In windyzn/urinaryDBP:
Title page
Title: Urinary Vitamin D Binding Protein Loss as a Potential Biomarker for Diabetic Nephropathy in Patients at Risk for Type 2 Diabetes
Author: Windy ZN Wang
Affiliations: University of Toronto
Disclaimers:
Correspondence: windy.wang@mail.utoronto.ca
Funding support: CIHR, Sharon Zeiler, BBDC Novo Nordisk, Dairy Farmers
Abstract
Background
Methods
Subjects
# Only set if the Rmd file is not in the parent directory (ie. 'projectname/')
knitr::opts_knit$set(root.dir = '../')
knitr::opts_chunk$set(collapse = TRUE, echo = FALSE, message = FALSE, warning = FALSE)
library(dplyr)
devtools::load_all()
load_data(update = TRUE)
set_options()
# extrafont::loadfonts(device="win")
# source('.Rprofile')
# run_setup()
# load_data('data/project_data.rda')
# dim(ds)
ds <- project_data
dsBase <- ds %>%
dplyr::filter(fVN == "Baseline")
# Subjects with measurements at all visit numbers
dsComplete <- ds %>%
dplyr::group_by(SID) %>%
dplyr::filter(n() == 3) %>%
dplyr::ungroup()
## Include captions below using `captioner` package
figNums <- captioner::captioner(prefix = 'Figure')
supFigNums <- captioner::captioner(prefix = 'Supplementary Figure')
tabNums <- captioner::captioner(prefix = 'Table')
supTabNums <- captioner::captioner(prefix = 'Supplementary Table')
PAPER 1: KIDNEY MEASURE RESULTS
Subject Characteristics
TABLE 1: Subject characteristics across UDBP tertiles
subchar_table_tert <- tableone::CreateTableOne(
vars = c("Age",
"Sex",
"Ethnicity",
"BMI",
"Waist",
"eGFR",
"ACR",
"UrineCreatinine",
"UrineMicroalbumin",
"UrinaryCalcium",
"UDBP",
"udbpCrRatio",
"Systolic",
"Diastolic",
"MeanArtPressure",
"dmStatus"),
strata = c("udbpTertile"),
data = dsBase,
factorVars = c("Sex", "Ethnicity", "dmStatus")
) %>%
print(nonnormal = c("UDBP",
"ACR",
"UrineMicroalbumin"),
quote = FALSE,
noSpaces = TRUE)
TABLE 2: Subject characteristics across UDBP:cR tertiles
subchar_table_tert <- tableone::CreateTableOne(
vars = c("Age",
"Sex",
"Ethnicity",
"BMI",
"Waist",
"eGFR",
"ACR",
"UrineCreatinine",
"UrineMicroalbumin",
"UrinaryCalcium",
"UDBP",
"udbpCrRatio",
"Systolic",
"Diastolic",
"MeanArtPressure",
"dmStatus"),
strata = c("udbpCrTertile"),
data = dsBase,
factorVars = c("Sex", "Ethnicity", "dmStatus")
) %>%
print(nonnormal = c("UDBP",
"ACR",
"UrineMicroalbumin"),
quote = FALSE,
noSpaces = TRUE)
TABLE 3: Subject characteristics across time
subchar_table_time <- tableone::CreateTableOne(
vars = c("Age",
"Sex",
"Ethnicity",
"BMI",
"Waist",
"eGFR",
"ACR",
"UrineCreatinine",
"UrineMicroalbumin",
"UDBP",
"udbpCrRatio",
"Systolic",
"Diastolic",
"MeanArtPressure",
"dmStatus"),
strata = c("fVN"),
data = ds,
factorVars = c("Sex", "Ethnicity", "dmStatus")
) %>%
print(nonnormal = c("UDBP",
"udbpCrRatio",
"ACR",
"UrineMicroalbumin"),
quote = FALSE,
noSpaces = TRUE)
TABLE 4: Subject characteristics across time (complete data)
subchar_table_time <- tableone::CreateTableOne(
vars = c("Age",
"Sex",
"Ethnicity",
"BMI",
"Waist",
"eGFR",
"ACR",
"UrineCreatinine",
"UrineMicroalbumin",
"UDBP",
"udbpCrRatio",
"Systolic",
"Diastolic",
"MeanArtPressure",
"dmStatus"),
strata = c("fVN"),
data = dsComplete,
factorVars = c("Sex", "Ethnicity", "dmStatus")
) %>%
print(nonnormal = c("UDBP",
"udbpCrRatio",
"ACR",
"UrineMicroalbumin"),
quote = FALSE,
noSpaces = TRUE)
Cross-sectional
ACR
# Clean data
acr <- ds %>%
filter(fVN == "Baseline") %>%
select(acrStatus, udbpCrRatio) %>%
na.omit()
# Box plot of uVDBP in different albuminuria categories
acr %>%
box_plot("acrStatus", "log(udbpCrRatio)",
"Albuminuria",
"log uVDBP:Creatinine")
# n
acr %>%
group_by(acrStatus) %>%
summarise(n = n())
# ANOVA
anova <- aov(formula = log(udbpCrRatio)~acrStatus, data = acr)
summary(anova)
TukeyHSD(anova)
rm(anova)
