In ohdsi-studies/DistributedLMM: Predicting Length of Hopsital Stay for COVID-19
```r
library(PatientLevelPrediction)
knitr::opts_chunk$set(
cache=FALSE,
comment = "#>",
error = FALSE,
tidy = FALSE)
# Introduction
This vignette describes how one can populate the SkeletonExistingModelStudy pacakge with the target cohort, outcome cohorts and model settings.
First make sure to open the Skeleton R project in R studio, this can be done by finding the SkeletonExistingModelStudy.Rproj file in the folder. Once the package project is opened in R studio there are 3 steps that must be followed:
1. Run the function: populatePackage (found in extras/populatePackage.R on line 51) to add all cohorts and settings into the study package
2. Build the study package
3. Run the study package execute function
## Step 1: Populate skeleton settings
All the settings can be added to the study package by using the function 'populatePackage()' that is found in extras/populatePackage.R.
To add the function to your environment, make sure the package R project is open in R studio and run:
```r
source('./extras/populatePackage.R')
This will make the function 'populatePackage()'available to use within your R session.
The 'populatePackage()' function requires users to specify:
- targetCohortId - The ATLAS id for the target cohort
- targetCohortName - A string with a sharable name for the target cohort
- outcomeId - The ATLAS id for the outcome cohort
- outcomeName - A string with a sharable name for the outcome cohort
- standardCovariates - A data.frame with the columns: covariateId (for standard fetures using FeatureExtraction), covariateName and points to assign points for standard covariates
- baseUrl - The url for the ATLAS webapi (this will be used to extract the ATLAS cohorts)
- atlasIds - an integer or vector of integers specifying the atlas cohort Ids that are used by the custom cohort covariates
- atlasNames - a string or vector of strings specifying the names of the atlas ids (must be the same length as atlasIds)
- startDays - a negative integer or vector of negative integers specifying the days relative to index to start looking for the patient being in the covariate cohort
- endDays - a negative integer (or zero) or vector of negative integers (or zero) specifying the days relative to index to stop looking for the patient being in the covariate cohort
- points - a double or vector of doubles specifying the points corresponding to each variable
For example, to create two custom cohort covariates into the package I can run:
populatePackage(targetCohortId = 10845,
targetCohortName = 'neg mamo',
outcomeId = 10082,
outcomeName = 'breast cancer',
standardCovariates = data.frame(covariateId = c(0003, 1003,
2003, 3003,
4003, 5003,
6003, 7003,
8003, 9003,
10003, 11003,
12003, 13003,
14003, 15003,
16003, 17003,
8507001),
covariateName = c('Age 0-4', 'Age 5-9',
'Age 10-14', 'Age 15-19',
'Age 20-24', 'Age 25-30',
'Age 30-34', 'Age 35-40',
'Age 40-44', 'Age 45-50',
'Age 50-54', 'Age 55-60',
'Age 60-64', 'Age 65-70',
'Age 70-74', 'Age 75-80',
'Age 80-84', 'Age 85-90',
'Male'),
points = c(rep(0,19))),
baseUrl = 'https://yourWebAPI',
atlasCovariateIds = c(14709,14709, 14710),
atlasCovariateNames = c('smoking anytime', 'smoking recent', 'traumatic brain injury'),
startDays = c(-999,-30,-999),
endDays = c(0,0,0),
points = c(1,2,1))
The code above extracts the target and outcome cohorts and two ATLAS cohort (14709, 14710) to create three covariates:
- covariate 1: The ATLAS cohort with the id of 14709 named 'smoking anytime' looks for patients who have a smoking anytime cohort_start_date between (index date-999 days) and (index date). E.g., If a patient is in the smoking anytime cohort 50 days before the index date then they will have a value of 1 for the custom covariate. If they are not in the smoking anytime cohort between 999 days before index and the day of index then they will have a value of 0 for the custom covariate.
- covariate 2: The ATLAS cohort with the id of 14709 named 'smoking recent' looks for patients who have a smoking recent cohort_start_date between (index date-30 days) and (index date). E.g., If a patient is in the smoking recent cohort 20 days before the index date then they will have a value of 1 for the custom covariate. If they are not in the smoking recent cohort between 30 days before index and the day of index then they will have a value of 0 for the custom covariate.
- covariate 3: The ATLAS cohort with the id of 14710 named 'traumatic brain injury' looks for patients who have a traumatic brain injury cohort_start_date between (index date-999 days) and (index date). E.g., If a patient is in the traumatic brain injury cohort 200 days before the index date then they will have a value of 1 for the custom covariate. If they are not in the traumatic brain injury cohort before index then they will have a value of 0 for the custom covariate.
It also creates three csv files in the inst/settings directory named:
- CohortsToCreate.csv - specifying the target and outcome cohorts
- CustomCovariates.csv - specifying the custom covariates
- SimpleModel.csv - settings specifying the simple prediction model
Step 2: Build the study package
Aftering adding the settings into the package, you now need to build the package. Use the standard process (in R studio press the 'Build' tab in the top right corner and then select the 'Install and Restart' button) to build the study package so an R library is created.
