EFFECTIVE MEDICAL DIAGNOSIS OF HUMAN HEART DISEASES USING MACHINE LEARNING TECHNIQUES WITH AND WITHOUT GRIDSEARCHCV

Computer Engineering

Type 2 diabetes mellitus (T2DM) is a widespread chronic condition marked by irregular insulin secretion, often leading to severe complications, including coronary mood disease (CHD), which is the most prevalent and severe. Medical analysis is recognized as a valuable source of comprehensive information in this context. Given the large number of T2DM patients, it is becoming increasingly critical to identify those who are at tall jeopardy of CHHD complications, but a quantitative technique is still lacking. Coronary Heart Illness (CHD) is unique of foremost reasons of death worldwide; consequently, early identification of CHD can assist lower mortality rates. The difficulty stems from the data's intricacy and relationship prediction using standard procedures. The goal of This study uses the method of machine learning (ML) and historical medical data to predict CHD. The primary aim of this study is to employ machine learning techniques such as Support Vector Machines (SVM), Decision Trees, KNN classifiers, Ensemble Classifiers, and neural network methods (ANN) to uncover associations within CHD data. Using the Coronary Heart Disease dataset instances, the investigated ML approaches generate intelligent models through cross validation. Using several performance assessment metrics, empirical data show the promise of statistical models in identifying CHD.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.