The HADES PROJECT and The OHDSI (Odyssey) Consortium
Health-Analytics Data to Evidence Suite (HADES): Open-Source Software for Observational Research
HADES, an R package suite, leverages the globally adopted OMOP CDM for analyzing healthcare data. It transforms CDM data into diagnostics, statistics, and visuals, shaping clinical decisions. Researchers worldwide have utilized HADES in impactful studies, w/ open-source code for reproducibility. HADES’ liberal Apache v2.0 license fosters flexibility for collaboration, modification, & sharing. Designed for federated networks, HADES prioritizes privacy by localizing data & sharing analytics.
pmc.ncbi.nlm.nih.gov/article…
Access HADES at:
ohdsi.github.io/Hades/
sparklyr:R Interface to Apache Spark
R interface to Apache Spark, a fast & general engine for big data processing, see <
spark.apache.org/>. This package supports connecting to local & remote Apache Spark clusters, provides a 'dplyr' compatible back-end, & provides an interface to Spark's built-in machine learning algorithms.
sparklyr.r-universe.dev/spar…
R interface for Apache Spark
spark.posit.co/
Hydra
An R package and Java library for hydrating package skeletons into executable R study packages based on specifications in JSON format.
ohdsi.github.io/Hydra/
AsynchroNous Disk-based Representation of MassivE DAta (ANDROMEDA)
Storing very large data objects on a local drive, while still making it possible to manipulate the data in an efficient manner.
ohdsi.github.io/Andromeda/
Cyclops (Cyclic coordinate descent for logistic, Poisson & survival analysis)
An R package for performing large scale regularized regressions.
ohdsi.github.io/Cyclops/
BigKnn
An R package implementing a large scale k-nearest neighbor (KNN) classifier using the Lucene search engine.
ohdsi.github.io/BigKnn/
Apache Lucene
Lucene Core
Lucene Core is a Java library providing powerful indexing & search features, as well as spellchecking, hit highlighting & advanced analysis/tokenization capabilities. The PyLucene sub project provides Python bindings for Lucene Core.
lucene.apache.org/
PyLucene
PyLucene is a Python extension for accessing Java Lucene™. Its goal is to allow you to use Lucene's text indexing & searching capabilities from Python. PyLucene is not a Lucene port but a Python wrapper around Java Lucene. PyLucene embeds a Java VM w/ Lucene into a Python process. The PyLucene Python extension, a Python module called lucene is machine-generated by JCC.
PyLucene is built with JCC, a C code generator that makes it possible to call into Java classes from Python via Java's Native Invocation Interface (JNI). Sources for JCC are included w/ the PyLucene sources.
lucene.apache.org/pylucene/
lucene.apache.org/pylucene/f…
Automated Characterization of Health Information at Large-Scale Longitudinal Evidence Systems (ACHILLES) Achilles provides descriptive statistics on an OMOP CDM database.
Performs broad database characterizationExport feature for ARES
ohdsi.github.io/Achilles/
A Research Exploration System (ARES)
ohdsi.github.io/Ares/
github.com/OHDSI/Ares
FeaturesExtraction
An R package for generating features (covariates) for a cohort using data in the Common Data Model.
ohdsi.github.io/FeatureExtra…
OMOP CDM (Common Data Model)
ohdsi.github.io/CommonDataMo…
OMOP CDM v5.4
This is the latest version of the OMOP CDM.
ohdsi.github.io/CommonDataMo…
The cdm reference
A cdm reference is a single R object that represents OMOP CDM data. A cdm reference is a list of tables. These tables come in three types: standard OMOP CDM tables, cohort tables, & other auxiliary tables. The tables in the cdm reference may be in a database, but a cdm reference may also contain OMOP CDM tables that are in dataframes or tibbles, or in arrow.
cloud.r-project.org/web/pack…
CDMConnector 2.0.0
CDMConnector is meant to be the entry point for composable tidyverse
tidyverse.org/ style data analysis operations on an OMOP CDM.
darwin-eu.github.io/CDMConne…