Clinical Trial Candidate Selection

This project focuses on the clustering and outlier analysis of clinical trial data to identify high-precision patient candidate pools. By leveraging R and various machine learning techniques, the analysis aims to improve trial outcomes by uncovering hidden patterns in patient demographics, baseline characteristics, and treatment responses.

This project was developed as an academic case study to explore the application of advanced analytics within clinical research. The goal was to simulate a real-world data environment to demonstrate how data modeling can enhance trial design and patient selection.