Pharmaceutical Demand Forecasting via GCN-LSTM: A Knowledge Graph-Based Approach

Accurate pharmaceutical demand forecasting is essential to ensure timely drug availabil-ity, minimize waste, and enhance the sustainability of healthcare supply chains. However, existing statistical, machine learning, and deep learning approaches often struggle to capture the nonlinear and dynamic demand patterns arising from drug substitutions, comorbidity treatments, and seasonal disease fluctuations. To address this challenge, we propose KG-GCN-LSTM, a novel hybrid model that integrates a pharmaceutical knowledge graph (KG) with deep learning techniques. The knowledge graph encodes se-mantic relationships among drugs and symptoms, thereby enriching the contextual in-formation for a Graph Convolutional Network (GCN). The outputs of the GCN are subse-quently processed by a Long Short-Term Memory (LSTM) network to capture temporal dynamics in drug demand. Experiments on real-world pharmacy sales data demonstrate that KG-GCN-LSTM consistently outperforms established benchmarks—including ARI-MA, SVR, XGBoost, RNN, CNN-LSTM, and NBEATS, achieving a 3.62% reduction in Symmetric Mean Absolute Percentage Error (SMAPE) relative to NBEATS. These findings underscore the potential of knowledge graph–enhanced deep learning in fostering resili-ent and sustainable pharmaceutical supply chains, thereby improving resource allocation, mitigating shortages, and ultimately enhancing public health outcomes.