对加拿大队列中的心血管疾病风险分层和生存分析的深度学习方法
Mrinalini Bhagawati1, Sudip Paul1, Laura Mantella2
1Department of Biomedical Engineering, North-Eastern Hill University, Shillong, India.
The international journal of cardiovascular imaging
|April 27, 2024
概括
与传统的机器学习方法相比,深度学习模型分析状斑块特征,特别是内新血管化 (IPN),显著改善了冠状动脉疾病 (CAD) 和心血管 (CV) 事件的预测.
科学领域:
- 心血管成像和诊断系统
- 人工智能在医学中的应用
- 对心血管疾病的预测分析.
背景情况:
- 耳斑量化是评估心血管疾病 (CVD) 和冠状动脉疾病 (CAD) 风险的标准方法.
- 现有的风险预测方法存在局限性,这促使人们探索先进的分析技术.
研究的目的:
- 评估深度学习 (DL) 模型在预测CAD概率和心血管 (CV) 事件中的有效性.
- 将DL模型的性能与风险分层的传统机器学习 (ML) 方法进行比较.
- 为了确定特定的带斑块特征,这些特征是CV事件的显著预测因素.
主要方法:
- 利用了459名接受冠状动脉血管造影和大脑动脉超声波的患者的数据,测量了最大斑块高度 (MPH),总斑块面积 (TPA),大脑动脉内膜介质厚度 (cIMT) 和内膜新血管化 (IPN).
- 应用了八个基于DL的模型用于CAD风险和CV事件分层.
- 进行单变量和多变量分析以确定关键风险预测因素.
- 使用曲线下的面积评估了DL模型的有效性,并将CV事件预测与Cox比例危险模型 (CPHM) 和基于DL的一致性指数 (c-index) 进行了比较.
主要成果:
- 内板内新血管化 (IPN) 显示出对心血管事件的显著预测能力 (p < 0.0001).
- 性能最好的DL系统比最好的ML系统 (0.929对0.762) 有21%的改进.
- 基于DL的CV事件预测与CPHM (0.86对0.73) 相比,实现了~17%更高的c指数.
- 动脉成像特征,特别是IPN,与CAD和CV事件有很强的关联.
结论:
- 基于深度学习的系统在预测CAD和CV事件方面明显优于基于ML的模型.
- DL模型提供了一种优越的方法,用于使用动脉成像数据进行生存分析和CAD风险预测.
- IPN是预测心血管风险的关键成像生物标志物.
相关概念视频
Genome-wide Association Studies-GWAS
13.4K
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
13.4K
Cancer Survival Analysis
345
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
345


