• Prity Kumari
• Jitendra Tyagi

Historical data may be used to forecast future developments and guide businesses in making strategic decisions that provide them a competitive edge, ultimately leading to greater efficiency and more profits. Data from the healthcare business is analyzed by several analysts, who look for patterns that may help them identify and predict diseases that patients and doctors may use in a variety of ways. Examining and assessing heart disease is the primary focus of this study. Worldwide, millions of lives are lost each year due to heart disease (HD). Numerous When heart illness first begins, there are no real-time diagnostic or prognostic techniques available. Using a systematic procedure, I gathered data, cleaned it, selected features using the FCMIM and PCA algorithms, and classified it using machine learning. To evaluate various training and testing data for HD prediction, ML methods are used. Research is being done on a variety of classification methods such as Xgboost, random forest, Extra tree, LGBM, and stacking classifiers. The UCI machinery HD data set is utilized in these experimental investigations. The feasibility of a prediction system was tested using a dataset containing 13 features. Accuracy, Precision, Recall, and the F1-score are used to measure the efficacy of these prediction models. Thus, an additional tree with the highest accuracy is considered the best technique for heart disease prediction based on their experimental research.

Twitter, Sentiment analysis, Machine Learning, LSTM model

"Comparative Analysis based on Performance of Classification Algorithms for Heart Disease Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.h270-h276, March-2023, Available :http://www.jetir.org/papers/JETIR2303744.pdf

"Comparative Analysis based on Performance of Classification Algorithms for Heart Disease Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. pph270-h276, March-2023, Available at : http://www.jetir.org/papers/JETIR2303744.pdf