CPRD Data Encoder

Authors: Sami Adnan
Cited by: 0

Abstract

The RL-CPRD Encoder is an open-source data encoding pipeline that prepares Clinical Practice Research Datalink (CPRD) Aurum extracts and their linked datasets for downstream reinforcement learning experiments evaluating AI/ML clinical prediction models. The project provides high-volume, vectorised data processing pipelines using Polars, outputting optimised Parquet datasets for large-scale healthcare research.

Fields of Study & Subjects

Machine Learning in Healthcare Artificial Intelligence in Healthcare Artificial Intelligence in Healthcare and Education

Publication details

Journal / source
OSF Preprints (OSF Preprints)
Publication date
12 January 2026
Document type
Preprint