Heart Disease Detection using Hybrid Machine Learning and IoT (Software based)

Heart disease is a prevalent ailment that may be deadly in the elderly and those who do not live a healthy lifestyle. It may avoid it to some degree with frequent check-ups and diagnosis, in addition to keeping a good eating routine. Hospitals generate a lot of patient data, such as x-rays, lung tests, heart pain tests, chest pain tests, personal health records (PHRs), and so on. The decision tree classifier is developed based on the symptoms, which are specifically the properties required for prediction. We will be able to identify specific features that are the best and will lead to a better forecast of the datasets using the decision tree technique. The data collected by hospitals is not being utilised efficiently. Other functions are not permitted, and some of these tools are used to harvest data from the heart disease detection database. In this research, several optimization methods (Fuzzy Logic, Random Forests, and Q-Learning) machine learning algorithms, and health care data are utilised to determine whether or not patients have cardiac illnesses based on the information in their records. Attempt to utilise the data as a model for determining whether the patient has cardiac disease.