Package 'ggscidca'

Title: Plotting Decision Curve Analysis with Coloured Bars
Description: Decision curve analysis is a method for evaluating and comparing prediction models that incorporates clinical consequences, requires only the data set on which the models are tested, and can be applied to models that have either continuous or dichotomous results. The 'ggscidca' package adds coloured bars of discriminant relevance to the traditional decision curve. Improved practicality and aesthetics. This method was described by Balachandran VP (2015) <doi:10.1016/S1470-2045(14)71116-7>.
Authors: Qiang Liu [aut, cre]
Maintainer: Qiang Liu <[email protected]>
License: GPL-3
Version: 0.2.3
Built: 2024-12-17 06:33:37 UTC
Source: CRAN

Help Index


A survival data on breast cancer.

Description

A survival data on breast cancer.

Usage

data(Breastcancer)

Format

An object of class data.frame with 660 rows and 12 columns.

Examples

data(Breastcancer)

cmprskstdca

Description

Generate data for plotting survival analysis decision curves.

Arguments

data

a data frame containing the variables in the model.

outcome

the outcome, response variable. Must be a variable contained within the data frame specified in data=.

predictors

the predictor variable(s). Must be a variable(s) contained within the data frame specified in data=.

probability

specifies whether or not each of the independent variables are probabilities. The default is TRUE.

xstart

starting value for x-axis (threshold probability) between 0 and 1. The default is 0.01.

xstop

stopping value for x-axis (threshold probability) between 0 and 1. The default is 0.99.

xby

increment for threshold probability. The default is 0.01.

ymin

minimum bound for graph.

harm

specifies the harm(s) associated with the independent variable(s). The default is none.

graph

specifies whether or not to display graph of net benefits. The default is TRUE.

intervention

plot net reduction in interventions

interventionper

number of net reduction in interventions per interger. The default is 100

loess.span

specifies the degree of smoothing. The default is 0.10.

timepoint

specifies the time point at which the decision curve analysis is performed.

cmprsk

if evaluating outcome in presence of a competing risk. The default is FALSE

smooth

specifies whether or not to smooth net benefit curve. The default is FALSE.

ttoutcome

Enter the time variable in your data.

legend.position

Set the position of the legend.

Details

This function was created and written by Dr Andrew Vickers to generate decision curve data.

Value

Returns a data for plotting a decision curve.


cox.tcdca

Description

You can use it to plot decision curves for multiple generative analysis or competitive risk models.

Arguments

...

Fill in multiple survival analysis or competitive risk models. You cannot mix and match.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

merge

If true is selected it will merge the two long zones.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Splitface

Name the faceted image.

Value

A picture.


dca

Description

Generate data for plotting survival analysis decision curves.

Arguments

data

a data frame containing the variables in the model.

outcome

the outcome, response variable. Must be a variable contained within the data frame specified in data=.

predictors

the predictor variable(s). Must be a variable(s) contained within the data frame specified in data=.

probability

specifies whether or not each of the independent variables are probabilities. The default is TRUE.

xstart

starting value for x-axis (threshold probability) between 0 and 1. The default is 0.01.

xstop

stopping value for x-axis (threshold probability) between 0 and 1. The default is 0.99.

xby

increment for threshold probability. The default is 0.01.

ymin

minimum bound for graph.

harm

specifies the harm(s) associated with the independent variable(s). The default is none.

graph

specifies whether or not to display graph of net benefits. The default is TRUE.

intervention

plot net reduction in interventions

interventionper

number of net reduction in interventions per interger. The default is 100

loess.span

specifies the degree of smoothing. The default is 0.10.

smooth

specifies whether or not to smooth net benefit curve. The default is FALSE.

Details

This function was created and written by Dr Andrew Vickers to generate decision curve data.

Value

Returns a data for plotting a decision curve.


A medical examination related data.

Description

A medical examination related data.

Usage

data(demo)

Format

An object of class data.frame with 832 rows and 34 columns.

Examples

data(demo)

A data for competitive risk modelling.