# Scatterplot of ACR and uVDBP ----------------------------------
ds %>%
filter(fVN == "Baseline") %>%
scatter_plot("log(ACR)", "log(udbpCrRatio)",
"log Albumin:Creatinine Ratio",
"log UDBP:Creatinine")
# Spearman Correlation ------------------------------------------
ds %>%
filter(fVN == "Baseline") %>%
cor.test(formula = ~ ACR + udbpCrRatio, data = ., method = "spearman")
# Linear Regression ---------------------------------------------
ds %>%
prep_mason_data() %>%
mason_glm(y = "ACR",
x = "udbpCrRatio",
covars = c("ageBase", "Sex", "Ethnicity", "fDM", "fMedsBP")
)
eGFR
# Clean data
eGFR <- ds %>%
filter(fVN == "Baseline") %>%
select(eGFRStatus, udbpCrRatio) %>%
na.omit()
# Box plot of uVDBP in different eGFR categories
eGFR %>%
box_plot("eGFRStatus", "log(udbpCrRatio)",
"Kidney Status",
"log uVDBP:Creatinine")
# n
eGFR %>%
group_by(eGFRStatus) %>%
summarise(n = n())
# ANOVA
anova <- aov(formula = log(udbpCrRatio)~eGFRStatus, data = eGFR)
summary(anova)
TukeyHSD(anova)
rm(anova)
# Scatterplot of eGFR and uVDBP ----------------------------------
ds %>%
filter(fVN == "Baseline") %>%
scatter_plot("log(eGFR)", "log(udbpCrRatio)",
"log Estimated Glomerular Filtration Rate",
"log UDBP:Creatinine")
# Spearman Correlation ------------------------------------------
ds %>%
filter(fVN == "Baseline") %>%
cor.test(formula = ~ eGFR + udbpCrRatio, data = ., method = "spearman")
# Linear Regression ---------------------------------------------
ds %>%
prep_mason_data() %>%
mason_glm(y = "eGFR",
x = "udbpCrRatio",
covars = c("ageBase", "Sex", "Ethnicity", "fDM", "fMedsBP")
)
ds %>%
prep_mason_data() %>%
mason_glm(y = "eGFR",
x = "udbpCrRatio"
# covars = "ageBase"
)
Medication
- There are 705 values across all time points with blood pressure medication data
- This is approximately half of all observations (1852 vs 705)
- CHECK IF MISSINGNESS == NOT TAKING OR REALLY MISSING!!
ds_med <- ds %>%
dplyr::select(SID, VN, fMedsBP) %>%
na.omit()
Progression
ACR
ds %>%
plot_progress(yvar = "log(ACR)",
ylab = "log(ACR)")
# Complete data
dsComplete %>%
plot_progress(yvar = "log(ACR)",
ylab = "log(ACR)")
# ANOVA ------------------------------------------------------------
anova <- aov(formula = log(ACR)~fVN, data = ds)
summary(anova)
TukeyHSD(anova)
rm(anova)
# GEE ---------------------------------------------------------------
ds %>%
prep_mason_data() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "VN") %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
dsComplete %>%
prep_mason_data() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "VN") %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
eGFR
ds %>%
plot_progress(yvar = "log(eGFR)",
ylab = "log(eGFR)")
# Complete data
dsComplete %>%
plot_progress(yvar = "log(eGFR)",
ylab = "log(eGFR)")
# ANOVA
anova <- aov(formula = log(eGFR)~fVN, data = dsComplete)
summary(anova)
TukeyHSD(anova)
rm(anova)
# GEE see above code chunk (ACR)
UDBP
ds %>%
plot_progress(yvar = "log(udbpCrRatio)",
ylab = "log(UDBP:Cr)")
# Complete data
dsComplete %>%
plot_progress(yvar = "log(udbpCrRatio)",
ylab = "log(UDBP:Cr)")
# ANOVA
anova <- aov(formula = log(udbpCrRatio)~fVN, data = dsComplete)
summary(anova)
TukeyHSD(anova)
rm(anova)
# Transformed using log
ds %>%
dplyr::select(udbpCrRatio, UDBP, fVN) %>%
box_plot("fVN", "log(udbpCrRatio)",
"Visit Number", "log UDBP:Creatinine")
# ANOVA Transformed
anova <- aov(formula = log(udbpCrRatio)~fVN, data = ds)
summary(anova)
TukeyHSD(anova)
rm(anova)
# Untransformed
ds %>%
dplyr::select(udbpCrRatio, UDBP, fVN) %>%
box_plot("fVN", "udbpCrRatio",
"Visit Number", "UDBP:Creatinine")
# ANOVA Untransformed
anova <- aov(formula = udbpCrRatio~fVN, data = ds)
summary(anova)
TukeyHSD(anova)
rm(anova)
# n
ds %>%
group_by(fMedsBP) %>%
summarise(n = n())
