DeepPatientLevelPrediction

Introduction

DeepPatientLevelPrediction is an R package for building and validating deep learning patient-level predictive models using data in the OMOP Common Data Model format and OHDSI PatientLevelPrediction framework.

Reps JM, Schuemie MJ, Suchard MA, Ryan PB, Rijnbeek PR. Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data. J Am Med Inform Assoc. 2018;25(8):969-975.

Features

• Adds deep learning models to use in the OHDSI PatientLevelPrediction framework.
• Allows to add custom deep learning models.
• Includes an MLP, ResNet, Transformer, and core RealMLP
• Allows to use all the features of PatientLevelPrediction to validate and explore your model performance.

Technology

DeepPatientLevelPrediction is an R package. It uses Python PyTorch through reticulate for deep learning model training and inference.

System Requirements

Requires R (version 4.0.0 or higher). Installation on Windows requires RTools. For training deep learning models in most cases an nvidia GPU is required using either Windows or Linux.

Getting Started

• To install the package please read the Package installation guide
• For Python, the recommended environment manager is uv with Python 3.12
• Please read the main vignette for the package: Building Deep Learning Models

User Documentation

Documentation can be found on the package website.

PDF versions of the documentation are also available, as mentioned above.

Support

• Developer questions/comments/feedback: <a href="http://forums.ohdsi.org/c/developers">OHDSI Forum</a>
• We use the <a href="https://github.com/OHDSI/DeepPatientLevelPrediction/issues">GitHub issue tracker</a> for all bugs/issues/enhancements

Contributing

Read here how you can contribute to this package.

License

DeepPatientLevelPrediction is licensed under Apache License 2.0

Development

DeepPatientLevelPrediction is being developed in R Studio.