Improved Heuristic Algorithm and Optimal Incremental Learning for Dashboard Visualization and Healthcare Data Analysis on COVID Outbreaks

The COVID-19 pandemic has exposed significant shortcomings in healthcare data accessibility, integration, and real-time analysis. For addressing these challenges, this paper presents a novel framework that combines intelligent dashboard visualization with an optimized incremental learning approach for efficient healthcare data analysis. The proposed model consists of three core components. First, heterogeneous raw data from various hospitals is continuously collected and preprocessed to feed into a unified, interactive dashboard that enables healthcare professionals to monitor demographic trends, outbreak patterns, and predictive analytics in real time. Second, an incremental learning-based recurrent neural network (ILRNN) is developed to perform time-series analysis and continuously adapt to new data without retraining on the entire dataset. Third, to optimize learning efficiency and accuracy, a revamped fitness-based coati optimization algorithm (RF-COA) is introduced, which fine-tunes network parameters by balancing exploration and exploitation in the learning process. Comparative experiments demonstrate the superiority of the proposed ILRNN-RF-COA model in terms of accuracy, scalability, and speed when benchmarked against existing systems. The integrated dashboard not only facilitates effective visualization but also supports data-driven decision-making in critical healthcare scenarios. Overall, the system offers a scalable and intelligent solution for managing real-time and historical healthcare data during pandemic outbreaks.