# LOESS curve
ds %>%
scatter_plot("VN", "log(UDBP)",
"Visit Number", "log(UDBP)")
# Plot individual progression with mean
plot_progress_by(ds, byvar = "Sex")
# Plot subset of individual progression with mean
ds %>%
dplyr::filter(Hypertension == 0) %>%
plot_progress_data(byvar = "fMedsBP")
# Interaction between BP medication and hypertension
ds %>%
prep_mason_data() %>%
mason_gee(y = c("UDBP"),
x = "MedsBloodPressure",
covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "fDM", "Hypertension"),
intvar = "Hypertension") %>%
dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
Generalized Estimating Equations
GEE where predictor is baseline UDBP
# Predictor is baseline UDBP ----------------------------------------
gee_baseline <- ds %>%
prep_mason_data_kidney() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "udbpBase",
covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "fPreDM", "fDysglycemia")) %>%
mason::polish_renaming(rename_gee_kidney)
# GEE table ----------------------------------------------------------
gee_baseline %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
# Plot ---------------------------------------------------------------
plot_gee_results_kidney(gee_baseline,
yvars = c("uAlbumin:creatinine (mg/mmol)",
"eGFR (ml/min/1.73m^2)"))
GEE where predictor is UDBP over time
# Predictor is UDBP at all time points ------------------------------
gee <- ds %>%
prep_mason_data_kidney() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "UDBP",
covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "fPreDM", "fDysglycemia")) %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::select(Yterms, Xterms, term, estimate, p.value, conf.low, conf.high, std.error)
# GEE table ----------------------------------------------------------
gee %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
# Plot ---------------------------------------------------------------
plot_gee_results_kidney(gee,
yvars = c("uAlbumin:creatinine (mg/mmol)",
"eGFR (ml/min/1.73m^2)"))
Interaction with Time
# Unadjusted interaction with visit number
ds %>%
prep_mason_data() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "UDBP",
covars = c("VN"),
intvar = "VN") %>%
dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
# Adjusted interaction with visit number
ds %>%
prep_gee_data() %>%
analyze_gee(y = c("ACR", "eGFR"),
x = "UDBP",
covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "fDM"),
intvar = "VN") %>%
dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
# Unadjusted interaction with months from baseline
ds %>%
prep_mason_data() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "UDBP",
covars = c("MonthsFromBaseline"),
intvar = "MonthsFromBaseline") %>%
dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
# Adjusted interaction with months from baseline
ds %>%
prep_mason_data() %>%
mason_gee(y = c("ACR", "eGFR"),
x = "UDBP",
covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "BMI", "fDM"),
intvar = "MonthsFromBaseline") %>%
dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
PAPER 2: VITAMIN D RESULTS
Subject Characteristics
# Diet information is not available at baseline. Only VN 3 data is available at the present time.
subchar_vitd_base <- tableone::CreateTableOne(
vars = c("Age",
"Sex",
"Ethnicity",
"BMI",
"Waist",
"eGFR",
"ACR",
"UrineCreatinine",
"UrineMicroalbumin",
"UrinaryCalcium",
"UDBP",
"udbpCrRatio",
"VitaminD",
"PTH",
"MET",
"Systolic",
"Diastolic",
"MeanArtPressure",
"diet_milk",
"diet_cal",
"diet_supp_cal",
"diet_supp_vitd",
"OralContraceptive",
"dmStatus"),
strata = c("vitdStatus"),
data = dsBase,
factorVars = c("Sex", "Ethnicity", "OralContraceptive", "dmStatus")
) %>%
print(nonnormal = c("UDBP",
"ACR",
"UrineMicroalbumin"),
quote = FALSE,
noSpaces = TRUE)
