Machine Learning Methods in Real-World Studies of Cardiovascular Disease - Review

Aug 5, 2026

Upload by Himbo

Cardiovascular disease (CVD) remains a leading cause of death, creating urgent needs for risk identification and prognosis prediction. Real-world studies provide large observational bases but are limited by high dimensionality and missing or unstructured data. This review summarizes supervised and unsupervised machine learning methods for data governance, high-dimensional analysis, and imputation, outlining key strengths, limitations, and applications with an example using random forests.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Objective

Methods

Conclusion

Keywords

Introduction

Cardiovascular Innovations and Applications Vol. 7 (2023) 25 ISSN 2009-8618 DOI 10. 15212/CVIA.2023.0011 REVIEW ARTICLE Machine Learning Methods in Real-World Studies of Cardiovascular Disease Jiawei Zhou1,a, Dongfang You1,a, Jianling Bai1, Xin Chen1, Yaqian Wu1, Zhongtian Wang1, Yingdan Tang1, Yang Zhao1 and Guoshuang Feng2,3 1Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, Jiangsu 211166, China 2Big Data Center, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, Beijing 100045, China 3Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University & Capital Medical University, Beijing 100083, China Received: 6 November 2022; Revised: 5 February 2023; Accepted: 13 February 2023 Abstract Objective: Cardiovascular disease (CVD) is one of the leading causes of death worldwide, and answers are urgently needed regarding many aspects, particularly risk identification and prognosis prediction. Real-world studies with large numbers of observations provide an important basis for CVD research but are constrained by high dimensionality, and missing or unstructured data. Machine learning (ML) methods, including a variety of supervised and unsupervised algorithms, are useful for data governance, and are effective for high dimensional data analysis and imputation in realworld studies. This article reviews the theory, strengths and limitations, and applications of several commonly used ML methods in the CVD field, to provide a reference for further application. Methods: This article introduces the origin, purpose, theory, advantages and limitations, and applications of multiple commonly used ML algorithms, including hierarchical and k-means clustering, principal component analysis, random forest, support vector machine, and neural networks. An example uses a random forest on the Systolic Blood Pressure Intervention Trial (SPRINT) data to demonstrate the process and main results of ML application in CVD. Conclusion: ML methods are effective tools for producing real-world evidence to support clinical decisions and meet clinical needs. This review explains the principles of multiple ML methods in plain language, to provide a reference for further application. Future research is warranted to develop accurate ensemble learning methods for wide application in the medical field. Keywords: Cardiovascular disease; Machine learning; Real-world study Introduction Cardiovascular disease (CVD) is the leading cause of death worldwide, killing 17.9 million people each aJiawei Zhou and Dongfang You contributed equally to this work. Correspondence: Yang Zhao, PhD, Department of Biostatistics, School of Public Health, Nanjing Medical University, 101 Longmian Avenue, Nanjing, Jiangsu 211166, China, E-mail: [yzhao@njmu.edu.cn](yzhao@njmu.edu.cn) ; and year [1] . Many randomized clinical trials (RCTs) are conducted to evaluate the efficacy and safety of CVD treatment interventions, as well as primary and secondary prevention of CVDs, including Guoshuang Feng, PhD, Big Data Center, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health, 56 Nanlishi Road, Xicheng District, Beijing 100045, China, E-mail: [glxfgsh@163.com](glxfgsh@163.com) © 2023 Cardiovascular Innovations and Applications. Creative Commons Attribution-NonCommercial 4.0 International License 2 J. Zhou et al. , Review of Machine Learning Methods in CVD drugs such as statins [2, 3] and polypills [4], dietary interventions (such as the Mediterranean diet and dietary supplements [5–7]), and behaviors [8] or lifestyles (such as weight loss [9]) . The importance of RCTs with large sample sizes is well-recognized. Although RCTs generate the most credible and highest-level evidence for assessing the prevention and treatment effects of CVD, their applications are limited by cost, duration, lack of generalizab

FAQs

What is the main goal of using machine learning in real-world cardiovascular disease studies?

To support risk identification and prognosis prediction by handling challenges in real-world data such as high dimensionality and missing or unstructured information.

Which machine learning algorithms are discussed in the review?

The review covers hierarchical and k-means clustering, principal component analysis, random forest, support vector machine, and neural networks.

How does the review demonstrate real-world ML application in CVD?

It provides an example applying a random forest to SPRINT data to illustrate the process and main results of ML use.

Aug 5, 2026

Upload by Himbo