[论文解读] A Comparative Study for Predicting Heart Diseases Using Data Mining Classification Methods

Israa Ahmed Zriqat, Ahmad Mousa Altamimi+1 more|arXiv (Cornell University)|Apr 10, 2017

Artificial Intelligence in Healthcare参考文献 19被引用 49

一句话总结

本研究使用 MATLAB 中的大规模数据集，评估了五种数据挖掘分类算法——朴素贝叶斯、决策树、判别分析、随机森林和支持向量机——在预测心脏病方面的表现。决策树的准确率最高，达到 99.0%，甚至优于其集成变体随机森林，表明在此特定数据集中，单个树模型在心脏病预测方面可能比集成方法更有效。

ABSTRACT

Improving the precision of heart diseases detection has been investigated by many researchers in the literature. Such improvement induced by the overwhelming health care expenditures and erroneous diagnosis. As a result, various methodologies have been proposed to analyze the disease factors aiming to decrease the physicians practice variation and reduce medical costs and errors. In this paper, our main motivation is to develop an effective intelligent medical decision support system based on data mining techniques. In this context, five data mining classifying algorithms, with large datasets, have been utilized to assess and analyze the risk factors statistically related to heart diseases in order to compare the performance of the implemented classifiers (e.g., Naïve Bayes, Decision Tree, Discriminant, Random Forest, and Support Vector Machine). To underscore the practical viability of our approach, the selected classifiers have been implemented using MATLAB tool with two datasets. Results of the conducted experiments showed that all classification algorithms are predictive and can give relatively correct answer. However, the decision tree outperforms other classifiers with an accuracy rate of 99.0% followed by Random forest. That is the case because both of them have relatively same mechanism but the Random forest can build ensemble of decision tree. Although ensemble learning has been proved to produce superior results, but in our case the decision tree has outperformed its ensemble version.

研究动机与目标

• 利用数据挖掘技术开发智能医疗决策支持系统，以提升心脏病预测能力。
• 评估并比较五种分类算法在大规模心脏病数据集上的性能表现。
• 识别出最适合早期检测心脏病的最准确、最可靠的分类器。
• 通过数据驱动的风险因素分析，减少诊断错误和医疗成本。
• 提供一种实用且高准确率的临床决策支持解决方案，基于机器学习技术。

提出的方法

• 实现了五种数据挖掘分类算法：朴素贝叶斯、决策树、判别分析、随机森林和支持向量机。
• 在 MATLAB 环境中，使用两个真实世界的心脏病数据集进行实验。
• 分类器在标准化数据上进行训练和测试，性能以准确率为首要评估指标。
• 应用特征选择和统计分析，识别与心脏病相关的关键风险因素。
• 通过组合多个决策树，利用集成学习方法提升随机森林的泛化能力。
• 性能比较基于分类准确率，结果在所有五种算法之间进行分析。

实验结果

研究问题

• RQ1 哪种数据挖掘分类算法在预测心脏病方面准确率最高？
• RQ2 在此背景下，单个树基模型与随机森林等集成方法相比表现如何？
• RQ3 数据挖掘技术在多大程度上可减少诊断错误并支持临床决策？
• RQ4 分类器识别出的与心脏病最相关的统计显著风险因素是什么？
• RQ5 使用大规模数据集是否显著提升了不同算法的预测性能？

主要发现

• 决策树分类器在预测心脏病方面达到了最高的准确率 99.0%。
• 尽管随机森林是多个决策树的集成，但其表现略逊于单个决策树模型。
• 所有五种分类器均表现出强劲的预测性能，准确率均超过 95%。
• 本研究证实，数据挖掘技术可显著提高诊断精度并减少医疗错误。
• 结果表明，在此数据集中，单个决策树的简洁性和可解释性可能优于集成学习带来的优势。
• 判别分析和朴素贝叶斯表现中等，准确率低于决策树和随机森林。