机器学习可以根据传统的风险因素,冠状动脉和心上脂肪体积预测血液动力学显著的CAD
Wenji Yu1, Le Yang1, Feifei Zhang1
1Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow University, Institute of Clinical Translation of Nuclear Medicine and Molecular Imaging, Soochow University, No.185, Juqian Street, Changzhou, 213003, Jiangsu, China.
一个可解释的机器学习模型有效地使用传统的风险因素,冠状动脉 (CAC) 和心上脂肪体积 (EFV) 选出血动力学显著的冠状动脉疾病 (CAD). 这种方法提供了高度准确的个性化风险预测.
科学领域:
- 心脏病学 心脏病学
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 冠状动脉疾病 (CAD) 的诊断依赖于侵入性手术.
- 像CT扫描这样的非侵入性成像为早期查提供了潜在的可能性.
- 可解释的人工智能可以提高预测模型的解释性.
研究的目的:
- 开发一种可解释的机器学习 (ML) 模型,用于选血液动力学上显著的CAD.
- 将传统的风险因素,冠状动脉 (CAC) 和心表脂肪体积 (EFV) 整合到ML模型中.
- 提供个性化的风险预测,并提供透明的解释.
主要方法:
- 利用了来自184名接受SPECT/MPI和ICA治疗的症状性住院患者的数据.
- 从非对比CT扫描中收集的临床数据,CAC和EFV.
- 采用递归特征消除 (RFE) 和XGBoost分类器,经过SHapley添加式扩展 (SHAP) 验证.
主要成果:
- 在XGBoost模型中,测试队列中的AUC达到0.89.
- 确定的主要预测因素是EFV,CAC,糖尿病,高血压和高脂血症.
- 该模型表现出高灵敏度 (68.0%),特异性 (96.8%) 和精度 (83.9%).
结论:
- 一个集成EFV和CAC的可解释的ML模型显示了对非侵入性评估血液动力学显著CAD的承诺.
- 该模型提供准确和可解释的风险预测,有助于临床决策.
- ML与SHAP相结合,可以为CAD提供透明,个性化的风险评估.
更多相关视频
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
06:16Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
相关概念视频
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
Coronary Artery Disease I: Introduction
Coronary Artery Disease IV: Preventive Measures
Atherosclerosis II: Clinical Manifestations and Diagnostic Tests
Acute Coronary Syndrome III: Diagnostic Studies
Imaging Studies for Cardiovascular System III: X-Ray
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...
