Medical Informatics Pipeline for Clinical Trials

This project demonstrates a data transformation pipeline using CDISC (Clinical Data Interchange Standards Consortium) standards for clinical research.

It uses synthetic patient data from an Acquired Immunodeficiency Syndrome (AIDS) clinical trial dataset obtained from Kaggle.

Objectives

The main objective is to transform the raw dataset into the CDISC standard formats, following these steps:

  1. SDTM (Study Data Tabulation Model) – defines a standard structure and naming convention for clinical trial data, ensuring consistency and regulatory compliance.
  2. ADaM (Analysis Data Model) – provides datasets derived from SDTM, optimized for statistical analysis and reproducibility of results.
  3. TLGs (Tables, Listings, and Graphs) – the outputs (tables, patient listings, and graphical summaries) generated from ADaM datasets, used for clinical trial reporting and regulatory submissions.
Warning

⚠️ Disclaimer: This repository is intended for educational and academic use only. Synthetic data was obtained at open source and does not represent real patient data.