Implementing AI for Dynamic Demand Forecasting in Lean Healthcare Logistics: A Case Study Approach

This research aims at establishing the contribution of AI in improving dynamic demand forecasting in lean healthcare logistics. Using a case study approach, the paper explores the effectiveness of adopting the AI-based advanced models such as LSTM in forecasting the demand for health care and distinguishing it from other models such as ARIMA. The results of the work indicate that compared to other methods, application of AI-based models radically improves the accuracy of the forecasts with predetermined variables, while LSTM shows a nuance RMSE value which is 31% less than ARIMA. Also, the study links intended AI-based forecasting to lean concepts, as well as the elimination of current waste and timely replenishment of stock based on real-time demand changes. However, this study also reveals barriers concerning data quality, the issues of recalibration, and the issue of integrating such systems with the traditional models of working healthcare logistics systems. H2 is that this paper elucidates the practical solutions for using AI in the healthcare logistics and provides the healthcare organizations with the strategic directions of AI application in demand forecasting for sustainable improvement in the organization’s performance. Thus, the results have outlined the applicability of AI in enhancing the logistics of the healthcare sector, but at the same time have highlighted the continuous process of change and development to meet the changes in the healthcare sector.