# Diet information is not available at baseline. Only VN 3 data is available at the present time.
subchar_vitd_base <- tableone::CreateTableOne(
vars = c("Age",
"Sex",
"Ethnicity",
"BMI",
"Waist",
"eGFR",
"ACR",
"UrineCreatinine",
"UrineMicroalbumin",
"UrinaryCalcium",
"UDBP",
"VitaminD",
"PTH",
"Systolic",
"Diastolic",
"MeanArtPressure",
"diet_milk",
"diet_cal",
"diet_supp_cal",
"diet_supp_vitd",
"OralContraceptive",
"dmStatus"),
strata = c("fVN"),
data = ds,
factorVars = c("Sex", "Ethnicity", "OralContraceptive", "dmStatus")
) %>%
print(nonnormal = c("UDBP",
"ACR",
"UrineMicroalbumin"),
quote = FALSE,
noSpaces = TRUE)
Cross-Sectional
# Clean data
vitd <- ds %>%
filter(fVN == "Baseline") %>%
select(vitdStatus, udbpCrRatio) %>%
na.omit()
# Box plot of uVDBP in different albuminuria categories
vitd %>%
box_plot("vitdStatus", "log(udbpCrRatio)",
"Vitamin D Status",
"log uVDBP:Creatinine")
# n
vitd %>%
group_by(vitdStatus) %>%
summarise(n = n())
# ANOVA
anova <- aov(formula = log(udbpCrRatio)~vitdStatus, data = vitd)
summary(anova)
TukeyHSD(anova)
rm(anova)
# Scatterplot of ACR and uVDBP ----------------------------------
dsBase %>%
scatter_plot("log(udbpCrRatio)", "VitaminD",
"log UDBP:Creatinine",
"Serum 25(OH)D")
# Spearman Correlation ------------------------------------------
dsBase %>%
cor.test(formula = ~ VitaminD + udbpCrRatio, data = ., method = "spearman")
# Linear Regression ---------------------------------------------
dsBase %>%
prep_mason_data() %>%
mason_glm(y = "VitaminD",
x = "udbpCrRatio",
covars = c("ageBase", "Sex", "Ethnicity", "MET", "BMI", "Season", "fDM")
) %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
PTH
# Scatterplot
dsBase %>%
scatter_plot("PTH", "VitaminD",
"Parathyroid Hormone (pmol/L)",
"Serum 25(OH)D (nmol/L)")
# Linear Regression ---------------------------------------------
dsBase %>%
prep_mason_data() %>%
mason_glm(y = "VitaminD",
x = "PTH"
) %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
Progression
ds %>%
plot_progress(yvar = "VitaminD",
ylab = "Serum 25(OH)D")
# Complete data
dsComplete %>%
plot_progress(yvar = "VitaminD",
ylab = "Serum 25(OH)D")
Generalized Estimating Equations
# Predictor is baseline UDBP ----------------------------------------
gee_vitd_baseline <- ds %>%
prep_mason_data_kidney() %>%
mason_gee(y = c("VitaminD"),
x = "udbpBase",
covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "BMI", "fDM", "Season"),
intvar = "Season")
# GEE table ----------------------------------------------------------
gee_vitd_baseline %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::mutate(p = round(p.value, 2),
p = ifelse(p == "0", "<0.001", p),
estCI = paste0(round(estimate, 2), " (",
round(conf.low, 2), ", ",
round(conf.high, 2), ")")) %>%
dplyr::select(Yterms, Xterms, term, estCI, p) %>%
# tidyr::spread(Yterms, estCI) %>%
pander::pander()
# Plot ---------------------------------------------------------------
plot_gee_results_kidney(gee_vitd_baseline,
yvars = c("uAlbumin:creatinine (mg/mmol)",
"eGFR (ml/min/1.73m^2)"))
# Predictor is baseline UDBP ----------------------------------------
gee <- ds %>%
prep_mason_data() %>%
mason_gee(y = c("VitaminD"),
x = "udbpBase",
covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "PTH", "fDM"))
# dplyr::filter(!term == "(Intercept)") %>%
# dplyr::select(Yterms, Xterms, term, estimate, p.value, conf.low, conf.high, std.error, sample.total)
# knitr::kable()
# Predictor is UDBP at all time points ------------------------------
gee <- ds %>%
prep_mason_data() %>%
mason_gee(y = c("VitaminD"),
x = "UDBP",
covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "PTH", "fDM")) %>%
dplyr::filter(!term == "(Intercept)") %>%
dplyr::select(Yterms, Xterms, term, estimate, p.value, conf.low, conf.high, std.error, sample.total)
plot_gee_results_vitd(gee,
yvars = c("VitaminD"))
