呼吸声音数据集，用于检测呼吸系统疾病

呼吸声音数据库，使用录音来检测呼吸系统疾病。呼吸音是呼吸健康和呼吸系统疾病的重要指标。人呼吸时发出的声音与空气流动，肺组织内的变化以及肺内分泌物的位置直接相关。例如，喘息声是患者患有阻塞性气道疾病（如哮喘或慢性阻塞性肺病（COPD））的常见征兆。 可以使用数字听诊器和其他录制技术录制这些声音。这些数字数据开辟了使用机器学习自动诊断呼吸系统疾病（例如哮喘，肺炎和细支气管炎）的可能性。 呼吸声音数据库是由葡萄牙和希腊的两个研究小组创建的。它包括920条带注释的长度不等的记录-10s至90s。这些录音来自126位患者。总共有5.5个小时的录音，包含6898个呼吸循环-1864个包含crack啪声，886个包含wh气，而506个包含crack啪声和喘息。数据包括干净的呼吸声以及模拟现实生活状况的嘈杂录音。患者涵盖所有年龄段-儿童，成人和老年人。 该数据集包括：

The Respiratory Sound Database utilizes audio recordings for the detection of respiratory diseases. Breath sounds are critical indicators of respiratory health and respiratory diseases. The sounds produced during human respiration are directly linked to airflow, changes in lung parenchyma, and the location of secretions within the lungs. For instance, wheezes are common clinical signs of obstructive airway diseases such as asthma and chronic obstructive pulmonary disease (COPD) in patients. These sounds can be captured using digital stethoscopes and other recording techniques. This digital data has enabled the feasibility of using machine learning for automated diagnosis of respiratory diseases including asthma, pneumonia, and bronchiolitis. The Respiratory Sound Database was developed by two research teams from Portugal and Greece. It comprises 920 annotated recordings with variable durations, ranging from 10 seconds to 90 seconds. These recordings were obtained from 126 unique patients, totaling 5.5 hours of audio content, and encompass 6,898 respiratory cycles: 1,864 contain crackles, 886 contain wheezes, and 506 contain both crackles and wheezes. The dataset includes both clean respiratory sounds and noisy recordings that simulate real-world clinical conditions. The patient cohort includes all age groups: children, adults, and the elderly. This dataset includes:

搜集汇总

背景与挑战

背景概述

该呼吸声音数据集包含920条来自126位患者的呼吸录音，总时长达5.5小时，用于检测如哮喘、肺炎等呼吸系统疾病。数据集涵盖了不同年龄段患者的声音特征，包括干净的呼吸声和模拟现实生活状况的嘈杂录音，适用于机器学习自动诊断研究。