Design, Development and Testing of Internet of Things based Preventive Healthcare System

Abstract

Cardio Vascular Disease (CVD) is the number one cause of death for both men and women worldwide. CVD represent 30% of global fatalities and are classified as high medical emergencies. In an attempt to decrease this rate and thus, be able to save lives, it is decisive to anticipate a heart attack by early detection of concomitant signs. Patients with CVD are at high risk of running irreversible incidents when left alone at home without close surveillance or monitoring. The objective of this thesis is to design a comprehensive system which gives a vital solution to the aforementioned unfortunate encounters. With the help of developed system one can detect the CVD and also change in abnormality in the essential parameters of the body. The system consists of sensors (such as pulse sensor, heart rate sensor, blood pressure sensor, blood sugar sensor, body temperature sensor, oxygen level in blood sensor, stress level sensor, breathing sensor) interfaced with an Arduino Uno. The Arduino Uno sends the data to the mobile application using the Bluetooth and results are displayed in the mobile application. An alert message on mobile is used to provide whenever the body parameters are lesser or greater than the normal values. The values are compared with normal values and SMS is sent to the personal doctor or concerned (relative) number given by the patient. The measured values are given to the Fuzzy Inference System (FIS) to detect whether an individual has a CVD or not by using Mamdani and Sugeno methods of FIS. The parameters considered for predicting whether the individual has CVD or not are blood pressure, blood sugar, heart rate and oxygen level in the blood (SPO2). The FIS outputs indicate (i) whether the individual has a CVD or not, (ii) the risk level of CVD and (iii) some primary level precautions depending on the risk level. Mamdani and Sugeno methods were evaluated by comparing them with the results of the pathology reports. The results show that the Sugeno method gives 2% more accuracy in predicting a CVD as compared to the Mamdani method.