HDRP: Integrated Strategies for Robust Heart Disease Detection using Random Crop LSTM Processing and Regression Models

Abstract

Detecting heart disease is significant for timely intervention and improved patient outcomes. With the rising global burden of cardiovascular disorders, there is an urgent need for accurate and efficient diagnostic tools. Advanced technologies, such as Machine Learning (ML) and Artificial Intelligence (AI), have shown promise in enhancing early detection and risk assessment. Integrating these innovative approaches into clinical practice can significantly contribute to the early identification of heart disease, facilitating timely interventions and personalized patient care. Addressing this need is vital for reducing the impact of heart disease on public health. This research presents a comprehensive examination of heart disease detection models, encompassing neural networks, backpropagation, random crop techniques, Long Short-Term Memory (LSTM), and regression methods. The investigation included a comparative analysis of various models, including Heart Disease Evaluation (HBE), AdaBoost, Support Vector Machine (SVM), Random Forest, and proposed method (HDRP), with a focus on accuracy, error rates, and precision over 5 and 10 epochs. Notably, the HDRP model emerged as a standout performer, consistently demonstrating superior accuracy and the lowest error values, showcasing its efficacy in heart disease prediction. The discussion highlights the unique features of HDRP, attributed to advanced methodologies or distinctive design elements. The study emphasizes the importance of future research to delve into the specific attributes contributing to HDRP's performance, exploring model architecture, optimization strategies, and scalability across diverse datasets.