Discussion
Acknowledgements
References
windyzn/urinaryDBP documentation built on May 4, 2019, 6:32 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Title page
Title: Urinary Vitamin D Binding Protein Loss as a Potential Biomarker for Diabetic Nephropathy in Patients at Risk for Type 2 Diabetes
Author: Windy ZN Wang
Affiliations: University of Toronto
Disclaimers:
Correspondence: windy.wang@mail.utoronto.ca
Funding support: CIHR, Sharon Zeiler, BBDC Novo Nordisk, Dairy Farmers
Abstract
Background
Methods
Subjects
# Only set if the Rmd file is not in the parent directory (ie. 'projectname/') knitr::opts_knit$set(root.dir = '../') knitr::opts_chunk$set(collapse = TRUE, echo = FALSE, message = FALSE, warning = FALSE) library(dplyr) devtools::load_all() load_data(update = TRUE) set_options() # extrafont::loadfonts(device="win")
# source('.Rprofile') # run_setup() # load_data('data/project_data.rda') # dim(ds) ds <- project_data dsBase <- ds %>% dplyr::filter(fVN == "Baseline") # Subjects with measurements at all visit numbers dsComplete <- ds %>% dplyr::group_by(SID) %>% dplyr::filter(n() == 3) %>% dplyr::ungroup()
## Include captions below using `captioner` package figNums <- captioner::captioner(prefix = 'Figure') supFigNums <- captioner::captioner(prefix = 'Supplementary Figure') tabNums <- captioner::captioner(prefix = 'Table') supTabNums <- captioner::captioner(prefix = 'Supplementary Table')
PAPER 1: KIDNEY MEASURE RESULTS
Subject Characteristics
TABLE 1: Subject characteristics across UDBP tertiles
subchar_table_tert <- tableone::CreateTableOne( vars = c("Age", "Sex", "Ethnicity", "BMI", "Waist", "eGFR", "ACR", "UrineCreatinine", "UrineMicroalbumin", "UrinaryCalcium", "UDBP", "udbpCrRatio", "Systolic", "Diastolic", "MeanArtPressure", "dmStatus"), strata = c("udbpTertile"), data = dsBase, factorVars = c("Sex", "Ethnicity", "dmStatus") ) %>% print(nonnormal = c("UDBP", "ACR", "UrineMicroalbumin"), quote = FALSE, noSpaces = TRUE)
TABLE 2: Subject characteristics across UDBP:cR tertiles
subchar_table_tert <- tableone::CreateTableOne( vars = c("Age", "Sex", "Ethnicity", "BMI", "Waist", "eGFR", "ACR", "UrineCreatinine", "UrineMicroalbumin", "UrinaryCalcium", "UDBP", "udbpCrRatio", "Systolic", "Diastolic", "MeanArtPressure", "dmStatus"), strata = c("udbpCrTertile"), data = dsBase, factorVars = c("Sex", "Ethnicity", "dmStatus") ) %>% print(nonnormal = c("UDBP", "ACR", "UrineMicroalbumin"), quote = FALSE, noSpaces = TRUE)
TABLE 3: Subject characteristics across time
subchar_table_time <- tableone::CreateTableOne( vars = c("Age", "Sex", "Ethnicity", "BMI", "Waist", "eGFR", "ACR", "UrineCreatinine", "UrineMicroalbumin", "UDBP", "udbpCrRatio", "Systolic", "Diastolic", "MeanArtPressure", "dmStatus"), strata = c("fVN"), data = ds, factorVars = c("Sex", "Ethnicity", "dmStatus") ) %>% print(nonnormal = c("UDBP", "udbpCrRatio", "ACR", "UrineMicroalbumin"), quote = FALSE, noSpaces = TRUE)
TABLE 4: Subject characteristics across time (complete data)
subchar_table_time <- tableone::CreateTableOne( vars = c("Age", "Sex", "Ethnicity", "BMI", "Waist", "eGFR", "ACR", "UrineCreatinine", "UrineMicroalbumin", "UDBP", "udbpCrRatio", "Systolic", "Diastolic", "MeanArtPressure", "dmStatus"), strata = c("fVN"), data = dsComplete, factorVars = c("Sex", "Ethnicity", "dmStatus") ) %>% print(nonnormal = c("UDBP", "udbpCrRatio", "ACR", "UrineMicroalbumin"), quote = FALSE, noSpaces = TRUE)
Cross-sectional
ACR
