Package 'SurviMChd'

Title: High Dimensional Survival Data Analysis with Markov Chain Monte Carlo
Description: High dimensional survival data analysis with Markov Chain Monte Carlo(MCMC). Currently supports frailty data analysis. Allows for Weibull and Exponential distribution. Includes function for interval censored data.
Authors: Atanu Bhattacharjee [aut, cre, ctb], Akash Pawar [aut, ctb]
Maintainer: Atanu Bhattacharjee <[email protected]>
License: GPL-3
Version: 0.1.2
Built: 2024-11-24 06:28:56 UTC
Source: CRAN

Help Index

Frailty with Discrete Mixture Model

Description

Discrete mixture model with MCMC

Usage

fraidm(m, n, Ins, Del, Time, T.min, chn, iter, data)

Arguments

m

Starting column number form where study variables to be selected.
n

Ending column number till where study variables will get selected.
Ins

Variable name of Institute information.
Del

Variable name containing the event information.
Time

Variable name containing the time information.
T.min

Variable name containing the time of event information.
chn

Number of MCMC chains
iter

Define number of iterations as number.
data

High dimensional data, event information given as (delta=0 if alive, delta=1 if died). If patient is censored then t.min=duration of survival. If patient is died then t.min=0. If patient is died then t=duration of survival. If patient is alive then t=NA.

Details

By given m and n, a total of 3 variables can be selected.

Value

fraidmout - b[1] is the posterior estimate of the regression coefficient for first covariate.

b[2] is the posterior estimate of the regression coefficient for second covariate.

b[3] is the posterior estimate of the regression coefficient for third covariate.

omega[1] and omega[2] are frailty effects.

c[1] and c[2] are regression intercept and coefficients of covariates over mean effect.

References

Bhattacharjee, A. (2020). Bayesian Approaches in Oncology Using R and OpenBUGS. CRC Press.

Congdon, P. (2014). Applied bayesian modelling (Vol. 595). John Wiley & Sons.

See Also

fraidpm frairand

Examples

##
data(frailty)
fraidm(m=5,n=7,Ins="institute",Del="del",Time="timevar",T.min="time.min",chn=2,iter=6,data=frailty)
##

Frailty with drichlet process mixture

Description

Frailty analysis on high dimensional data by Drichlet process mixture.

Usage

fraidpm(m, n, Ins, Del, Time, T.min, chn, iter, adapt, data)

Arguments

m

Starting column number form where study variables to be selected.
n

Ending column number till where study variables will get selected.
Ins

Variable name of Institute information.
Del

Variable name containing the event information.
Time

Variable name containing the time information.
T.min

Variable name containing the time of event information.
chn

Number of MCMC chains.
iter

Define number of iterations as number.
adapt

Define number of adaptations as number.
data

High dimensional data, event information given as (delta=0 if alive, delta=1 if died). If patient is censored then t.min=duration of survival. If patient is died then t.min=0. If patient is died then t=duration of survival. If patient is alive then t=NA.

Details

By given m and n, a total of 3 variables can be selected.

Value

fraidpmout omeg[i] are frailty effects.

Author(s)

Atanu Bhattacharjee and Akash Pawar

References

Bhattacharjee, A. (2020). Bayesian Approaches in Oncology Using R and OpenBUGS. CRC Press.

Congdon, P. (2014). Applied bayesian modelling (Vol. 595). John Wiley & Sons.

See Also

fraidm frairand

Examples

##
data(frailty)
fraidpm(m=5,n=7,Ins="institute",Del="del",Time="timevar",T.min="time.min",chn=2,iter=6,
adapt=100,data=frailty)
##

Frailty in high dimensional survival data.

