Collation Tube Utilization Prediction in Central Fill Pharmacy through Discrete Markov Chains

Recently, the pharmaceutical industry has realized the importance of reliable automated robots for improving operational efficiency. Embracing these advanced technologies, the Central Fill Pharmacy (CFP) has become a notable trend, addressing workforce shortages, managing rising prescription demands, and achieving heightened levels of efficiency. Among the various types of automated robots utilized in the CFP, collation stations are crucial for assembling orders from auto-dispensing robots. Each order is highly customized, necessitating collation in different tubes before packing. A fully occupied collation tube triggers a system block, making it essential to accurately predict the number of orders stored in these stations. Monitoring collation tube utilization emerges as a key factor in maintaining operational efficiency. To achieve this, the present study uses a Discrete Markov Chain (DMC) approach to predict collation tube utilization in the CFP, focusing on estimating changes in tube usage and forecasting the utilization in subsequent states. By analyzing historical data, a transition probability matrix is derived as a fundamental component of the prediction model. The accuracy of these predictions is evaluated by comparing them with simulation results, providing valuable insights and validating the model's performance. These research findings significantly enhance understanding of collation tube utilization patterns, offering invaluable insights for establishing tube release rules at collation stations within the CFP.