Scholarlink

Cardiovascular disease (CVD) is the predominant cause of mortality globally, surpassing both diabetes and cancer. Reducing illness and mortality rates requires the prompt identification and accurate prediction of CVDs. Diagnostic techniques such as coronary angiography are very precise but also invasive, costly, and cause discomfort. There is a need for diagnostic approaches that are reliable and do not require intrusive procedures. Machine learning (ML) and data mining play a crucial role in healthcare, particularly in the identification of heart problems. ML algorithms can accurately predict cardiac disease by analyzing clinical data, aiding in clinical decision-making. This comprehensive study provides a concise overview of the latest developments in ML and DL techniques for the detection, classification, and prediction of CVDs. The assessment assesses Support Vector Machines (SVMs), Artificial Neural Networks, Logistic Regression, Random Forests, and Decision Trees. The evaluation is based on data from trustworthy sources spanning from 2014 to 2024. The report additionally delineates the main obstacles encountered by researchers, examines potential remedies, and proposes future investigations to augment heart disease prediction systems. This study assesses the efficacy of clinical decision-making tools in enhancing the identification and prevention of CVD.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrative Review of Machine Learning and Deep Learning Approaches for Cardiovascular Disease Detection, Classification, and Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Muhammad Anas,
  • Saeid Nahavandi,
  • Jingxin Zhang

摘要

Cardiovascular disease (CVD) is the predominant cause of mortality globally, surpassing both diabetes and cancer. Reducing illness and mortality rates requires the prompt identification and accurate prediction of CVDs. Diagnostic techniques such as coronary angiography are very precise but also invasive, costly, and cause discomfort. There is a need for diagnostic approaches that are reliable and do not require intrusive procedures. Machine learning (ML) and data mining play a crucial role in healthcare, particularly in the identification of heart problems. ML algorithms can accurately predict cardiac disease by analyzing clinical data, aiding in clinical decision-making. This comprehensive study provides a concise overview of the latest developments in ML and DL techniques for the detection, classification, and prediction of CVDs. The assessment assesses Support Vector Machines (SVMs), Artificial Neural Networks, Logistic Regression, Random Forests, and Decision Trees. The evaluation is based on data from trustworthy sources spanning from 2014 to 2024. The report additionally delineates the main obstacles encountered by researchers, examines potential remedies, and proposes future investigations to augment heart disease prediction systems. This study assesses the efficacy of clinical decision-making tools in enhancing the identification and prevention of CVD.