Main Article Content
Cardiovascular disease is among the common causes of mortality rate in the world. It is tough for healthcare professionals to forecast because it is a complex undertaking that necessitates competence and a greater level of information. The medical system is still characterized by an abundance of information but a scarcity of knowledge. Mostly online, there is a wealth of information about healthcare organizations. However, reliable analytic techniques for uncovering underlying correlations and relationships between variables are lacking. A computerized medical diagnostics system would promote health productivity while lowering costs. Cardiovascular attack detection required a huge amount of information that is very much complicated and enormous to collect and analyzed utilizing traditional existing functions. Our research aim is to detect the most suitable machine learning methodology for finding cardiac disease which is operationally efficient and accurate. We created a heart disease prediction program that utilizes the patient history to forecast whether or not a person would be identified with cardiovascular disease. To identify and categorize patients having cardiovascular disease, we applied various machine learning methods such as logistic regression & K - Nearest Neighbours (KNN). To govern how well the model may be utilized to improve the accuracy of diagnosis of Heart Attack inside any patient, a very useful technique was applied. The suggested model's performance was quite pleasing, as it was possible to forecast evidence to confirm a heart illness in a particular person using KNN & Linear Regression (LR), with high accuracy when compared to Naïve Bayes.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.