A novel data-driven patient and medical waste queueing-inventory system under pandemic: a real-life case study

It is necessary to control patient congestion in medical centers during pandemics where medical demand grows rapidly. Also, managing generated medical waste is critical since pandemic waste can be a source of disease spread. Although some researchers have studied healthcare optimization in medical systems, there is still a lack of models simultaneously managing congestion in medical centers integrated with waste management using a new application of queueing systems. The model is also the first to use a data-driven method to develop a mathematical model of healthcare and waste management. To fill these gaps, this paper develops a multi-shift mathematical model to manage the congestion in the medical center and medical waste during the pandemic. To this aim, patients are categorized using machine learning algorithms at first. Then, the number of outpatients and inpatients, as well as medical waste, is modeled as a Markovian healthcare waste queueing-inventory system (HWQIS) using a bulk service queueing model. A case study based on the Covid-19 pandemic is applied after the model has been validated using twelve test problems. By determining the optimal size of waste packages, vehicle capacity, and the number of servers, we minimized the patients waiting time and reduced waste accumulation.