Recently, pharmaceutical companies have made concerted efforts to expand their presence in the global market by actively engaging in clinical research through collaborative networks. Considering the notable demand for the treatment of chronic diseases...
Recently, pharmaceutical companies have made concerted efforts to expand their presence in the global market by actively engaging in clinical research through collaborative networks. Considering the notable demand for the treatment of chronic diseases, there is a clear imperative to prioritize the exploration of suitable affiliations and collaboration networks. In order to respond to this trend, we propose iGraphCTC model, an inter-connected Graph Convolutional Network for Clinical Trial Collaborations, with consideration of disease-specific clinical trials, presenting a comprehensive understanding of network dynamics. With the proposed model, we attempt to identify viable collaborations in the domain of chronic disease clinical trials. Based on both geographical and intervention datasets, iGraphCTC outperforms existing basic graph models by achieving maximum improvements of 16.08%p (AUC), 14.28%p (F1-Score), and 6.68-17.44%p (Accuracy@K). Based on the results, we present the effectiveness of graph-oriented approaches in finding collaborative activities and pinpointing potential collaborators, examining valuable insights into the dynamics of the pharmaceutical industry's collaborative landscape.