EnsemblePatientLevelPrediction is part of HADES.

Introduction

EnsemblePatientLevelPrediction is an R package for building and validating ensemble patient-level predictive models using data in the OMOP Common Data Model format. The package expands the OHDSI R PatientLevelPrediction package to enable ensemble learning.

In our study here we found that combining models developed using different databases resulted in models that had better discrimination performance compared to the level 1 models (single database) when transported to new data. However, calibration was poor. This has prompted the EnsemblePatientLevelPrediction package where users can combine models developed on the same database or models developed on different databases.

User Documentation

Vignette: EnsemblePatientLevelPrediction

Website: Documentation can be found on the package website.

Package manual: EnsemblePatientLevelPrediction

Support

• Developer questions/comments/feedback: OHDSI Forum
• We use the GitHub issue tracker for all bugs/issues/enhancements

Contributing

Read here how you can contribute to this package.

License

EnsemblePatientLevelPrediction is licensed under Apache License 2.0

Development

EnsemblePatientLevelPrediction is being developed in R Studio.

Beta

Acknowledgements

• The package is maintained by Jenna Reps