# Clean data acr <- ds %>% filter(fVN == "Baseline") %>% select(acrStatus, udbpCrRatio) %>% na.omit() # Box plot of uVDBP in different albuminuria categories acr %>% box_plot("acrStatus", "log(udbpCrRatio)", "Albuminuria", "log uVDBP:Creatinine") # n acr %>% group_by(acrStatus) %>% summarise(n = n()) # ANOVA anova <- aov(formula = log(udbpCrRatio)~acrStatus, data = acr) summary(anova) TukeyHSD(anova) rm(anova)
# Scatterplot of ACR and uVDBP ---------------------------------- ds %>% filter(fVN == "Baseline") %>% scatter_plot("log(ACR)", "log(udbpCrRatio)", "log Albumin:Creatinine Ratio", "log UDBP:Creatinine") # Spearman Correlation ------------------------------------------ ds %>% filter(fVN == "Baseline") %>% cor.test(formula = ~ ACR + udbpCrRatio, data = ., method = "spearman") # Linear Regression --------------------------------------------- ds %>% prep_mason_data() %>% mason_glm(y = "ACR", x = "udbpCrRatio", covars = c("ageBase", "Sex", "Ethnicity", "fDM", "fMedsBP") )
eGFR
# Clean data eGFR <- ds %>% filter(fVN == "Baseline") %>% select(eGFRStatus, udbpCrRatio) %>% na.omit() # Box plot of uVDBP in different eGFR categories eGFR %>% box_plot("eGFRStatus", "log(udbpCrRatio)", "Kidney Status", "log uVDBP:Creatinine") # n eGFR %>% group_by(eGFRStatus) %>% summarise(n = n()) # ANOVA anova <- aov(formula = log(udbpCrRatio)~eGFRStatus, data = eGFR) summary(anova) TukeyHSD(anova) rm(anova)
# Scatterplot of eGFR and uVDBP ---------------------------------- ds %>% filter(fVN == "Baseline") %>% scatter_plot("log(eGFR)", "log(udbpCrRatio)", "log Estimated Glomerular Filtration Rate", "log UDBP:Creatinine") # Spearman Correlation ------------------------------------------ ds %>% filter(fVN == "Baseline") %>% cor.test(formula = ~ eGFR + udbpCrRatio, data = ., method = "spearman") # Linear Regression --------------------------------------------- ds %>% prep_mason_data() %>% mason_glm(y = "eGFR", x = "udbpCrRatio", covars = c("ageBase", "Sex", "Ethnicity", "fDM", "fMedsBP") )
ds %>% prep_mason_data() %>% mason_glm(y = "eGFR", x = "udbpCrRatio" # covars = "ageBase" )
Medication
- There are 705 values across all time points with blood pressure medication data
- This is approximately half of all observations (1852 vs 705)
- CHECK IF MISSINGNESS == NOT TAKING OR REALLY MISSING!!
ds_med <- ds %>% dplyr::select(SID, VN, fMedsBP) %>% na.omit()
Progression
ACR
ds %>% plot_progress(yvar = "log(ACR)", ylab = "log(ACR)") # Complete data dsComplete %>% plot_progress(yvar = "log(ACR)", ylab = "log(ACR)") # ANOVA ------------------------------------------------------------ anova <- aov(formula = log(ACR)~fVN, data = ds) summary(anova) TukeyHSD(anova) rm(anova) # GEE --------------------------------------------------------------- ds %>% prep_mason_data() %>% mason_gee(y = c("ACR", "eGFR"), x = "VN") %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander() dsComplete %>% prep_mason_data() %>% mason_gee(y = c("ACR", "eGFR"), x = "VN") %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander()
eGFR
ds %>% plot_progress(yvar = "log(eGFR)", ylab = "log(eGFR)") # Complete data dsComplete %>% plot_progress(yvar = "log(eGFR)", ylab = "log(eGFR)") # ANOVA anova <- aov(formula = log(eGFR)~fVN, data = dsComplete) summary(anova) TukeyHSD(anova) rm(anova) # GEE see above code chunk (ACR)
UDBP
ds %>% plot_progress(yvar = "log(udbpCrRatio)", ylab = "log(UDBP:Cr)") # Complete data dsComplete %>% plot_progress(yvar = "log(udbpCrRatio)", ylab = "log(UDBP:Cr)") # ANOVA anova <- aov(formula = log(udbpCrRatio)~fVN, data = dsComplete) summary(anova) TukeyHSD(anova) rm(anova)
# Transformed using log ds %>% dplyr::select(udbpCrRatio, UDBP, fVN) %>% box_plot("fVN", "log(udbpCrRatio)", "Visit Number", "log UDBP:Creatinine") # ANOVA Transformed anova <- aov(formula = log(udbpCrRatio)~fVN, data = ds) summary(anova) TukeyHSD(anova) rm(anova) # Untransformed ds %>% dplyr::select(udbpCrRatio, UDBP, fVN) %>% box_plot("fVN", "udbpCrRatio", "Visit Number", "UDBP:Creatinine") # ANOVA Untransformed anova <- aov(formula = udbpCrRatio~fVN, data = ds) summary(anova) TukeyHSD(anova) rm(anova) # n ds %>% group_by(fMedsBP) %>% summarise(n = n()) # LOESS curve ds %>% scatter_plot("VN", "log(UDBP)", "Visit Number", "log(UDBP)") # Plot individual progression with mean plot_progress_by(ds, byvar = "Sex") # Plot subset of individual progression with mean ds %>% dplyr::filter(Hypertension == 0) %>% plot_progress_data(byvar = "fMedsBP") # Interaction between BP medication and hypertension ds %>% prep_mason_data() %>% mason_gee(y = c("UDBP"), x = "MedsBloodPressure", covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "fDM", "Hypertension"), intvar = "Hypertension") %>% dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
Generalized Estimating Equations
