LEVERAGING DATA ANALYTICS AND LSTM MODELS FOR PREDICTIVE MANAGEMENT IN HOSPITALS

Current hospital management struggles to adapt to fluctuating patient volumes, leading to inefficiencies and crowding. Traditional paper or spreadsheet-based methods lack real-time responsiveness. This research proposes a novel approach utilizing data analytics and prediction using long short-term memory models to modernize medical processes and optimize patient experience. The study aims to develop a data-driven system that aggregates and visualizes information on patient numbers, medical visits, and clinic status. A data warehouse information system was built by leveraging large datasets from Tien Giang Provincial General Hospital (Vietnam). Data analytics tools and long shortterm memory models were then employed to analyze trends and predict future patient volumes and disease patterns. This system offers several advantages: improved scheduling, regulated patient flow, optimized resource allocation, and a more convenient and efficient medical experience. It not only empowers managers with realtime insights and predictive capabilities but also paves the way for broader applications of data analytics and prediction models in healthcare management.