Predicting Global Healthcare Supply Chain Delays: A Machine Learning Approach Leveraging Country-level Logistics Metrics

In global healthcare logistics, ensuring the timely delivery of medical commodities is critical, particularly in low- and middle-income countries characterized by infrastructural limitations and operational uncertainties. This research introduces an advanced, data-driven predictive framework designed to forecast delivery delays by synthesizing granular, internal shipment-level data from the USAID Global Health Supply Chain Program (GHSC-PSM) with external country-level logistics capabilities indicators derived from the World Bank’s Logistics Performance Index (LPI). Rather than relying on retrospective trend analyses, this study employs machine learning algorithms such as Random Forest, XGBoost, Support Vector Machines (SVM), and Multi-Layer Perceptron (MLP) to detect shipment delays proactively. A distinctive methodological innovation lies in explicitly integrating country logistics capabilities such as customs efficiency, infrastructure quality, and timeliness with internal shipment metadata, enabling a more comprehensive and precise prediction of delays. Empirical validation demonstrates that this integrative approach significantly enhances predictive performance, revealing systemic inefficiencies and enabling targeted managerial interventions. Consequently, logistics managers can leverage these insights to strategically optimize healthcare logistics and supply chains. This study contributes to a rigorously validated and scalable predictive tool, facilitating a strategic shift from reactive to anticipatory logistics management within global health supply chains.