Step 3: Execute the study to validate an existing model
library(SkeletonExistingPredictionModelStudy)
options(fftempdir = "location with space to save big data")
# The folder where the study intermediate and result files will be written:
outputFolder <- "./SkeletonExistingPredictionModelStudyResults"
# Details for connecting to the server:
dbms <- "you dbms"
user <- 'your username'
pw <- 'your password'
server <- 'your server'
port <- 'your port'
connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = dbms,
server = server,
user = user,
password = pw,
port = port)
# Add the database containing the OMOP CDM data
cdmDatabaseSchema <- 'cdm database schema'
# Add a database with read/write access as this is where the cohorts will be generated
cohortDatabaseSchema <- 'work database schema'
oracleTempSchema <- NULL
# table name where the cohorts will be generated
cohortTable <- 'SkeletonExistingPredictionModelStudyCohort'
# TAR settings
sampleSize <- NULL
riskWindowStart <- 1
startAnchor <- 'cohort start'
riskWindowEnd <- 365
endAnchor <- 'cohort start'
firstExposureOnly <- F
removeSubjectsWithPriorOutcome <- F
priorOutcomeLookback <- 99999
requireTimeAtRisk <- F
minTimeAtRisk <- 1
includeAllOutcomes <- T
#=======================
standardCovariates <- FeatureExtraction::createCovariateSettings(useDemographicsAgeGroup = T, useDemographicsGender = T)
SkeletonExistingPredictionModelStudy::execute(connectionDetails = connectionDetails,
cdmDatabaseSchema = cdmDatabaseSchema,
cdmDatabaseName = cdmDatabaseName,
cohortDatabaseSchema = cohortDatabaseSchema,
cohortTable = cohortTable,
sampleSize = sampleSize,
riskWindowStart = riskWindowStart,
startAnchor = startAnchor,
riskWindowEnd = riskWindowEnd,
endAnchor = endAnchor,
firstExposureOnly = firstExposureOnly,
removeSubjectsWithPriorOutcome = removeSubjectsWithPriorOutcome,
priorOutcomeLookback = priorOutcomeLookback,
requireTimeAtRisk = requireTimeAtRisk,
minTimeAtRisk = minTimeAtRisk,
includeAllOutcomes = includeAllOutcomes,
standardCovariates = standardCovariates,
outputFolder = outputFolder,
createCohorts = T,
runAnalyses = T,
viewShiny = T,
packageResults = F,
minCellCount= 5,
verbosity = "INFO",
cdmVersion = 5)
)
ohdsi-studies/DistributedLMM documentation built on June 19, 2021, 1:12 p.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.
```r library(PatientLevelPrediction) knitr::opts_chunk$set( cache=FALSE, comment = "#>", error = FALSE, tidy = FALSE)
# Introduction
This vignette describes how one can populate the SkeletonExistingModelStudy pacakge with the target cohort, outcome cohorts and model settings.
First make sure to open the Skeleton R project in R studio, this can be done by finding the SkeletonExistingModelStudy.Rproj file in the folder. Once the package project is opened in R studio there are 3 steps that must be followed:
1. Run the function: populatePackage (found in extras/populatePackage.R on line 51) to add all cohorts and settings into the study package
2. Build the study package
3. Run the study package execute function
## Step 1: Populate skeleton settings
All the settings can be added to the study package by using the function 'populatePackage()' that is found in extras/populatePackage.R.
To add the function to your environment, make sure the package R project is open in R studio and run:
```r
source('./extras/populatePackage.R')
This will make the function 'populatePackage()'available to use within your R session.
The 'populatePackage()' function requires users to specify:
- targetCohortId - The ATLAS id for the target cohort
- targetCohortName - A string with a sharable name for the target cohort
- outcomeId - The ATLAS id for the outcome cohort
- outcomeName - A string with a sharable name for the outcome cohort
- standardCovariates - A data.frame with the columns: covariateId (for standard fetures using FeatureExtraction), covariateName and points to assign points for standard covariates
- baseUrl - The url for the ATLAS webapi (this will be used to extract the ATLAS cohorts)
- atlasIds - an integer or vector of integers specifying the atlas cohort Ids that are used by the custom cohort covariates
- atlasNames - a string or vector of strings specifying the names of the atlas ids (must be the same length as atlasIds)
- startDays - a negative integer or vector of negative integers specifying the days relative to index to start looking for the patient being in the covariate cohort
- endDays - a negative integer (or zero) or vector of negative integers (or zero) specifying the days relative to index to stop looking for the patient being in the covariate cohort
- points - a double or vector of doubles specifying the points corresponding to each variable
For example, to create two custom cohort covariates into the package I can run:
populatePackage(targetCohortId = 10845, targetCohortName = 'neg mamo', outcomeId = 10082, outcomeName = 'breast cancer', standardCovariates = data.frame(covariateId = c(0003, 1003, 2003, 3003, 4003, 5003, 6003, 7003, 8003, 9003, 10003, 11003, 12003, 13003, 14003, 15003, 16003, 17003, 8507001), covariateName = c('Age 0-4', 'Age 5-9', 'Age 10-14', 'Age 15-19', 'Age 20-24', 'Age 25-30', 'Age 30-34', 'Age 35-40', 'Age 40-44', 'Age 45-50', 'Age 50-54', 'Age 55-60', 'Age 60-64', 'Age 65-70', 'Age 70-74', 'Age 75-80', 'Age 80-84', 'Age 85-90', 'Male'), points = c(rep(0,19))), baseUrl = 'https://yourWebAPI', atlasCovariateIds = c(14709,14709, 14710), atlasCovariateNames = c('smoking anytime', 'smoking recent', 'traumatic brain injury'), startDays = c(-999,-30,-999), endDays = c(0,0,0), points = c(1,2,1))
The code above extracts the target and outcome cohorts and two ATLAS cohort (14709, 14710) to create three covariates:
- covariate 1: The ATLAS cohort with the id of 14709 named 'smoking anytime' looks for patients who have a smoking anytime cohort_start_date between (index date-999 days) and (index date). E.g., If a patient is in the smoking anytime cohort 50 days before the index date then they will have a value of 1 for the custom covariate. If they are not in the smoking anytime cohort between 999 days before index and the day of index then they will have a value of 0 for the custom covariate.
