An Experimental Study to Perform Bioinformatics Based on Heart Disease Case Study Using Supervised Machine Learning

Heart diseases are very dangerous and can be detrimental. Especially in today’s busy life schedule, people are getting more prone to these. After an extensive literature review, the authors realized that experimental studies in bioinformatics can prove to be very helpful for fast analysis of medical databases like these, without their quality being compromised. To verify this, a dataset was extracted and filtered under the supervision of a cardiologist. A model was then created which was later tested on different machine learning algorithms. The F1 scores, precision, and recall for different algorithms tested were then calculated and compared. This paper aims to showcase an experimental study and verify the significance of distinct machine learning algorithms and to find and study the various features and align them in the best way possible. The paper also aims to perform feature engineering and motivate people to take care of themselves.