Heart related diseases or Cardiovascular Diseases (CVDs) are the main reason for a huge number of deaths in the world over the last few decades and has emerged as the most life-threatening disease, not only in India but in the whole world. Many researchers, in recent times, have been using several machine learning techniques to help the health care industry and the professionals in the diagnosis of heart related diseases. This indicates a need of reliable, accurate and feasible system to

more »

... ously monitor and diagnose for CVD for timely action and treatment. This work proposes a smartphone-based heart disease prediction system than can have both monitoring as well as prediction of heart disease. A system to monitor patients in real-time has been developed using Node MCU interfaced with temperature, humidity and pulse rate sensors. The developed system is capable to transmit the acquired sensor data to a cloud(firebase) every 10 seconds. An Android application is designed to display the sensor data. One best machine learning algorithm was ported to the Android application for heart disease prediction in real-time. The machine learning algorithms were trained and tested using two widely used open-access datasets. Five machine learning algorithms were checked for their performances using two different methods. ANN was found to be the best performing algorithm with an accuracy of 93.5%. This algorithm is deployed to the Android application and the heart disease is predicted in real-time. The proposed work is limited by use of single hidden layer for implementing Neural network. Data from few more sensors related to heart parameters should be experimented with. Trying out with increasing hidden layer size may increase the accuracy of the neural network. There is further scope in optimizing the Android application user interface.