Packages

Below are the packages included in HADES. For each package a link is provided with more information, including instructions on how to install and use the package.

Population-level estimation

• CohortMethod

  New-user cohort studies using large-scale regression for propensity and outcome models.
  Learn more…

• SelfControlledCaseSeries

  Self-Controlled Case Series analysis using few or many predictors, includes splines for age and seasonality.
  Learn more…

• SelfControlledCohort

  A self-controlled cohort design, where time preceding exposure is used as control.
  Learn more…

• EvidenceSynthesis

  Routines for combining causal effect estimates and study diagnostics across multiple data sites in a distributed study.
  Learn more…

Patient-level prediction

• PatientLevelPrediction

  Build and evaluate predictive models for user-specified outcomes, using a wide array of machine learning algorithms.
  Learn more…

• DeepPatientLevelPrediction

  Performing patient level prediction using deep learning
  Learn more…

• EnsemblePatientLevelPrediction

  Building and validating ensemble patient-level predictive models.
  Learn more…

Characterization

• Characterization

  Various types of characterizations of a target and outcome cohort.
  Learn more…

Cohort construction and evaluation

• Capr

  Develop and manipulate complex cohort definitions in R
  Learn more…

• CirceR

  An R wrapper for Circe, a library for creating cohort definitions, expressing them as JSON, SQL, or Markdown.
  Learn more…

• CohortGenerator

  Instantiating cohorts in a database based on a set of cohort definitions.
  Learn more…

• PhenotypeLibrary

  The OHDSI Phenotype Library: a collection of community-maintained pre-definined cohorts.
  Learn more…

• CohortDiagnostics

  Generate a wide set of diagnostics to evaluate cohort definitions against databases in the CDM.
  Learn more…

• PheValuator

  Semi-automated evaluation of cohorts, producing metrics suchs as sensitivity, specificity, and positive and negative preditive value.
  Learn more…

• CohortExplorer

  Visually explore all individual-level data of patients in a cohort
  Learn more…

Evidence Quality

• DataQualityDashboard

  Expose and evaluate observational data quality.
  Learn more…

• EmpiricalCalibration

  Use negative control exposure-outcome pairs to profile and calibrate a particular analysis design.
  Learn more…

• MethodEvaluation

  Use real data and established reference sets as well as simulations injected in real data to evaluate the performance of methods.
  Learn more…

Supporting packages

• Andromeda

  Storing very large data objects on a local drive, while still making it possible to manipulate the data in an efficient manner.
  Learn more…

• BigKnn

  A large scale k-nearest neighbor classifier using the Lucene search engine.
  Learn more…

• Cyclops

  Highly efficient implementation of regularized logistic, Poisson and Cox regression.
  Learn more…

• DatabaseConnector

  Connect directly to a wide range of database platforms, including SQL Server, Oracle, and PostgreSQL.
  Learn more…

• Eunomia

  A standard CDM dataset for testing and demonstration purposes that runs on an embedded SQLite database.
  Learn more…

• FeatureExtraction

  Automatically extract large sets of features for user-specified cohorts using data in the CDM.
  Learn more…

• Hydra

  Hydrating package skeletons into executable R study packages based on specifications in JSON format.
  Learn more…

• IterativeHardThresholding

  Performing L0-based regressions using Cyclops
  Learn more…

• OhdsiSharing

  Securely sharing (large) files between OHDSI collaborators.
  Learn more…

• OhdsiShinyModules

  Contains shiny modules that can be used within shiny result interfaces
  Learn more…

• ParallelLogger

  Support for parallel computation with logging to console, disk, or e-mail.
  Learn more…

• ResultModelManager

  A lightweight utility for data migrations allowing old results to work with new shiny apps and data visualisations.
  Learn more…

• ROhdsiWebApi

  Interact with OHDSI WebAPI web services.
  Learn more…

• ShinyAppBuilder

  Interactively view analysis results across different types of analyses.
  Learn more…

• SqlRender

  Generate SQL on the fly for the various SQL dialects.
  Learn more…