk table color by groups
ggtheme = theme_bw(), # Change ggplot2 theme
fun = "cumhaz",
title = "Cumulative Hazard by Transgender Group (Surgery)")
data$trans_type <- factor(data$trans_type)
cox_res_proc <- coxph(Surv(time_years, GAS_any_binary) ~ strata(trans_type) + age_at_index_group + race_ethnicity + site + INS_MEDICAID + poverty_cat, data = data, x=TRUE)
cox_res_surg <- coxph(Surv(time_years, GAS_surgery_binary) ~ strata(trans_type) + age_at_index_group + race_ethnicity + site + INS_MEDICAID + poverty_cat, data = data, x=TRUE)
# cumulative hazard curves
ggsurvplot(survfit(cox_res_proc),
data = data,
conf.int = TRUE,
risk.table.col = "strata",
risk.table = FALSE,
fun = "cumhaz",
title = "Adjusted Cumulative Hazard for Any Procedure",
subtitle = "Adjusted for age at index group, race/ethnicity, KP site, type of insurance, and percent living below poverty.",
font.subtitle = c("#838383"),
legend = c(0.15,0.85),
xlab = "Time (Years)",
ggtheme = theme())
ggsurvplot(survfit(cox_res_surg),
data = data,
conf.int = TRUE,
risk.table.col = "strata",
fun = "cumhaz",
title = "Adjusted Cumulative Hazard for Surgery",
subtitle = "Adjusted for age at index group, race/ethnicity, KP site, type of insurance, and percent living below poverty.",
font.subtitle = c("#838383"),
legend = c(0.15,0.85),
xlab = "Time (Years)",
ggtheme = theme())
# Confounder-adjusted survival curves --> takes forever to run
adjsurv_proc <- adjustedsurv(data=data,
variable="trans_type",
ev_time="time_years",
event="GAS_any_binary",
method="direct",
outcome_model=cox_res_proc,
conf_int=TRUE,
ggtheme=theme())
plot(adjsurv_proc, title= "Adjusted Cumulative Hazard for Any Procedure", conf_int=TRUE)
adjsurv_surg <- adjustedsurv(data=data,
variable="trans_type",
ev_time="time_years",
event="GAS_surgery_binary",
method="direct",
outcome_model=cox_res_surg,
conf_int=TRUE,
ggtheme=theme())
plot(adjsurv_surg, title= "Adjusted Cumulative Hazard for Surgery", conf_int=TRUE)