Dynamic capacity planning of hospital resources under COVID-19 uncertainty using approximate dynamic programming

COVID-19 pandemic has resulted in an inflow of patients into the hospitals and overcrowding of healthcare resources. Healthcare managers increased the capacities reactively by utilizing expensive but quick methods. Instead of this reactive capacity expansion approach, we propose a proactive approach considering different realizations of demand uncertainties in the future due to COVID-19. For this purpose, a stochastic and dynamic model is developed to find the right amount of capacity increase in the most critical hospital resources. Due to the problem size, the model is solved with Approximate Dynamic Programming. Based on the data collected in a large tertiary hospital in Turkey, the experiments show that ADP performs better than a benchmark myopic heuristic. Finally, sensitivity analysis is performed to explore the impact of different epidemic dynamics and cost parameters on the results.

Automated summary

The COVID-19 pandemic has caused hospitals to be flooded with patients, leading to overcrowding of healthcare resources. Instead of reactively expanding capacities, a proactive approach is proposed to address future uncertainties in demand due to COVID-19. A stochastic and dynamic model is developed to determine the appropriate amount of capacity increase in critical hospital resources. Experiments based on data from a large tertiary hospital in Turkey demonstrate that Approximate Dynamic Programming outperforms a benchmark myopic heuristic. Sensitivity analysis is also conducted to examine the impact of different epidemic dynamics and cost parameters on the results.