<p>Edge computing, the Internet of Things (IoT), and artificial intelligence are game changers for emerging delay-sensitive and crisp-response applications and services. Smart systems, such as smart cities, smart health, are the major beneficiaries of these technologies. The incorporation of Edge computing and Artificial Intelligence of Things (AIoT) in healthcare has transformed patient monitoring, diagnosis, and treatment through real-time data acquisition and intelligent analysis. This study proposed an edge computing integration architecture for Parkinson's disease prediction in healthcare systems. The system integrates smart sensors, wearable devices, edge computing, and cloud infrastructure to facilitate ongoing health monitoring and data-driven decision-making. A hybrid machine learning model combining convolutional neural networks (CNN) with bidirectional LSTM is developed. Integrated with an edge-based integration architecture, it enables real-time patient health monitoring, accurate disease prediction and assisted data-driven decision-making. The experimental finding clearly supports the effectiveness of the proposed model, demonstrated by its evaluation metrics: an accuracy of 0.90, precision of 0.93, recall of 0.90, and an F1 score of 0.91. These values collectively demonstrate the model's strong predictive capability and balanced performance across key evaluation measures. The architecture achieves low latency, scalability, privacy, and seamless coordination between healthcare units.</p>