用于预测冠状动脉疾病的机器学习算法：迈向开源解决方案的努力。
Machine learning algorithms for predicting coronary artery disease: efforts toward an open source solution.
作者信息
Akella Aravind, Akella Sudheer
机构信息
Qualicel Global Inc., Huntington Station, NY 11746, USA.
出版信息
Future Sci OA. 2021 Mar 29;7(6):FSO698. doi: 10.2144/fsoa-2020-0206.
Abstract
AIM
The development of coronary artery disease (CAD), a highly prevalent disease worldwide, is influenced by several modifiable risk factors. Predictive models built using machine learning (ML) algorithms may assist clinicians in timely detection of CAD and may improve outcomes.
MATERIALS & METHODS: In this study, we applied six different ML algorithms to predict the presence of CAD amongst patients listed in 'the Cleveland dataset.' The generated computer code is provided as a working open source solution with the ultimate goal to achieve a viable clinical tool for CAD detection.
RESULTS
All six ML algorithms achieved accuracies greater than 80%, with the 'neural network' algorithm achieving accuracy greater than 93%. The recall achieved with the 'neural network' model is also the highest of the six models (0.93), indicating that predictive ML models may provide diagnostic value in CAD.
摘要
目的
冠状动脉疾病（CAD）是一种在全球范围内高度流行的疾病，其发展受到多种可改变的风险因素影响。使用机器学习（ML）算法构建的预测模型可能有助于临床医生及时检测CAD，并改善治疗结果。
材料与方法
在本研究中，我们应用六种不同的ML算法来预测列于“克利夫兰数据集”中的患者是否患有CAD。生成的计算机代码作为一个有效的开源解决方案提供，最终目标是实现一种可行的CAD检测临床工具。
结果
所有六种ML算法的准确率均超过80%，其中“神经网络”算法的准确率超过93%。“神经网络”模型的召回率也是六个模型中最高的（0.93），这表明预测性ML模型可能在CAD诊断中具有价值。
相似文献
1
Machine learning algorithms for predicting coronary artery disease: efforts toward an open source solution.用于预测冠状动脉疾病的机器学习算法：迈向开源解决方案的努力。
Future Sci OA. 2021 Mar 29;7(6):FSO698. doi: 10.2144/fsoa-2020-0206.
2
Diagnosis of Coronary Artery Disease based on Machine Learning algorithms Support Vector Machine, Artificial Neural Network, and Random Forest.基于机器学习算法支持向量机、人工神经网络和随机森林的冠状动脉疾病诊断
Adv Biomed Res. 2023 Feb 25;12:51. doi: 10.4103/abr.abr_383_21. eCollection 2023.
3
A new machine learning technique for an accurate diagnosis of coronary artery disease.一种用于准确诊断冠心病的新机器学习技术。
Comput Methods Programs Biomed. 2019 Oct;179:104992. doi: 10.1016/j.cmpb.2019.104992. Epub 2019 Jul 24.
4
Score and Correlation Coefficient-Based Feature Selection for Predicting Heart Failure Diagnosis by Using Machine Learning Algorithms.基于评分和相关系数的特征选择在使用机器学习算法预测心力衰竭诊断中的应用。
Comput Math Methods Med. 2021 Dec 20;2021:8500314. doi: 10.1155/2021/8500314. eCollection 2021.
5
Machine Learning Predictive Models for Coronary Artery Disease.用于冠状动脉疾病的机器学习预测模型
SN Comput Sci. 2021;2(5):350. doi: 10.1007/s42979-021-00731-4. Epub 2021 Jun 22.
6
Custom machine learning algorithm for large-scale disease screening - taking heart disease data as an example.用于大规模疾病筛查的定制机器学习算法——以心脏病数据为例。
Artif Intell Med. 2023 Dec;146:102688. doi: 10.1016/j.artmed.2023.102688. Epub 2023 Oct 28.
7
Predicting coronary artery disease using different artificial neural network models.使用不同的人工神经网络模型预测冠状动脉疾病。
Anadolu Kardiyol Derg. 2008 Aug;8(4):249-54.
8
Ensemble of heterogeneous classifiers for diagnosis and prediction of coronary artery disease with reduced feature subset.用于冠状动脉疾病诊断和预测的具有简化特征子集的异构分类器集成
Comput Methods Programs Biomed. 2021 Jan;198:105770. doi: 10.1016/j.cmpb.2020.105770. Epub 2020 Sep 30.
9
Artificial plant optimization algorithm to detect heart rate & presence of heart disease using machine learning.基于机器学习的人工植物优化算法，用于检测心率和心脏病。
Artif Intell Med. 2020 Jan;102:101752. doi: 10.1016/j.artmed.2019.101752. Epub 2019 Nov 8.
10
Performance of a deep learning algorithm for the evaluation of CAD-RADS classification with CCTA.深度学习算法在 CCTA 评估 CAD-RADS 分类中的性能。
Atherosclerosis. 2020 Feb;294:25-32. doi: 10.1016/j.atherosclerosis.2019.12.001. Epub 2019 Dec 23.
引用本文的文献
1
Risk factor identification and prediction of pleural effusion following coronary artery bypass grafting.冠状动脉搭桥术后胸腔积液的危险因素识别与预测
Am J Transl Res. 2025 Apr 15;17(4):2850-2871. doi: 10.62347/KGKL5899. eCollection 2025.
2
Evaluating the quality of TikTok videos on coronary artery disease using various scales to examine correlations with video characteristics and high-quality content.使用各种量表评估TikTok上关于冠状动脉疾病的视频质量，以检验与视频特征和高质量内容的相关性。
Sci Rep. 2025 Mar 17;15(1):9189. doi: 10.1038/s41598-025-93986-3.