GEE where predictor is baseline UDBP
# Predictor is baseline UDBP ---------------------------------------- gee_baseline <- ds %>% prep_mason_data_kidney() %>% mason_gee(y = c("ACR", "eGFR"), x = "udbpBase", covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "fPreDM", "fDysglycemia")) %>% mason::polish_renaming(rename_gee_kidney) # GEE table ---------------------------------------------------------- gee_baseline %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander() # Plot --------------------------------------------------------------- plot_gee_results_kidney(gee_baseline, yvars = c("uAlbumin:creatinine (mg/mmol)", "eGFR (ml/min/1.73m^2)"))
GEE where predictor is UDBP over time
# Predictor is UDBP at all time points ------------------------------ gee <- ds %>% prep_mason_data_kidney() %>% mason_gee(y = c("ACR", "eGFR"), x = "UDBP", covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "fPreDM", "fDysglycemia")) %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::select(Yterms, Xterms, term, estimate, p.value, conf.low, conf.high, std.error) # GEE table ---------------------------------------------------------- gee %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander() # Plot --------------------------------------------------------------- plot_gee_results_kidney(gee, yvars = c("uAlbumin:creatinine (mg/mmol)", "eGFR (ml/min/1.73m^2)"))
Interaction with Time
# Unadjusted interaction with visit number ds %>% prep_mason_data() %>% mason_gee(y = c("ACR", "eGFR"), x = "UDBP", covars = c("VN"), intvar = "VN") %>% dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total) # Adjusted interaction with visit number ds %>% prep_gee_data() %>% analyze_gee(y = c("ACR", "eGFR"), x = "UDBP", covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "fDM"), intvar = "VN") %>% dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total) # Unadjusted interaction with months from baseline ds %>% prep_mason_data() %>% mason_gee(y = c("ACR", "eGFR"), x = "UDBP", covars = c("MonthsFromBaseline"), intvar = "MonthsFromBaseline") %>% dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total) # Adjusted interaction with months from baseline ds %>% prep_mason_data() %>% mason_gee(y = c("ACR", "eGFR"), x = "UDBP", covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "BMI", "fDM"), intvar = "MonthsFromBaseline") %>% dplyr::select(Yterms, Xterms, term, p.value, conf.low, conf.high, sample.total)
PAPER 2: VITAMIN D RESULTS
Subject Characteristics
# Diet information is not available at baseline. Only VN 3 data is available at the present time. subchar_vitd_base <- tableone::CreateTableOne( vars = c("Age", "Sex", "Ethnicity", "BMI", "Waist", "eGFR", "ACR", "UrineCreatinine", "UrineMicroalbumin", "UrinaryCalcium", "UDBP", "udbpCrRatio", "VitaminD", "PTH", "MET", "Systolic", "Diastolic", "MeanArtPressure", "diet_milk", "diet_cal", "diet_supp_cal", "diet_supp_vitd", "OralContraceptive", "dmStatus"), strata = c("vitdStatus"), data = dsBase, factorVars = c("Sex", "Ethnicity", "OralContraceptive", "dmStatus") ) %>% print(nonnormal = c("UDBP", "ACR", "UrineMicroalbumin"), quote = FALSE, noSpaces = TRUE)
# Diet information is not available at baseline. Only VN 3 data is available at the present time. subchar_vitd_base <- tableone::CreateTableOne( vars = c("Age", "Sex", "Ethnicity", "BMI", "Waist", "eGFR", "ACR", "UrineCreatinine", "UrineMicroalbumin", "UrinaryCalcium", "UDBP", "VitaminD", "PTH", "Systolic", "Diastolic", "MeanArtPressure", "diet_milk", "diet_cal", "diet_supp_cal", "diet_supp_vitd", "OralContraceptive", "dmStatus"), strata = c("fVN"), data = ds, factorVars = c("Sex", "Ethnicity", "OralContraceptive", "dmStatus") ) %>% print(nonnormal = c("UDBP", "ACR", "UrineMicroalbumin"), quote = FALSE, noSpaces = TRUE)
Cross-Sectional
