Bibliometric Analysis of Deep Learning Approaches for Early Detection of Cardiovascular Diseases

Cardiovascular diseases (CVD) are a major global health challenge, demanding advanced methods for early detection and intervention. This survey paper offers a comprehensive review of state-of-the-art deep learning approaches for early prediction of CVD, focusing particularly on artificial intelligence methods, including gradient boosting techniques. The main goal is to ensure that the developed predictive models are reliable, accurate, and comprehensive by leveraging diverse datasets that integrate objective, exploratory, and subjective elements. This research also provides a bibliometric survey to analyze the trends, key contributors, and influential publications in the field of CVD prediction using deep learning. It evaluates various deep learning techniques, highlighting their strengths and limitations in predicting cardiovascular risks. Furthermore, it discusses the significance of feature selection, data preprocessing, and model optimization in enhancing predictive performance. The findings of this survey aim to provide physicians with advanced, sophisticated, and nuanced tools for diagnosing patients at risk of cardiovascular illness and its complications, thereby enabling early intervention with specialized preventive therapy. This paper also outlines future research directions and the potential for integrating multimodal data sources to further improve the accuracy and utility of predictive models in clinical practice.