Description

Data set listing institutional wise survival outcomes

Survival observations data for frailty model functions of SurviMChd

Usage

data(frailty)

Format

A tibble with 7 columns and 272 rows which are :

institute

Institute of the sample observations

del

Numberic values 0 or 1 containing death/event information

timevar

Survival duration

time.min

Minimum survival

female

Covariate_1, gender variable indicating either a female or not

ph.karno

Covariate_2

pat.karno

Covariate_3

Examples

data(frailty)

Frailty with random effects in high dimensional data with MCMC

Description

Random effects frailty model

Usage

frairand(m, n, Ins, Del, Time, T.min, chn, iter, adapt, data)

Arguments

m

Starting column number form where study variables to be selected.
n

Ending column number till where study variables will get selected.
Ins

Variable name of Institute information.
Del

Variable name containing the event information.
Time

Variable name containing the time information.
T.min

Variable name containing the time of event information.
chn

Numner of MCMC chains.
iter

Define number of iterations as number.
adapt

Define number of adaptations as number.
data

High dimensional data having survival duration, event information and column of time for death cases.

Details

By given m and n, a total of 3 variables can be selected.

Value

frairandout omeg[i] are frailty effects.

Author(s)

Atanu Bhattacharjee and Akash Pawar

References

Tawiah, R., Yau, K. K., McLachlan, G. J., Chambers, S. K., & Ng, S. K. (2019). Multilevel model with random effects for clustered survival data with multiple failure outcomes. Statistics in medicine, 38(6), 1036-1055.

See Also

fraidm fraidpm

Examples

##
data(frailty)
frairand(m=5,n=7,Ins="institute",Del="del",Time="timevar",T.min="time.min",chn=2,iter=6,
 adapt=100,data=frailty)
##

High dimensional genomic data on head and neck cancer

Description

Head and neck cancer data tibble on head and neck cancer patients for survexpMC and survweibMC functions.

Usage

data(headnneck)

Format

A tibble with 13 columns which are :

Subjects

Patients referred to as Subjects

OS

Overall Survival

Death

Death status for the particular subjects

randgrp1

Arm of group assigned to subjects

gender1

Demographic information of Subjects, i.e. Gender

Stratum1

Stratum from where the sample is drawn

prevoi

Categorical observation

Covariate_1

Continuous observations

Covariate_2

Continuous observations

Covariate_3

Continuous observations

Covariate_4

Continuous observations

Covariate_5

Continuous observations

Covariate_6

Continuous observations

Examples

data(headnneck)

hnscc Head and neck cancer data

Description

High dimensional head and neck cancer gene expression data

Usage

data(hnscc)

Format

A dataframe with 565 rows and 104 variables

ID

ID of subjects

leftcensoring

Initial censoring time

death

Survival event

os

Duration of overall survival

PFS

Duration of progression free survival

Prog

Progression event

GJB1,...,HMGCS2

High dimensional covariates

Examples

data(hnscc)

Metronomic cancer data

Description

Observations made tibble on the head and neck cancer patients. Data for survMC function from SurviMChd package.

Usage

data(mcsurv)

Format

A tibble with 15 columns which are :

OS

Overall Survival

Death

Death status

t

Time at which event occurred

x1

Variable measured on continuous scale

x2

Variable measured on discrete scale

x3

Variable measured on continuous scale

x4

Variable measured on discrete scale

x5

Variable measured on continuous scale

Examples

data(mcsurv)

Exponential survival analysis with MCMC

Description

Survival analysis with exponential distribution by MCMC

Usage

survexpMC(m1, n1, m2, n2, chains, iter, data)

Arguments

m1

Starting column number from where variables of high dimensional data will be selected.
n1

Ending column number till where variables of high dimensional data will get selected.
m2

Starting column number from where demographic observations starts
n2

Ending column number of the demographic observations
chains

Number of MCMC chains
iter

Number of MCMC iterations
data

High dimensional data having survival duration as (OS), event information as Death (1 if died, or 0 if alive).

Value

survexpMCout A data set listing estimated posterior means and deviances

Author(s)

Atanu Bhattacharjee and Akash Pawar

References

Kumar, M., Sonker, P. K., Saroj, A., Jain, A., Bhattacharjee, A., & Saroj, R. K. (2020). Parametric survival analysis using R: Illustration with lung cancer data. Cancer Reports, 3(4), e1210.