# Clean data vitd <- ds %>% filter(fVN == "Baseline") %>% select(vitdStatus, udbpCrRatio) %>% na.omit() # Box plot of uVDBP in different albuminuria categories vitd %>% box_plot("vitdStatus", "log(udbpCrRatio)", "Vitamin D Status", "log uVDBP:Creatinine") # n vitd %>% group_by(vitdStatus) %>% summarise(n = n()) # ANOVA anova <- aov(formula = log(udbpCrRatio)~vitdStatus, data = vitd) summary(anova) TukeyHSD(anova) rm(anova)
# Scatterplot of ACR and uVDBP ---------------------------------- dsBase %>% scatter_plot("log(udbpCrRatio)", "VitaminD", "log UDBP:Creatinine", "Serum 25(OH)D") # Spearman Correlation ------------------------------------------ dsBase %>% cor.test(formula = ~ VitaminD + udbpCrRatio, data = ., method = "spearman") # Linear Regression --------------------------------------------- dsBase %>% prep_mason_data() %>% mason_glm(y = "VitaminD", x = "udbpCrRatio", covars = c("ageBase", "Sex", "Ethnicity", "MET", "BMI", "Season", "fDM") ) %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander()
PTH
# Scatterplot dsBase %>% scatter_plot("PTH", "VitaminD", "Parathyroid Hormone (pmol/L)", "Serum 25(OH)D (nmol/L)") # Linear Regression --------------------------------------------- dsBase %>% prep_mason_data() %>% mason_glm(y = "VitaminD", x = "PTH" ) %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander()
Progression
ds %>% plot_progress(yvar = "VitaminD", ylab = "Serum 25(OH)D") # Complete data dsComplete %>% plot_progress(yvar = "VitaminD", ylab = "Serum 25(OH)D")
Generalized Estimating Equations
# Predictor is baseline UDBP ---------------------------------------- gee_vitd_baseline <- ds %>% prep_mason_data_kidney() %>% mason_gee(y = c("VitaminD"), x = "udbpBase", covars = c("MonthsFromBaseline", "ageBase", "Sex", "Ethnicity", "BMI", "fDM", "Season"), intvar = "Season") # GEE table ---------------------------------------------------------- gee_vitd_baseline %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::mutate(p = round(p.value, 2), p = ifelse(p == "0", "<0.001", p), estCI = paste0(round(estimate, 2), " (", round(conf.low, 2), ", ", round(conf.high, 2), ")")) %>% dplyr::select(Yterms, Xterms, term, estCI, p) %>% # tidyr::spread(Yterms, estCI) %>% pander::pander() # Plot --------------------------------------------------------------- plot_gee_results_kidney(gee_vitd_baseline, yvars = c("uAlbumin:creatinine (mg/mmol)", "eGFR (ml/min/1.73m^2)"))
# Predictor is baseline UDBP ---------------------------------------- gee <- ds %>% prep_mason_data() %>% mason_gee(y = c("VitaminD"), x = "udbpBase", covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "PTH", "fDM")) # dplyr::filter(!term == "(Intercept)") %>% # dplyr::select(Yterms, Xterms, term, estimate, p.value, conf.low, conf.high, std.error, sample.total) # knitr::kable() # Predictor is UDBP at all time points ------------------------------ gee <- ds %>% prep_mason_data() %>% mason_gee(y = c("VitaminD"), x = "UDBP", covars = c("VN", "ageBase", "Sex", "Ethnicity", "BMI", "PTH", "fDM")) %>% dplyr::filter(!term == "(Intercept)") %>% dplyr::select(Yterms, Xterms, term, estimate, p.value, conf.low, conf.high, std.error, sample.total)
plot_gee_results_vitd(gee, yvars = c("VitaminD"))
Discussion
Acknowledgements
References
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.