相关实验视频

Updated: Jan 7, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

可解释的机器学习模型用于AECOPD患者的一年再入院风险预测:将缓解特征选择与样本增大相结合

Yuanyuan Huang¹, Tianpu Feng², Xiaoxue Song³

¹Department of Emergency Medicine, The Affiliated Lianyungang Hospital of Xuzhou Medical University, No. 6 Zhenhua Road, Lianyungang, Jiangsu, 222000, China.

BMC infectious diseases

|December 30, 2025

概括

这项研究开发了一种XGBoost模型,用于预测慢性阻塞性肺病 (AECOPD) 急性恶化患者的再入院风险. 数据增强改善了模型性能,识别了早期干预的关键预测因素.

科学领域:

肺部医学肺部医学
医疗保健中的人工智能
生物统计学生物统计学

背景情况:

患有慢性阻塞性肺病 (AECOPD) 急性恶化症的患者有重新入院的高风险.
准确预测再入院对于有效的患者管理至关重要.
现有的预测模型面临诸如小样本大小和数据问题等挑战.

研究的目的:

为AECOPD患者开发和验证一个强大的再接收风险预测模型.
用先进的数据增强技术解决临床预测模型中的挑战.
为了确定与AECOPD再接收相关的关键临床变量.

主要方法:

从2018年12月到2023年7月对AECOPD患者进行的回顾性研究.
用链式方程 (MICE) 计算缺少数据的多重计算.
条件生成对抗网络 (CTGAN) 用于数据增强.
XGBoost使用SHAP进行模型开发和评估,以提高可解释性.

主要成果:

包括1960名患者;39.9%的人重新入院.
CTGAN数据增强改善了模型的概括性,并减轻了过度拟合.
XGBoost模型实现了0.696的AUC,其中的关键预测因素包括乙酸细胞计数,ICU入院,RDW-SD,PNI和PLR.

结论:

使用常规临床数据开发了一种经过验证的AECOPD再接收风险模型.
CTGAN数据增强显著提高了模型性能.
可解释的XGBoost模型可以帮助识别高风险患者进行早期干预.

关键词:

慢性阻塞性肺病的急性恶化.有条件的生成对抗网络.数据增强数据增强机器学习是机器学习.模型的解释性模型的解释性再接收预测预测重新接收

更多相关视频

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

相关概念视频

Receiver Operating Characteristic Plot

Receiver Operating Characteristic Plot

A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...