Abstract:
Machine learning techniques are used in this study to examine data and forecast cardiac illness. The main objective of my work is to examine the data and estimate the proportion of persons who will develop heart disease based on each dataset. We wanted to examine the topic of " The Heart Disease Prediction using the Technique of Classification in Machine Learning using the concepts of Data Mining " and evaluate the machine learning algorithm and approaches for detecting heart disease in this research-based project. The classification methodology found in machine learning and data mining principles is used in this work to propose a technique for predicting cardiac disease. Random Forest Classifier is a method that is commonly employed in machine learning (RFC). This algorithm, along with others like Support Vector Machine, Linear Regression, AdaBoost, Naive Bayes, and K-Nearest Neighbor, aims to deliver better outcomes and forecasts. A method for evaluating the accuracy and error rate is also demonstrated in this study, using performance matrices such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Square Error (RMSE). Additionally, purely for performance evaluation, all of these algorithms were evaluated on a dataset. Age, sex, cp, trestbps, chol, fbs, restecg, thalach, exang, oldpeak, slope, ca, thal, and target are the 14 attributes that we have acquired from our dataset to employ in this prediction technique. In order to predict cardiac illness in this study, I have argued in favor of using the XGBC, GBC, RFC algorithm.
