← 返回项目详情
此成果详情页已在新标签打开。查看完成后，可关闭当前标签返回原项目页，也可以点击“返回项目详情”。网页不会强制关闭浏览器标签。
成果详情 / 项目说明与报告
四记录 R 峰技术预研报告
原始文件名report.md
- 内容说明
- 完整说明 MIT-BIH/PhysioNet 来源、MLII 与 360 Hz 信号条件、±150 ms/±54 samples 一对一匹配、TP 9092、FP 28、FN 18 和 46 个错误事件。
- 能够证明
- 支持该固定四记录技术基线的协议、结果和 Build 544c45cd1dbe33d85a5de8184c5594061a5fb605。
- 不能证明
- 不证明临床准确率、诊断能力、医疗器械性能、完整数据库表现或导师批准。
- 许可说明
- CC BY 4.0 国际署名许可（自行编写的预研报告）；原始数据遵循 ODC Attribution 1.0
- 来源和脱敏说明
- 来自 MIT-BIH 公开预研包的既有报告；本 Goal 不重跑 detector、benchmark 或 Notebook。
预览
站内查看方式
以 Markdown 安全文本预览，页面同时显示不可替代医生诊断的提示。
# Four-record technical report
The study references the MIT-BIH Arrhythmia Database, PhysioNet, version 1.0.0, DOI 10.13026/C2F305, under the Open Data Commons Attribution License 1.0. The four records are 100, 105, 118, and 119. MLII is the primary ECG lead and the sampling rate is 360 Hz.
The public result preserves the established R-peak baseline and its deterministic one-to-one matching rule. The evaluation window is ±150 ms, equivalent to ±54 samples at 360 Hz. This package does not rerun the detector, benchmark, or notebook.
TP=9092, FP=28, FN=18. The error-stratification Build contains 46 event figures, 16 reciprocal counterpart pairs, and 32 linked events. Errors are concentrated in record 105 (44 of 46 events) and record 119 has 2 events. The canonical Build is 544c45cd1dbe33d85a5de8184c5594061a5fb605.
These values describe a bounded engineering pre-study on four public records. They do not establish clinical accuracy, diagnosis capability, medical-device performance, or generalization to the full database or a patient population.
本项目仅供教学、实验和辅助分析，不可替代医生诊断。
公开包完整性
SHA-256 摘要
48b0308df1189bf7525d86c39cc2d7431d08385223cd0a924fcdbd3a66cce522