MIT-BIH Arrhythmia Database
收藏资源简介:
MIT-BIH 心律失常数据库包含 48 个半小时的两通道动态心电图记录摘录,这些记录来自 1975 年至 1979 年间 BIH 心律失常实验室研究的 47 名受试者。从一组 4000 个 24-从波士顿贝斯以色列医院的住院患者(约 60%)和门诊患者(约 40%)的混合人群中收集的小时动态心电图记录;其余 25 个记录是从同一组中选择的,以包括不太常见但具有临床意义的心律失常,这些心律失常在小随机样本中无法很好地表现出来。_x000D_ _x000D_ 记录以每通道每秒 360 个样本的速度数字化,在 10 mV 范围内具有 11 位分辨率。两名或多名心脏病专家独立注释每条记录;解决分歧以获得数据库中包含的每个节拍的计算机可读参考注释(总共大约 110,000 个注释)。_x000D_ _x000D_ 该目录包含整个 MIT-BIH 心律失常数据库。自 1999 年 9 月 PhysioNet 成立以来,该数据库的大约一半(48 条完整记录中的 25 条,以及所有 48 条记录的参考注释文件)已在此处免费提供。剩下的 23 个信号文件仅在 MIT-BIH Arrhythmia 上可用数据库 CD-ROM,于 2005 年 2 月在此处发布。
The MIT-BIH Arrhythmia Database contains 48 half-hour excerpts of two-channel ambulatory electrocardiographic (ECG) recordings, which were obtained from 47 subjects studied in the BIH Arrhythmia Laboratory between 1975 and 1979. A total of 4000 24-hour ambulatory ECG recordings were first collected from a mixed population of inpatients (approximately 60%) and outpatients (approximately 40%) at Boston's Beth Israel Hospital; 25 of the selected recordings were chosen from this cohort to include less common but clinically significant arrhythmias that would be poorly represented in a small random sample. All recordings were digitized at a rate of 360 samples per second per channel, with 11-bit resolution over a 10 mV range. Two or more cardiologists independently annotated each recording; disagreements were resolved to generate computer-readable reference annotations for each heartbeat included in the database, with a total of approximately 110,000 annotations. This archive contains the complete MIT-BIH Arrhythmia Database. Since the establishment of PhysioNet in September 1999, approximately half of the database (25 out of 48 full recordings, plus the reference annotation files for all 48 recordings) has been freely accessible here. The remaining 23 signal files were only available on the MIT-BIH Arrhythmia Database CD-ROM, and were released on this platform in February 2005.

- MIT-BIH Arrhythmia Database首次发表,由麻省理工学院和Beth Israel医院合作创建,旨在为心律失常的研究提供标准化的数据集。
- 该数据集首次应用于心电图(ECG)分析算法的研究,标志着其在医学诊断领域的初步应用。
- MIT-BIH Arrhythmia Database被广泛认可为心律失常研究的标准数据集,成为全球多个研究机构和学术会议的重要参考。
- 随着计算机技术的进步,该数据集开始被用于开发和验证基于机器学习的心律失常检测算法。
- MIT-BIH Arrhythmia Database的数据质量和标准化程度进一步提升,成为心电图分析领域的黄金标准。
- 该数据集继续被广泛应用于最新的心律失常研究和临床诊断工具的开发,推动了医学数据科学的发展。



