Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Pulmonary Hypertension: Classification and Pathogenesis

Pulmonary Hypertension: Classification and Pathogenesis

Pulmonary hypertension (PH) is a severe health condition in which the mean pulmonary arterial pressure increases to 25 mmHg or more, even when the body is at rest. This high pressure in the blood vessels that transport blood from the heart to the lungs can cause various symptoms, including shortness of breath, can lead to right heart failure, and significantly affect the overall quality of life.
There are various classifications for PH, each relating to different underlying causes and also...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Utility of a novel point-of-care test in detecting coronary artery disease following negative nuclear testing: a case series.

European heart journal. Case reports·2026

Same author

Clinical validation of a machine-learned, point-of-care system to IDENTIFY pulmonary hypertension.

ERJ open research·2025

Same author

Facilitating Earlier Diagnosis of Pulmonary Hypertension Using a Novel Noninvasive Diagnostic.

JACC. Case reports·2025

Same author

Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease.

Journal of visualized experiments : JoVE·2024

Same author

Machine Learning Algorithms: Selection of Appropriate Validation Populations for Cardiology Research-Be Careful!

JACC. Advances·2024

Same author

Clinical Validation of a Machine-Learned, Point-of-Care System to IDENTIFY Functionally Significant Coronary Artery Disease.

Diagnostics (Basel, Switzerland)·2024

Search research articles

相关实验视频

Updated: Jun 26, 2025

Establishment and Validation of a Rat Model of Pulmonary Arterial Hypertension Associated with Pulmonary Fibrosis

Establishment and Validation of a Rat Model of Pulmonary Arterial Hypertension Associated with Pulmonary Fibrosis

Published on: May 23, 2025

在护理点使用机器学习算法非侵入性检测肺高血压.

Navid Nemati¹, Timothy Burton¹, Farhad Fathieh¹

¹Analytics for Life, Toronto, ON M5X 1C9, Canada.

Diagnostics (Basel, Switzerland)

|May 11, 2024

概括

这项研究开发了一种机器学习模型,使用非侵入性信号来诊断肺高血压 (PH). 该模型显示高精度,为早期检测和干预提供了潜力.

关键词:

人工智能的人工智能是人工智能.数字健康数字健康前线前线的第一线.医疗中心的关心点肺高血压是一种肺高血压.

更多相关视频

Increasing Pulmonary Artery Pulsatile Flow Improves Hypoxic Pulmonary Hypertension in Piglets

Increasing Pulmonary Artery Pulsatile Flow Improves Hypoxic Pulmonary Hypertension in Piglets

Published on: May 11, 2015

Invasive Hemodynamic Assessment for the Right Ventricular System and Hypoxia-Induced Pulmonary Arterial Hypertension in Mice

Invasive Hemodynamic Assessment for the Right Ventricular System and Hypoxia-Induced Pulmonary Arterial Hypertension in Mice

Published on: October 24, 2019

相关实验视频

Last Updated: Jun 26, 2025

Establishment and Validation of a Rat Model of Pulmonary Arterial Hypertension Associated with Pulmonary Fibrosis

Establishment and Validation of a Rat Model of Pulmonary Arterial Hypertension Associated with Pulmonary Fibrosis

Published on: May 23, 2025

Increasing Pulmonary Artery Pulsatile Flow Improves Hypoxic Pulmonary Hypertension in Piglets

Increasing Pulmonary Artery Pulsatile Flow Improves Hypoxic Pulmonary Hypertension in Piglets

Published on: May 11, 2015

Invasive Hemodynamic Assessment for the Right Ventricular System and Hypoxia-Induced Pulmonary Arterial Hypertension in Mice

Invasive Hemodynamic Assessment for the Right Ventricular System and Hypoxia-Induced Pulmonary Arterial Hypertension in Mice

Published on: October 24, 2019

科学领域:

医学研究医学研究
心血管诊断心血管诊断
医学中的人工智能.

背景情况:

肺高血压 (PH) 诊断是具有挑战性的,因为其复杂的性质和重叠的症状与其他心血管疾病.
非侵入性诊断方法对于早期检测和治疗PH至关重要.

研究的目的:

开发和验证一个监督机器学习模型,用于肺高血压的非侵入性诊断.
通过直角电压梯度和光聚光学信号来评估模型的性能.

主要方法:

一个受监督的机器学习模型被训练,使用从非侵入性的直角电压梯度和光聚光学信号中提取的3298个特征.
用灵敏度,特异性和接收器操作员特征曲线 (AUC-ROC) 下的区域来评估模型性能.
进行了特征重要性分析,以确定对模型预测能力的关键贡献者.

主要成果:

开发的模型实现了87%的灵敏度和83%的特异性,AUC-ROC为0.93.
在不同性别,年龄组和肺高血压类别中观察到一致的表现.
分析发现导电,再极化和呼吸指标的变化是重要的预测因素.

结论:

机器学习模型显示了肺高血压的准确,非侵入性诊断的巨大潜力.
这种方法可以促进早期检测和及时干预,当集成到 point-of-care诊断系统时.