This repository contains data for the paper "An inter-connected Graph Convolutional Network for Comprehensive Clinical Trial Collaborations".
Recently, pharmaceutical companies have actively engaged in clinical research through collaborative networks to expand their presence in the global market. This trend is particularly evident in the field of chronic disease research, where collaborative efforts are essential to improve patient outcomes and advance scientific knowledge. To address this need, we proposed the iGraphCTC model, an interconnected Graph Convolutional Network designed to optimize clinical trial collaborations by identifying viable partners and enhancing network efficiency. By utilizing both geographical and intervention datasets, iGraphCTC demonstrated superior performance compared to existing graph models.
The dataset was collected from ClinicalTrials.gov, one of the largest clinical trial databases globally. It focuses on clinical trials related to two chronic diseases: diabetes and stroke. The data collection period spans from January 2013 to January 2022, ensuring a comprehensive overview of recent clinical trial activities. The dataset includes detailed information on study titles, conditions, interventions, sponsors, collaborators, and locations, which are crucial for constructing the collaboration network.
The exported search result is in a CSV format with seven fields:
- NCT Number
- Study Title
- Conditions
- Interventions
- Sponsor
- Collaborators
- Locations
TBD