数据增强变换在XGBoost中对于CVD预测具有重要意义
Shuai Chang1, Xiangyu Wang1, Yu Luo2
1Department of Physical Education, Capital Normal University, Beijing, 100048, China.
Scientific reports
|November 25, 2025
概括
数据增强显著改变了用于心血管疾病 (CVD) 预测的机器学习模型,更改了特征的重要性,而不是准确性. 评估合成数据的评估
科学领域:
- 心血管疾病研究研究
- 机器学习在医学中的应用
- 数据科学数据科学数据科学
背景情况:
- 机器学习模型对于心血管疾病 (CVD) 预测至关重要.
- 数据集大小和类不平衡往往限制了模型的性能.
- 数据增强对模型可解释性和特征重要性的影响不太清楚.
研究的目的:
- 调查数据增强策略如何影响CVD预测的极端梯度增强 (XGBoost) 模型的性能和特征重要性.
- 为了比较合成少数群体过量采样技术 (SMOTE) 和瓦斯斯坦生成对抗网络与梯度惩罚 (WGAN-GP) 的增强效应.
主要方法:
- 使用公开的CVD数据集进行了废除研究.
- 我们比较了三个XGBoost模型:基线 (原始数据),SMOTE增强和WGAN-GP增强.
- 模型性能使用准确度,F1得分和AUC进行评估;特征重要性使用增益指标进行评估.
主要成果:
- 所有模型都显示出高预测性能;SMOTE增强模型实现了1.0的准确性和AUC.
- 数据增强显著改变了特征重要性排名.
- "斜率"成为增强模型 (SMOTE:增益27.49,WGAN-GP:增益36.68) 中的主导特征,与基线模型 (增益7.01) 不同.
结论:
- 数据增强可以重塑机器学习模型的预测策略.
- 对于高质量的数据集,增强可能会重新优先考虑特征,而不是仅仅提高准确性.
- 在临床应用之前,评估合成数据对模型解释性的影响至关重要.
相关概念视频
Blood Studies for Cardiovascular System I: Cardiac Biomarkers
769
Cardiac biomarkers are enzymes, proteins, and hormones released into the blood when cardiac cells are injured. They are powerful tools for triaging.
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
769
Survival Tree
374
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
374
Coronary Artery Disease I: Introduction
857
Coronary Artery Disease (CAD): An Overview with Scientific InsightsCoronary Artery Disease (CAD), often referred to as C-A-D, is a prevalent blood vessel disorder classified under the broader category of atherosclerosis. Atherosclerosis is a pathological process characterized by the hardening and narrowing of arteries due to the accumulation of atherosclerotic plaques. These plaques are composed of cholesterol, fatty substances, inflammatory cells, calcium, and fibrin, reducing blood flow to...
857
Cardiovascular Drugs: Classification based on Therapeutic Indications
4.0K
Cardiovascular diseases, encompassing a range of conditions, can significantly affect the heart's operations and the overall circulatory system. These conditions impair the heart's ability to pump blood, leading to a deficit in oxygen supply to crucial organs. Anomalies in the heart's electrical system, known as arrhythmias, can cause heartbeats to accelerate or slow down. Usually, heart rates increase during physical activity and decrease while resting or sleeping. However,...
4.0K
Imaging Studies for Cardiovascular System III: X-Ray
455
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
455
Cardiac Output and Stroke Volume
4.3K
Cardiac output (CO) is an integral aspect of human physiology, reflecting the heart's efficiency and responsiveness to the body's needs. It represents the volume of blood that the left or right ventricle ejects into the aorta or pulmonary trunk each minute. The CO is calculated by multiplying the heart rate (HR)—the number of heartbeats per minute—by the stroke volume (SV)—the amount of blood pumped out with each heartbeat.
In an average resting adult male, the typical cardiac...
In an average resting adult male, the typical cardiac...
4.3K

