SmartCardio: Advancing cardiac risk prediction through Internet of things and edge cloud intelligence

Abstract Cardiovascular disease is a leading cause of illness and death globally. The integration of Internet of Things (IoT) and deep learning technologies, including transfer learning, has transformed healthcare by improving the prediction and monitoring of conditions such as arrhythmias, which can be fatal if not detected and treated promptly. Traditional methods often lack real‐time accuracy due to scattered data sources. A novel heart care approach utilising IoT technology and edge cloud computing is introduced to provide rapid, automated responses and support decision‐making. The system connects smart devices, sensors, and healthcare providers to predict patient conditions and deliver accessible healthcare services. It consists of two main phases: data acquisition, where sensors measure heart rate, temperature, and blood pressure, and data processing, where the edge cloud processes the data using Haar Wavelet transform, Convolutional Neural Network (CNN), and transfer learning. Experimental results demonstrate that this smart cardio system achieves 99.3% accuracy with reduced network delay and response time, outperforming traditional methods, such as k‐nearest neighbours, support vector machine, and discrete wavelet‐based convolutional neural network.