IoT-based patient monitoring system for predicting heart disease using deep learning

Abstract

Motivation: Chronic diseases include diabetes, cancer, heart disease (HD), and chronic respiratory diseases are the main causes of mortality globally. It is quite challenging to identify heart diseases when the symptoms or characteristics vary. In the contemporary digital environment, the healthcare sector produces a considerable volume of patient data. For doctors, manually processing these created data becomes exceedingly challenging. The Internet of Things is handling the generated data quite well. It provides continuous communication between individuals and devices, and its fusion with the Cloud enhances the quality of life. Materials and Methods: Deep learning, a branch of machine learning, has the transformational ability to rapidly and reliably analyse massive amounts of data, produce insightful conclusions, and effectively resolve complex problems. Massive volumes of data were collected by the IoT, and because of deep-learning algorithms, it is now possible to identify and diagnose diseases. The suggested approach collects information from IoT devices, and electronic medical evidence connected to patient histories that are stored in the cloud are sent to predictive analytics. Results and Conclusion: The Long Short Term Memory (LSTM) and Recurrent Neural Network based smart healthcare system for monitoring and precisely forecasting heart diseases obtains an accuracy of 99.99%, which is substantially superior to the current smart heart disease prediction systems such as traditional methods.