See Also

survweibMC

Examples

##
data(headnneck)
survexpMC(m1=8,n1=12,m2=4,n2=7,chains=2,iter=10,data=headnneck)
##

Survival analysis using Cox Proportional Hazards with MCMC.

Description

Performs survival analysis using Cox Proportional Hazards with MCMC.

Usage

survMC(m, n, Time, Event, chains, adapt, iter, data)

Arguments

m

Starting column number from where variables of high dimensional data will get selected.
n

Ending column number till where variables of high dimensional data will get selected.
Time

Variable/Column name containing the information on duration of survival
Event

Variable/Column name containing the information of survival event
chains

Number of chains to perform
adapt

Number of adaptations to perform
iter

Number of iterations to perform
data

High dimensional data having survival duration and event.

Details

The survival columns of the data should be arranged as follows - Death Death status=1 if died otherwise 0. OS Survival duration measured as 'OS' t.len Number of censored times

Value

Data set containing Posterior HR estimates, SD and quantiles.

Author(s)

Atanu Bhattacharjee and Akash Pawar

References

Bhattacharjee, A. (2020). Bayesian Approaches in Oncology Using R and OpenBUGS. CRC Press.

See Also

survintMC

Examples

##
data(mcsurv)
survMC(m=4,n=8,Time="OS",Event="Death",chains=2,adapt=100,iter=1000,data=mcsurv)
##

Survival analysis on multiple variables with MCMC

Description

Performs survival analysis using Cox Proportional Hazards with MCMC with an option to input select multiple variables.

Usage

survMCmulti(
  var1 = NULL,
  var2 = NULL,
  var3 = NULL,
  var4 = NULL,
  var5 = NULL,
  Time,
  Event,
  chains,
  adapt,
  iter,
  data
)

Arguments

var1

Variable name (first one)
var2

Variable name (second one)
var3

Variable name (third one)
var4

Variable name (fourth one)
var5

Variable name (fifth one)
Time

Variable/Column name containing the information on duration of survival
Event

Variable/Column name containing the information of survival event
chains

Number of chains to perform
adapt

Number of chains to perform
iter

Number of iterations to perform
data

High dimensional data having survival duration and event.

Details

The survival columns of the data should be arranged as follows - Death Death status=1 if died otherwise 0. OS Survival duration measured as 'OS'

Value

Data set containing Posterior HR estimates, SD, quantiles and meandeviance.

Author(s)

Atanu Bhattacharjee and Akash Pawar

References

Bhattacharjee, A. (2020). Bayesian Approaches in Oncology Using R and OpenBUGS. CRC Press.

See Also

survintMC

Examples

##
data(mcsurv)
survMCmulti(var1="x1",var2=NULL,var3="x3",var4="x2",
   var5="x4",Time="OS",Event="Death",chains=2,adapt=100,iter=1000,data=mcsurv)
##

Weibull survival analysis with MCMC

Description

Survival analysis with weibull distribution by MCMC

Usage

survweibMC(m1, n1, m2, n2, chains, iter, data)

Arguments

m1

Starting column number from where variables of high dimensional data will be selected.
n1

Ending column number till where variables of high dimensional data will get selected.
m2

Starting column number from where demographic observations starts
n2

Ending column number of the demographic observations
chains

Number of MCMC chains
iter

Number of MCMC iterations
data

High dimensional data having survival duration as (OS), event information as Death (1 if died, or 0 if alive).

Value

beta1[1] Posterior estimates of regression coefficients and deviance

Author(s)

Atanu Bhattacharjee and Akash Pawar

References

Kumar, M., Sonker, P. K., Saroj, A., Jain, A., Bhattacharjee, A., & Saroj, R. K. (2020). Parametric survival analysis using R: Illustration with lung cancer data. Cancer Reports, 3(4), e1210.

Khan, S. A. (2018). Exponentiated Weibull regression for time-to-event data. Lifetime data analysis, 24(2), 328-354.

See Also

survexpMC

Examples

##
data(headnneck)
survweibMC(m1=8,n1=12,m2=4,n2=7,chains=2,iter=10,data=headnneck)
##