Internet of things-enabled fuzzy goal programming for healthcare resource allocation

Abstract

Resource allocation of medical services under uncertainty (from COVID-19) is crucial for resilient healthcare service provision during pandemics, emergency surges and resource shortages. In this study, an internet of things (IoT)-assisted fuzzy goal programming (FGP) framework is developed for the allocation of healthcare resources in a network of five regional hospitals. The considered model combines fuzzy aspiration levels and priority weights with operational constraints to simultaneously optimize the portion of patients served, the overall resource utilization and the total cost-these three conflicting objectives all related to intensive care unit (ICU) beds, ventilators, and medical staff. It is modeled using mixed-integer linear programming (MILP) model and solved through LINGO and Python. Experimental results demonstrate that the proposed FGP framework outperforms classical linear programming (LP), enabling expanding patient service coverage from 83.4% to 93.7%, while improving healthcare resource allocation regarding crack utilization of critical healthcare resources. Sensitivity analysis under low, moderate and high uncertainty levels also indicates that the model remains above 90% coverage regardless of demand side and supply shocks. These results illustrate that the proposed framework represents a flexible, resilient and adaptive decision-support framework for healthcare resource allocation under uncertain operational contexts.