Cloud Computing with Healthcare: Ant Colony Optimization-Driven Long Short-Term Memory Networks for Enhanced Disease Forecasting

Abstract

Background: Cloud computing and artificial intelligence are quickly changing healthcare systems and providing strong, data-driven disease prediction capabilities. Traditional models fail to strike a compromise between processing efficiency and accuracy when
managing real-time data from IoT health devices. Objective: Using massive datasets from Internet of Things (IoT) devices for real-time
monitoring, this study attempts to create a model that employs Ant Colony Optimization (ACO) to enhance Long Short-Term Memory (LSTM) networks for more precise and effective disease prediction in cloud-based healthcare settings. Methods: The ACO-LSTM model optimizes LSTM parameters by modifying weights and biases to reduce prediction errors using ACO algorithms. The infrastructure required to manage and process large amounts of IoT data is provided by cloud computing, while pretreatment procedures standardize data to guarantee successful LSTM sequence learning. Results: In comparison to conventional models like CNN and BKNN, the proposed solution obtained 94% accuracy and cut processing time to 54 seconds. The model's high sensitivity (93%) and specificity (92%), that minimize false positives and allow for accurate disease prediction, are also essential for prompt therapies. Conclusion: In cloud-based healthcare systems, the ACO-LSTM model provides a dependable and effective framework for real-time disease prediction. The model supports scalable patient monitoring by integrating ACO optimization with the sequential analysis of LSTM to produce insightful data in real time