Intelligent Systems for Chronic Disease Management: Integrating IOT and AI for Enhanced Delivery of Healthcare

The latest advancements like Artificial Intelligence (AI), the Internet of Things (IoT), and cloud computing have transformed healthcare from conventional to intelligent in order to enhance medical care. Healthcare potential arises from IoT and AI convergence. The proposed system introduces an IoT and AI-based illness diagnosis framework for modern healthcare delivery infrastructures. The article aims to induce a health problem detection algorithm for diabetes and heart disease utilizing IoT and AI integration approaches. The approach comprises data collecting, preprocessing, categorization, and modification parameter. IoT devices like sensors and wearables enable data collecting, while AI approaches diagnose diseases using the data. The method presents a Crow Search Optimization (CSO) algorithm-based Cascade Long Short-Term Memory (CLSTM) model for disease diagnosis. CSO is utilized to adjust the bias and weight parameters of the CLSTM structure to enhance medical data categorization. Additionally, the Isolation Forest (iForest) approach is utilized to eliminate outliers in this approach. CSO improves CLSTM method diagnostics significantly. CSO-LSTM model performance was validated using information related to healthcare. In experiments, the CSO-LSTM model achieved the highest accuracies of 97.02% and 97.7% in identifying diabetes and heart disease. Thus, the CSO-LSTM structure is a suitable instrument for diagnosing diseases for intelligent healthcare structures.