An analysis utilizing the TSSP model to forecast consumption and surgical supply stocks

The healthcare industry is one of the many diverse businesses that depend on a functional supply chain. Demand forecasting and inventory control are essential components of supply chain management in the healthcare industry to ensure optimal patient outcomes, minimise costs, and minimise waste. The development of data analytics and technology has made it feasible to use several sophisticated techniques for demand forecasting and inventory control. This project aims to use these improvements to accurately estimate demand and regulate the surgical supply inventory, therefore reducing costs and improving patient care. To forecast medical caseloads and supplies for certain operations, an LSTM model grounded in literature is employed. In order to account for COVID-19-related variability in surgical case volumes in 2020, new characteristics have been added to the accepted model. The paper builds a dynamic replenishment model for various goods using Mixed Integer Programming (MIP). In the actual world, demand is rarely predetermined, and forecasting is usually erroneous. We created a Two-Stage Stochastic Programming (TSSP) paradigm in order to deal with these problems.