Treffer: Application of Mixed-Integer Linear Programming for Optimal Allocation of Quality Analysts in Hospital Safety Programs Using Python.

This study presents the development of a Mixed Integer Linear Programming (MILP) model to optimize the allocation of quality analysts across hospital units in a vertically integrated healthcare system. The model incorporates geographic proximity and unit criticality to construct a weighted cost matrix, combining Euclidean distance with a normalized criticality index derived from institutional safety indicators. Implemented in Python and solved using the CBC (COIN-OR Branch and Cut) solver within Google Colab, the model ensures accessibility, reproducibility, and computational robustness. The optimization respected all institutional constraints, including exclusive assignment of high-criticality units, workload limits, and full allocation of available analysts—the use of the median criticality score as a classification threshold allowed for balanced, data-driven decision-making. The resulting allocation was cost-effective, equitable, and strategically aligned with patient safety priorities. By integrating mathematical modeling and open-source technologies, the proposed method supports evidence-based decision-making, strengthens institutional governance, and promotes safer and more resilient healthcare operations through the strategic deployment of qualified human resources. [ABSTRACT FROM AUTHOR]