Predicting Cardiovascular Disease Through IoT and Deep Learning Methods

Today, heart disease affects many people and is a leading cause of death worldwide. Cardiovascular disease, also known as CVD, is the leading cause of morbidity and mortality, accounting for more than 70% of all deaths. According to the 2017 Global Burden of Disease Study, CVD causes 43% of all deaths. According to the World Health Organization (WHO), heart disease and stroke will kill 23.6 million people worldwide by 2030. This situation is difficult to predict when there are no symptoms and requires prior knowledge of the patient. A brilliant method called the Internet of Things captures the information that patients need and stores it in cloud servers. Many studies have been done on heart diseases; however, the accuracy of the prediction is very low. To solve this problem, we have created a revolutionary IoT-smart solution. Current healthcare systems are based on IoT devices and distributed systems, and they face serious problems due to insufficient distribution of patient information, which can lead to wrong diagnosis and treatment decisions. This paper uses a combination of ResNet197 and Gradient Boosting Machine (GBM). ResNet197 is a deep residual neural network with 197 layers for CVD diagnosis. This technology outperforms existing models for predicting heart disease with 99.25% accuracy, 96.68% accuracy, 93.97 sensitivity, 96.96 F1 score, 98.69% accuracy, and 97.8% return.