Cardiovascular Disease Detection Using Intelligent Systems: A Cursory Survey

Globally, cardiovascular diseases, comprising a range of ailments, continue to demonstrate increasing mortality rates. Despite collaborative endeavors to predict and initiate timely treatment, achieving the necessary diagnostic accuracy poses a challenge due to the diverse lifestyles prevalent in the population. As a result, intensive research is directed toward formulating a model that gains acceptance within the medical community. In this context, we elucidate the operational principles of each machine learning model, as detailed in the selected articles for our review, including their mathematical aspects. This literature survey delves into comprehending the breadth of conducted research, providing insights into the prevailing emphasis. Notably, every article consistently underscores the need for a hybrid model, acknowledging the limitations of the efficacy of single models. Each study, in its pursuit of optimization, begins with meticulous pre-processing, hyperparameter tuning, and the application of statistical models, showcasing commendable efforts. A straightforward comparison of the selected models is presented, along with their respective results, implications, strengths, and limitations. However, despite these commendable initiatives, there is still considerable room for improving accuracy and further advancing diverse hybrid models, marking an ongoing trajectory of progress in this field. This article aims to be a convenient reference for researchers and practitioners interested in the application of machine learning for cardiovascular disease detection.