Ambient assisted living predictive model for cardiovascular disease prediction using supervised learning

The rapid increase of the aged population and challenges towards taking health care and social care become the key point for the industry and researchers nowadays. Heart diseases are typical chronic illnesses with a high recurrence rate. In some of the cases, a heart attack occurs suddenly without any omens. Patients typically live in their homes rather than in hospitals and are often unable to access medical care in an emergency. Cardiovascular disease leads to a significant difficulty for the doctors to know the patient’s status in time, and it becomes one of the significant reasons for death. To overcome these problems, a solution needs to design, implement, and validate adequately through an appropriate base knowledge. To overcome these challenges, remotely real-time patient’s health data can be identified. Today Internet of Things is playing a key role in solving the problem of heart disease. The patients can avail of the medical resource much. This research work aims to propose a framework for prediction of heart disease using major risk factors based on various classifier arrangements; K-nearest neighbors, Naïve Bayes, support vector machine, Lasso and ridge regression algorithms. Apart from these data classification, linear discriminant analysis and principal component analysis were done. The support vector machine provides 92% accuracy, and F1 accuracy is 85%. The performance of the proposed research work is evaluated using precision, accuracy, and sensitivity.