Machine learning-based heart disease diagnosis: A systematic literature review
Machine learning-based heart disease diagnosis: A systematic literature review
复制标题
DOI：
10.1016/j.artmed.2022.102289
复制
发表时间：
2022-03-31
影响因子：
7.5
通讯作者：
Siddique, Zahed
中科院分区：
文献类型：
--
作者：
Ahsan, Md Manjurul;Siddique, Zahed
心脏病是当今世界面临的重大挑战之一，也是全世界许多人死亡的主要原因之一。机器学习（ML）应用的最新进展表明，利用心电图（ECG）和患者数据，在早期阶段检测心脏病是可行的。然而，心电图和患者数据往往不平衡，这最终对传统机器学习的公正性提出了挑战。多年来，许多研究人员和从业者已经接触到了多种数据级别和算法级别的解决方案。为了更广泛地了解现有文献，本研究采用系统文献综述（SLR）方法来揭示与心脏病预测中数据不平衡相关的挑战。在此之前，我们对2012年至2021年11月15日期间从知名期刊获取的451篇参考文献进行了荟萃分析。为了进行深入分析，我们对49篇参考文献进行了考虑和研究，考虑了以下因素：心脏病类型、算法、应用和解决方案。我们的 SLR 研究表明，当前的方法在处理不平衡数据时遇到各种开放性问题，最终阻碍了它们的实际适用性和功能。在心脏病的诊断中，机器学习方法有助于改善数据驱动的决策。对451篇心脏病诊断文章的元数据分析和49篇选定的心脏病诊断文章的内容分析。研究人员主要集中于增强模型的性能，而忽略了机器学习算法的可解释性和可解释性等其他问题。
Heart disease is one of the significant challenges in today's world and one of the leading causes of many deaths worldwide. Recent advancement of machine learning (ML) application demonstrates that using electrocardiogram (ECG) and patients' data, detecting heart disease during the early stage is feasible. However, both ECG and patients' data are often imbalanced, which ultimately raises a challenge for the traditional ML to perform unbiasedly. Over the years, several data level and algorithm level solutions have been exposed by many researchers and practitioners. To provide a broader view of the existing literature, this study takes a systematic literature review (SLR) approach to uncover the challenges associated with imbalanced data in heart diseases predictions. Before that, we conducted a meta-analysis using 451 reference literature acquired from the reputed journals between 2012 and November 15, 2021. For in-depth analysis, 49 referenced literature has been considered and studied, taking into account the following factors: heart disease type, algorithms, applications, and solutions. Our SLR study revealed that the current approaches encounter various open problems/issues when dealing with imbalanced data, eventually hindering their practical applicability and functionality. In the diagnosis of heart disease, machine learning approaches help to improve data-driven decision-making. A metadata analysis of 451 articles and content analysis of 49 selected articles of heart disease diagnosis. Researchers primarily concentrated on enhancing the performance of the models while disregarding other issues such as the interpretability and explainability of Machine learning algorithms.