Year: 2025
Type: article
Abstract: Staffing shortages, inefficient resource allocation, and inflexible scheduling systems are among workforce challenges across different healthcare systems. To address these pressing issues, the current study presents a novel optimization model that integrates gig workers with traditional full-time staff. The developed model is a multi-objective mathematical model that simultaneously minimises labour costs, maximises workforce coverage, and reduces scheduling disruptions while adhering to operational constraints. Data was collected from a healthcare system in the US. Based on the data collected, this study conducted a comparative analysis of metaheuristic algorithms. The results obtained showed that the genetic algorithm (GA) outperforms simulated annealing and differential evolution. GA achieved a 16.7% reduction in penalty costs and an optimal total objective value of $1,010,800. Using GA as a solution method for the developed model, the results obtained showed that a balanced workforce composition (51.5% gig workers at $200/hour and 48.5% full-time staff at $250/hour) yields a cost-efficient average of $224.27/hour. The analysis of role-specific results revealed that physicians achieved 94% shift coverage satisfaction, while support staff exhibited higher variability (25% understaffed shifts). The model also identifies critical gaps, for instance, there was a 33% uncovered physician shifts during peak afternoon demand. This study contributes a data-driven, scalable solution for healthcare administrators to harness the gig economy's flexibility while mitigating its ethical and operational risks. Hence, the developed model offers a transformative approach to workforce planning in resource-constrained environments.
Authors: Ighravwe, Desmond Eseoghene, Ibikunle, Olumide Emmanuel, Oloko, Omodunni Adejoke, Adefolaju, Ifeloluwa Marcus
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W7082274298
FWCI:
Cites:
Cited by:
Related to: