OHDSI/SelfControlledCaseSeries

Name: SelfControlledCaseSeries

Owner: Observational Health Data Sciences and Informatics

Description: An R package for performing Self-Controlled Case Series (SCCS) analyses in an observational database in the OMOP Common Data Model.

Created: 2014-06-10 20:53:47.0

Updated: 2017-06-22 23:25:42.0

Pushed: 2017-12-13 05:41:04.0

Homepage:

Size: 4933

Language: R

GitHub Committers

User	Most Recent Commit	# Commits
Marc Suchard	2017-05-19 17:30:18.0	30
Martijn Schuemie	2018-03-19 16:43:42.0	109
Jamie Weaver	2017-02-17 22:08:19.0	7
Ajit Londhe	2017-12-12 17:02:15.0	1

Other Committers

User	Email	Most Recent Commit	# Commits
Schuemie	mschuemi@its.jnj.com	2017-10-18 08:54:57.0	5

README

SelfControlledCaseSeries

Introduction

SelfControlledCaseSeries is an R package for performing Self-Controlled Case Series (SCCS) analyses in an observational database in the OMOP Common Data Model.

Features

• Extracts the necessary data from a database in OMOP Common Data Model format.
• Optionally add seasonality using a spline function.
• Optionally add age using a spline function.
• Optionally correct for event-dependent censoring of the observation period.
• Optionally add many covariates in one analysis (e.g. all drugs).
• Options for constructing different types of covariates and risk windows, including pre-exposure windows (to capture contra-indications).
• Optionally use regularization on all covariates except the outcome of interest.

Example

Data <- getDbSccsData(connectionDetails = connectionDetails,
                      cdmDatabaseSchema = cdmDatabaseSchema,
                      outcomeIds = 192671,
                      exposureIds = 1124300)
rDiclofenac = createCovariateSettings(label = "Exposure of interest",
                                      includeCovariateIds = 1124300,
                                      start = 0,
                                      end = 0,
                                      addExposedDaysToEnd = TRUE)
EraData <- createSccsEraData(sccsData,
                             naivePeriod = 180,
                             firstOutcomeOnly = FALSE,
                             covariateSettings = covarDiclofenac)
l <- fitSccsModel(sccsEraData)
ary(model)
csModel object summary

tcome ID: 192671

tcome count:
     Event count Case count
2671      433433     137888

timates:
                            Name    ID  Estimate  lower .95  upper .95   logRr  seLogRr
Exposure of interest: Diclofenac  1000     1.274      1.213      1.336  0.2421  0.02431

Technology

SelfControlledCaseSeries is an R package, with some functions implemented in C++.

System Requirements

Requires R (version 3.2.2 or higher). Installation on Windows requires RTools. Libraries used in SelfControlledCaseSeries require Java.

Dependencies

• Cyclops
• DatabaseConnector
• SqlRender
• OhdsiRTools

Getting Started

1. On Windows, make sure RTools is installed.

2. The DatabaseConnector and SqlRender packages require Java. Java can be downloaded from http://www.java.com.

3. In R, use the following commands to download and install SelfControlledCaseSeries:

   all.packages("devtools")
   ary(devtools)
   all_github("ohdsi/OhdsiRTools") 
   all_github("ohdsi/SqlRender")
   all_github("ohdsi/DatabaseConnector")
   all_github("ohdsi/Cyclops")
   all_github("ohdsi/SelfControlledCaseSeries")
   

Getting Involved

• Vignette: Single studies using the SelfControlledCaseSeries package
• Vignette: Running multiple analyses at once using the SelfControlledCaseSeries package
• Package manual: SelfControlledCaseSeries.pdf
• Developer questions/comments/feedback: OHDSI Forum
• We use the GitHub issue tracker for all bugs/issues/enhancements

License

SelfControlledCaseSeries is licensed under Apache License 2.0

Development

SelfControlledCaseSeries is being developed in R Studio.

Development status

Beta

Acknowledgements

• This project is supported in part through the National Science Foundation grant IIS 1251151.
• Part of the code is based on the SCCS package by Yonas Ghebremichael-Weldeselassie, Heather Whitaker, and Paddy Farrington.