Objective: The purpose of this research was  to predict the tonsillitis using machine learning algorithms. Increasing utilization of smartphones with sensor systems and machine learning capability promise better M-Healthcare services. Tonsillitis is an inflammation of your tonsils.  Tonsillitis analysis requires contemporary technology. Method: Different machine learning algorithms and frameworks used for evaluating the accuracy and performance.Artificial Neural Networks combined with picture processing and RGB color coding used for identify tonsillitis early and monitor prognosis at home. This study describes an innovative machine learning and  smartphone-based optimization approach with a linked camera. Results:Patients in remote locations, poor and impoverished countries may check, assess, and frequently do tonsillitis exams anywhere, anytime, and any place.  This research proposes an unique method and machine learning approach to evaluate tonsillitis photos and diagnose infections with 90\% accuracy for Random Forest and Decision Tree, . Conclusion:In this research paper, we have introduced an advanced MHealth application on human health and monitoring systems. The use and technological advancement of smartphones has skyrocketed in the last decade. Now embedded sensors in smartphone devices help to assess physiological indicators and evaluate the health status. We have demonstrated that M-health can be effectively applied in the detection of tonsillitis by using smartphone devices and machine learning

We have collected two data sets. First data set consisted of 45 thousand data and second one 43. One data set consisted of food information , like calorie count, sugar in per 100 gram, fat in per 100 gram and so on. Second data set consisted of Obesity rate among USA people from age 0 to 80. We wanted to show a relation with sugar intake and obesity rate. Last of all our experiment found that ther's a significance evidence that there's a link between obesity and sugar intake . We used the machine learning approach for our experimental analysis.

Heart Disease is the most dominating disease which is taking a large number of deaths every year. A report from WHO in 2016 portrayed that every year at least 17 million people die of heart disease. This number is gradually increasing day by day and WHO estimated that this death toll will reach the summit of 75 million by 2030. Despite having modern technology and health care system predicting heart disease is still beyond limitations. As the Machine Learning algorithm is a vital source predicting data from available data sets we have used a machine learning approach to predict heart disease. We have collected data from the UCI repository. In our study, we have used Random Forest, Zero R, Voted Perceptron, K star classifier. We have got the best result through the Random Forest classifier with an accuracy of 97.69.