Utilizing Artificial Intelligence Techniques for Predicting Cases of Coronary Disease: An Investigative Approach
Abstract
Coronary disease stands as one of the most significant human health challenges worldwide, profoundly impacting human lives. Cardiovascular disorders, including heart-related ailments, have been responsible for a considerable number of deaths globally over the past few decades, emerging as the deadliest disease not only in India but also worldwide. Accurate and timely diagnosis of coronary disease is crucial for preventing cardiovascular failure and ensuring effective treatment. Thus, there is a pressing need for robust, precise, and efficient systems to diagnose such infections promptly for appropriate treatment. In this study, we utilized the Heart Stalog dataset obtained from the UCI repository, employing Neural Networks and Logistic Regression algorithms to accurately predict the occurrence of coronary disease. The proposed decision support system based on Neural Networks and Logistic Regression will aid healthcare professionals in efficiently identifying heart patients. Logistic Regression emerged as the superior model among the two algorithms, achieving an overall accuracy rate of 91.54%. Our findings demonstrate the superior performance of Logistic Regression over Neural Networks in terms of precision. Developing accurate and computationally efficient classifiers for clinical applications remains a significant challenge in Machine Learning.
Keywords
Download Options
Introduction
In recent years, there has been a significant surge in interest in analyzing clinical data, as healthcare organizations recognize the potential of leveraging patient data from various clinical systems to improve healthcare delivery and management of clinical datasets. Extracting insights from such data requires advancements from the realms of Data Mining, Machine Learning, Artificial Intelligence, and Data Visualization.
Healthcare institutions are now generating vast amounts of data, posing challenges in data management. Hospitals have accumulated extensive patient data and medical records, prompting the need for data mining to uncover patterns and associations that can inform effective decision-making. Clinical data mining is pivotal for extracting valuable clinical insights from medical datasets.
This urgency stems from various critical health issues such as heart disease, liver failure, kidney complications, nerve damage, and vision impairment. Early identification of diabetes is among the significant clinical challenges. The heart, being the central organ in the human body, plays a vital role, and any impairment can affect other crucial body functions, necessitating cardiac health assessments.
Coronary artery disease (CAD) is regarded as one of the most complex and life-threatening human diseases globally. It impedes the heart's ability to pump an adequate amount of blood to fulfill the body's normal functions, leading to heart failure. According to the World Health Organization (WHO), an estimated 17 million people die annually from cardiovascular diseases, including coronary failures and strokes.
Symptoms of heart disease include shortness of breath, fatigue, swollen feet, and other associated signs indicative of cardiovascular or noncardiac abnormalities. Early-stage diagnostic methods for identifying heart disease were complex, and their subsequent complications have significantly impacted quality of life. Diagnosis and treatment of heart disease remain challenging, particularly in non-industrialized countries, due to limited access to medical resources and a shortage of healthcare professionals, affecting accurate diagnosis and treatment of patients.
Accurate and timely diagnosis of coronary artery disease risk in patients is crucial for reducing their associated risks of severe heart issues and improving heart health outcomes. [1]. [7]. [6].
Conclusion
The abundance of clinical datasets available for various data mining and AI techniques underscores the importance of enhancing the accuracy and efficiency of disease diagnosis. The objective of this research is to demonstrate how classifying Heart Stalog disease categories from publicly available raw clinical datasets can assist physicians in reaching precise diagnoses to predict the presence or absence of heart disease. Upon evaluating the results, Logistic Regression emerged with the highest prediction accuracy of 91.54%. This model proves to be the most effective in predicting patients with coronary disease. Thus, the proposed Logistic Regression Classifier approach offers a reliable method for both prediction and diagnosis.