- covariate 2: The ATLAS cohort with the id of 14709 named 'smoking recent' looks for patients who have a smoking recent cohort_start_date between (index date-30 days) and (index date). E.g., If a patient is in the smoking recent cohort 20 days before the index date then they will have a value of 1 for the custom covariate. If they are not in the smoking recent cohort between 30 days before index and the day of index then they will have a value of 0 for the custom covariate.
- covariate 3: The ATLAS cohort with the id of 14710 named 'traumatic brain injury' looks for patients who have a traumatic brain injury cohort_start_date between (index date-999 days) and (index date). E.g., If a patient is in the traumatic brain injury cohort 200 days before the index date then they will have a value of 1 for the custom covariate. If they are not in the traumatic brain injury cohort before index then they will have a value of 0 for the custom covariate.
It also creates three csv files in the inst/settings directory named:
- CohortsToCreate.csv - specifying the target and outcome cohorts
- CustomCovariates.csv - specifying the custom covariates
- SimpleModel.csv - settings specifying the simple prediction model
Step 2: Build the study package
Aftering adding the settings into the package, you now need to build the package. Use the standard process (in R studio press the 'Build' tab in the top right corner and then select the 'Install and Restart' button) to build the study package so an R library is created.
Step 3: Execute the study to validate an existing model
library(SkeletonExistingPredictionModelStudy) options(fftempdir = "location with space to save big data") # The folder where the study intermediate and result files will be written: outputFolder <- "./SkeletonExistingPredictionModelStudyResults" # Details for connecting to the server: dbms <- "you dbms" user <- 'your username' pw <- 'your password' server <- 'your server' port <- 'your port' connectionDetails <- DatabaseConnector::createConnectionDetails(dbms = dbms, server = server, user = user, password = pw, port = port) # Add the database containing the OMOP CDM data cdmDatabaseSchema <- 'cdm database schema' # Add a database with read/write access as this is where the cohorts will be generated cohortDatabaseSchema <- 'work database schema' oracleTempSchema <- NULL # table name where the cohorts will be generated cohortTable <- 'SkeletonExistingPredictionModelStudyCohort' # TAR settings sampleSize <- NULL riskWindowStart <- 1 startAnchor <- 'cohort start' riskWindowEnd <- 365 endAnchor <- 'cohort start' firstExposureOnly <- F removeSubjectsWithPriorOutcome <- F priorOutcomeLookback <- 99999 requireTimeAtRisk <- F minTimeAtRisk <- 1 includeAllOutcomes <- T #======================= standardCovariates <- FeatureExtraction::createCovariateSettings(useDemographicsAgeGroup = T, useDemographicsGender = T) SkeletonExistingPredictionModelStudy::execute(connectionDetails = connectionDetails, cdmDatabaseSchema = cdmDatabaseSchema, cdmDatabaseName = cdmDatabaseName, cohortDatabaseSchema = cohortDatabaseSchema, cohortTable = cohortTable, sampleSize = sampleSize, riskWindowStart = riskWindowStart, startAnchor = startAnchor, riskWindowEnd = riskWindowEnd, endAnchor = endAnchor, firstExposureOnly = firstExposureOnly, removeSubjectsWithPriorOutcome = removeSubjectsWithPriorOutcome, priorOutcomeLookback = priorOutcomeLookback, requireTimeAtRisk = requireTimeAtRisk, minTimeAtRisk = minTimeAtRisk, includeAllOutcomes = includeAllOutcomes, standardCovariates = standardCovariates, outputFolder = outputFolder, createCohorts = T, runAnalyses = T, viewShiny = T, packageResults = F, minCellCount= 5, verbosity = "INFO", cdmVersion = 5) )
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.