Description

A data for competitive risk modelling.

Usage

data(df_surv)

Format

An object of class tbl_df (inherits from tbl, data.frame) with 750 rows and 9 columns.

Examples

data(df_surv)

A data for random forest analysis.

Description

A data for random forest analysis.

Usage

data(LIRI)

Format

An object of class data.frame with 232 rows and 6 columns.

Examples

data(LIRI)

netdata

Description

netdata

Usage

netdata(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A data used for plotting.


netdata.ksvm

Description

netdata.ksvm

Usage

## S3 method for class 'ksvm'
netdata(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A data used for plotting.


newcrr

Description

Types of transformation of survival analysis models into competitive risk models.

Usage

newcrr(fit, cencode = 0, failcode = 1)

Arguments

fit

Modelling for Survival Analysis.

cencode

Censor status, default is 0.

failcode

Events of interest, default is 1.

Value

A list of competing risk model formats.


scidca

Description

You can use it to generate a decision curve with coloured bars.

Usage

scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Details

Table 1 represents the relationship between the baseline values of the data. This function can be easily done.Creates 'Table 1', i.e., description of baseline patient characteristics, which is essential in every medical research. Supports both continuous and categorical variables, as well as p-values and standardized mean differences.

Value

A picture.

Examples

library(survival)
library(reshape2)
library(ggplot2)
##Import the internal data of the R package
bc<-Breastcancer
##Categorical variables converted to factors
bc$histgrad<-as.factor(bc$histgrad)
bc$er<-as.factor(bc$er)
bc$pr<-as.factor(bc$pr)
bc$ln_yesno<-as.factor(bc$ln_yesno)
##Generate Survival Analysis Model
f1<-coxph(Surv(time,status)~er+histgrad+pr+age+ln_yesno,bc)
##Draw decision curve
scidca(f1)
scidca(f1,threshold.line = TRUE,threshold.text = TRUE)
##logistic regression model
fit<-glm(status~er+histgrad+pr+age+ln_yesno,family = binomial(link = "logit"),data=bc)
##Draw decision curve
scidca(f1)
scidca(f1,threshold.line = TRUE,threshold.text = TRUE)
##random forest model
library(randomForest)
LIRI<-LIRI
set.seed(1)
index <- sample(2,nrow(LIRI),replace = TRUE,prob=c(0.7,0.3))
traindata <- LIRI[index==1,]
testdata <- LIRI[index==2,]
traindata$status<-as.factor(traindata$status)
#Modelling random forests
fit<-randomForest(status ~ANLN+CENPA+GPR182+BCO2 ,data=traindata,ntree=500,
important=TRUE,proximity=TRUE)
scidca(fit,newdata = traindata)
scidca(fit,newdata = testdata )
scidca(fit,newdata = testdata ,threshold.line = TRUE,threshold.text = TRUE)

scidca.coxph

Description

scidca.coxph

Usage

## S3 method for class 'coxph'
scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A picture.


scidca.crr

Description

scidca.crr

Usage

## S3 method for class 'crr'
scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A picture.


scidca.glm

Description

scidca.glm

Usage

## S3 method for class 'glm'
scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A picture.


scidca.ksvm

Description

scidca.ksvm

Usage

## S3 method for class 'ksvm'
scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

This parameter is indispensable in the random forest decision curve. Fill in your data.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A picture.


scidca.randomForest

Description

scidca.randomForest

Usage

## S3 method for class 'randomForest'
scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

This parameter is indispensable in the random forest decision curve. Fill in your data.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A picture.


