相关实验视频

Updated: Jan 13, 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

深度神经网络的比较,用于对偶然的肺声音进行分类

Said Polanco-Martagón¹, Yahir Hernández-Mier¹, Marco Aurelio Nuño-Maganda¹

¹Intelligent Systems Department, Universidad Politécnica de Victoria, Ciudad Victoria 87138, Tamaulipas, Mexico.

Journal of clinical medicine

|October 29, 2025

概括

对于肺部声音分类的深度学习模型对呼吸道疾病查有很大的希望. 虽然ResNet152V2实现了高特异性,但新的双流网络提供了更平衡的性能,突出了提高临床应用中的灵敏度的必要性.

科学领域:

人工智能的人工智能
医学诊断医学诊断医学诊断
呼吸系统医学呼吸系统医学

背景情况:

深度学习模型通过自动肺声分类提供客观的呼吸道疾病查.
在不平衡的临床数据集上评估模型性能存在重大挑战.
本研究研究了卷积神经网络 (CNN) 架构,并引入了双流分类方法.

研究的目的:

为了比较各种预训练CNN架构的性能,用于偶然的肺声分类.
开发和评估一个新的双流网络,以解决阶级不平衡和提高分类性能.
评估呼吸道疾病查深度学习模型中灵敏度和特异性之间的权衡.

主要方法:

利用公开的ICBHI 2017数据集进行模型培训和评估.
我们比较了五个预训练的CNN架构:VGG16,VGG19,InceptionV3,MobileNetV2和ResNet152V2.2.
实施了数据增强技术 (音调转移,随机转移,混合) 和一个新的VGGish双流网络.

主要成果:

ResNet152V2获得了最高的平均分数 (AS) 0.541,具有高特异性 (0.67),但敏感性低 (0.41).
拟议的VGGish双流网络表现出更平衡的性能,AS为0.508.
基准模型接近最先进的性能,但显示出偏向于特异性而不是灵敏性.

结论:

像ResNet152V2这样的标准CNN提供了竞争力的性能,但由于敏感度低,可能会错过病理事件.
双流网络提供了更平衡的分类,但需要进一步优化.
未来的研究必须优先考虑提高模型对临床安全和呼吸道诊断中的实用性敏感性的策略.

关键词:

一些冒险的声音.深度学习是一种深度学习.双流神经网络是一个双流神经网络.

更多相关视频

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

相关概念视频

Physical Assessment of the Respiratory Tract IV: Auscultation

Physical Assessment of the Respiratory Tract IV: Auscultation

Auscultation is a crucial component of the physical assessment of the respiratory tract. It offers valuable insights into airflow through the bronchial tree and potential lung obstructions. This process involves careful listening to breath, voice, and adventitious sounds, which can reveal a wealth of information about a patient's respiratory health.
Breath Sounds
Breath sounds are categorized into vesicular, bronchovesicular, and bronchial.

Assessment of Respiration

Assessment of Respiration

The respiratory system's basic structures and primary functions lay the foundation for nurses' comprehensive respiratory assessments. This assessment includes subjective and objective data to gauge the patient's respiratory health.
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like...