3
An efficient artificial neural network-based optimization techniques for the early prediction of coronary heart disease: comprehensive analysis.一种基于高效人工神经网络的冠心病早期预测优化技术：综合分析
Sci Rep. 2025 Feb 9;15(1):4827. doi: 10.1038/s41598-025-85765-x.
4
Quantum-inspired seagull optimised deep belief network approach for cardiovascular disease prediction.用于心血管疾病预测的量子启发式海鸥优化深度信念网络方法
PeerJ Comput Sci. 2024 Dec 13;10:e2498. doi: 10.7717/peerj-cs.2498. eCollection 2024.
5
Cardiovascular risk factors and development of nomograms in an Italian cohort of patients with suspected coronary artery disease undergoing SPECT or PET stress myocardial perfusion imaging.在意大利一组疑似冠心病且接受单光子发射计算机断层扫描（SPECT）或正电子发射断层扫描（PET）负荷心肌灌注成像的患者中，心血管危险因素与列线图的制定。
Front Nucl Med. 2024 Feb 14;4:1232135. doi: 10.3389/fnume.2024.1232135. eCollection 2024.
6
A deep learning-based automated diagnosis system for SPECT myocardial perfusion imaging.基于深度学习的 SPECT 心肌灌注成像自动诊断系统。
Sci Rep. 2024 Jun 12;14(1):13583. doi: 10.1038/s41598-024-64445-2.
7
Which risk factor best predicts coronary artery disease using artificial neural network method?哪种风险因素最适合使用人工神经网络方法预测冠状动脉疾病？
BMC Med Inform Decis Mak. 2024 Feb 14;24(1):52. doi: 10.1186/s12911-024-02442-1.
8
Prediction of atmospheric PM level by machine learning techniques in Isfahan, Iran.利用机器学习技术预测伊朗伊斯法罕的大气颗粒物水平
Sci Rep. 2024 Jan 24;14(1):2109. doi: 10.1038/s41598-024-52617-z.
9
A Systematic Review: Do the Use of Machine Learning, Deep Learning, and Artificial Intelligence Improve Patient Outcomes in Acute Myocardial Ischemia Compared to Clinician-Only Approaches?一项系统评价：与仅由临床医生参与的方法相比，机器学习、深度学习和人工智能的应用是否能改善急性心肌缺血患者的治疗结局？
Cureus. 2023 Aug 5;15(8):e43003. doi: 10.7759/cureus.43003. eCollection 2023 Aug.
10
Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study.机器学习方法揭示的 CAD 患者高 CAD-RADS 评分的风险因素：一项回顾性研究。
PeerJ. 2023 Aug 3;11:e15797. doi: 10.7717/peerj.15797. eCollection 2023.
本文引用的文献
1
Current applications of big data and machine learning in cardiology.大数据与机器学习在心脏病学中的当前应用。
J Geriatr Cardiol. 2019 Aug;16(8):601-607. doi: 10.11909/j.issn.1671-5411.2019.08.002.
2
Machine learning-based coronary artery disease diagnosis: A comprehensive review.基于机器学习的冠状动脉疾病诊断：全面综述。
Comput Biol Med. 2019 Aug;111:103346. doi: 10.1016/j.compbiomed.2019.103346. Epub 2019 Jul 4.
3
Machine Learning Outperforms ACC / AHA CVD Risk Calculator in MESA.机器学习在 MESA 研究中优于 ACC/AHA CVD 风险计算器。
J Am Heart Assoc. 2018 Nov 20;7(22):e009476. doi: 10.1161/JAHA.118.009476.
4
From Machine Learning to Artificial Intelligence Applications in Cardiac Care.从机器学习到人工智能在心脏护理中的应用。
Circulation. 2018 Nov 27;138(22):2569-2575. doi: 10.1161/CIRCULATIONAHA.118.031734.
5
Variable selection - A review and recommendations for the practicing statistician.变量选择——给执业统计学家的一篇综述与建议
Biom J. 2018 May;60(3):431-449. doi: 10.1002/bimj.201700067. Epub 2018 Jan 2.
6
Risk Factors for Coronary Artery Disease: Historical Perspectives.冠状动脉疾病的风险因素：历史视角
Heart Views. 2017 Jul-Sep;18(3):109-114. doi: 10.4103/HEARTVIEWS.HEARTVIEWS_106_17.
7
Can machine-learning improve cardiovascular risk prediction using routine clinical data?机器学习能否利用常规临床数据改善心血管疾病风险预测？
PLoS One. 2017 Apr 4;12(4):e0174944. doi: 10.1371/journal.pone.0174944. eCollection 2017.
8
Global, regional, and national life expectancy, all-cause mortality, and cause-specific mortality for 249 causes of death, 1980-2015: a systematic analysis for the Global Burden of Disease Study 2015.1980 - 2015年全球、区域和国家249种死因的预期寿命、全死因死亡率和死因别死亡率：全球疾病负担研究2015的系统分析
Lancet. 2016 Oct 8;388(10053):1459-1544. doi: 10.1016/S0140-6736(16)31012-1.
9
Predicting the Future - Big Data, Machine Learning, and Clinical Medicine.预测未来——大数据、机器学习与临床医学。
N Engl J Med. 2016 Sep 29;375(13):1216-9. doi: 10.1056/NEJMp1606181.
10
Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges.超越心血管风险预测中的回归技术：应用机器学习解决分析挑战。
Eur Heart J. 2017 Jun 14;38(23):1805-1814. doi: 10.1093/eurheartj/ehw302.
Zotero 插件