scidca.svm

Description

scidca.svm

Usage

## S3 method for class 'svm'
scidca(
  fit,
  newdata = NULL,
  timepoint = "median",
  cmprsk = FALSE,
  modelnames = NULL,
  merge = FALSE,
  y.min = NULL,
  xstop = NULL,
  y.max = NULL,
  pyh = NULL,
  relcol = "#c01e35",
  irrelcol = "#0151a2",
  relabel = "Nomogram relevant",
  irrellabel = "Nomogram irrelevant",
  text.size = 4.5,
  text.col = "green",
  colbar = TRUE,
  threshold.text = FALSE,
  threshold.line = FALSE,
  nudge_x = 0,
  nudge_y = 0,
  threshold.linetype = 2,
  threshold.linewidth = 1.2,
  threshold.linecol = "black",
  po.text.size = 4,
  po.text.col = "black",
  po.text.fill = "white",
  liftpec = NULL,
  rightpec = NULL,
  legend.position = c(0.85, 0.75)
)

Arguments

fit

Fill in the model you want to analyze. Support survival analysis and logistic regression.

newdata

This parameter is indispensable in the random forest decision curve. Fill in your data.

timepoint

If it is a survival analysis, fill in the point in time you need to study. The default is the median time.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

merge

If true is selected it will merge the two long zones.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Value

A picture.


stdca

Description

Generate data for plotting survival analysis decision curves.

Arguments

data

a data frame containing the variables in the model.

outcome

the outcome, response variable. Must be a variable contained within the data frame specified in data=.

predictors

the predictor variable(s). Must be a variable(s) contained within the data frame specified in data=.

probability

specifies whether or not each of the independent variables are probabilities. The default is TRUE.

xstart

starting value for x-axis (threshold probability) between 0 and 1. The default is 0.01.

xstop

stopping value for x-axis (threshold probability) between 0 and 1. The default is 0.99.

xby

increment for threshold probability. The default is 0.01.

ymin

minimum bound for graph.

harm

specifies the harm(s) associated with the independent variable(s). The default is none.

graph

specifies whether or not to display graph of net benefits. The default is TRUE.

intervention

plot net reduction in interventions

interventionper

number of net reduction in interventions per interger. The default is 100

loess.span

specifies the degree of smoothing. The default is 0.10.

timepoint

specifies the time point at which the decision curve analysis is performed.

cmprsk

if evaluating outcome in presence of a competing risk. The default is FALSE

smooth

specifies whether or not to smooth net benefit curve. The default is FALSE.

ttoutcome

Enter the time variable in your data.

Details

This function was created and written by Dr Andrew Vickers to generate decision curve data.

Value

Returns a data for plotting a decision curve.


tcdca

Description

You can use it to plot decision curves for multiple binary classification models.

Arguments

...

Fill in multiple binary classification models. Cannot populate correlation models with time.

newdata

If the decision curve of the validation set is to be analysed. Fill in the validation set data here.

cmprsk

If it is a competitive risk model, select TRUE here.

modelnames

Defines the name of the generated image model.

y.min

The maximum value of the negative part of the picture. Generally defaults to positive values multiplied by 0.4.

xstop

The maximum value of the X-axis of the picture.

y.max

The maximum value of the Y-axis. The default value is the maximum net benefit.

pyh

The height at which the bars are plotted cannot exceed y.min.

relcol

The colour of the relevant part of the bar. The default is red.

irrelcol

The colour of the irrelevant part of the bar. The default is blue.

relabel

Relevance Tags.

irrellabel

No relevant tags.

text.size

Font size.

text.col

The colour of the font.

colbar

The default is true, and if false is selected, bar plotting is cancelled.

merge

If true is selected it will merge the two long zones.

threshold.text

The default is FALSE, if TRUE is selected, a text message for the threshold will be added.

threshold.line

The default is FALSE, and if TRUE is selected, lines for the threshold will be added.

nudge_x

Used to adjust the x-axis position of the point where the threshold is located.

nudge_y

Used to adjust the y-axis position of the point where the threshold is located.

threshold.linetype

The line shape of the threshold line.

threshold.linewidth

The line width of the threshold line.

threshold.linecol

The colour of the threshold line.

po.text.size

The size of the threshold point text.

po.text.col

The colour of the threshold point text.

po.text.fill

The background of the threshold point text.

liftpec

Threshold point left displacement.

rightpec

Threshold point right displacement.

legend.position

Set the position of the legend.

Splitface

Name the faceted image.

Value

A picture.