相关实验视频

Updated: Jul 15, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

通过机器学习技术进行炎症状态评估,以预测经过过导管大动脉置换治疗的症状性大动脉狭窄症患者的结果

Alexandru Stan^1,2, Paul-Adrian Călburean^1,2, Reka-Katalin Drinkal^1,2

¹Emergency Institute for Cardiovascular Diseases and Transplantation Târgu Mureş, 540136 Târgu Mureş, Romania.

Diagnostics (Basel, Switzerland)

|September 28, 2023

概括

机器学习模型确定了关键的炎症生物标志物,如CRP和WBC数量,作为跨导管大动脉置换 (TAVR) 后不良事件的预测因素. 这些发现可以帮助改善TAVR程序后的患者结果.

科学领域:

心脏病学心脏病学
生物标志物生物标志物
机器学习机器学习

背景情况:

过导管大动脉置换 (TAVR) 改善了严重大动脉狭窄的结果,但长期死亡率仍然令人担忧.
鉴定TAVR后不良事件的预测因素对于改善患者管理至关重要.

研究的目的:

使用机器学习 (ML) 识别预测TAVR后不良事件的炎症生物标志物.
评估单独和与临床参数相结合的炎症生物标志物的预测性能.

主要方法:

对338名接受TAVR治疗的患者进行了回顾性分析,这些患者患有症状严重的大动脉狭窄.
开发了三种ML模型: (a) 仅炎症生物标志物, (b) 炎症生物标志物+年龄,肌素,LVEF, (c) 所有收集的参数.
接收器运行特征曲线下的面积 (AUC-ROC) 和精度回调曲线下的面积 (AUC-PR) 用于评估模型性能.

主要成果:

结合炎症生物标志物的ML模型显示出预测值 (AUC-ROC 0.743). 关键预测因素包括C反应性蛋白 (CRP),白细胞 (WBC) 计数和中性粒细胞与淋巴细胞的比率 (Neu/Lym).
添加临床因素 (年龄,肌素,LVEF) 改善了预测 (AUC-ROC 0.860),LVEF是最重要的,但炎症标志物仍然具有意义.
使用所有数据 (AUC-ROC 0.916) 实现了最佳表现,强调CRP和Neu/Lym比率作为关键预测指标.

结论:

机器学习模型有效地识别了炎症生物标志物,包括CRP,Neu/Lym比率,WBC数量和纤维素素,作为TAVR后不良事件的显著预测因素.
这些生物标志物,特别是CRP和Neu/Lym比率,为接受TAVR的患者提供了有价值的预后信息.
将炎症生物标志物与临床数据相结合,可以更好地预测TAVR后的不良事件.

关键词:

炎症标志物的炎症标志物机器学习是机器学习.通过导管更换大动脉门.

更多相关视频

Technique and Patient Selection Criteria of Right Anterior Mini-Thoracotomy for Minimal Access Aortic Valve Replacement

Technique and Patient Selection Criteria of Right Anterior Mini-Thoracotomy for Minimal Access Aortic Valve Replacement

Published on: March 26, 2018

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia

Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia

Published on: September 22, 2020

相关概念视频

Aortic Regurgitation III: Medical Management

Aortic Regurgitation III: Medical Management

Aortic regurgitation (AR) is when the aortic valve does not close or seal properly, leading to backward blood circulation from the aorta into the left ventricle during diastole. Common causes of AR include rheumatic heart disease, congenital valve defects, and aortic root dilation. Managing AR requires a multifaceted approach to alleviate symptoms, preserve left ventricular function, and address the underlying cause of the regurgitation. Patients with symptomatic AR or significant left...