Cuff-Less Blood Pressure Estimation (Cuff-Less Blood Pressure Estimation. Pre-processed and cleaned vital signals for cuff-less BP estimation.)

数据集信息:
该数据集的主要目标是为设计无袖带血压估计算法提供干净有效的信号。原始心电图 (ECG)，光电容积描记仪 (PPG) 和动脉血压 (ABP) 信号最初是从th e physionet.org收集的，然后对其进行一些预处理和验证。(有关该过程的更多信息，请参阅我们的论文)
属性信息:
该数据库由矩阵的单元格数组组成，每个单元格是一个记录部分。在每个矩阵中，每行对应一个信号通道:
1: PPG信号，FS = 125Hz; 来自指尖的光电容积描记仪
2: ABP信号，FS = 125Hz; 有创动脉血压 (mmHg)
3: 心电信号，FS = 125Hz; 来自通道II的心电图
注意: 数据集被分成多个部分，以便更容易在内存低的机器上加载。每个单元格都是一个记录。每个患者可能有多个记录 (无法区分)。但是，同一患者的记录彼此相邻。建议进行N倍交叉测试和火车，以减少火车被测试患者污染的机会。

Dataset Information:
The primary goal of this dataset is to provide clean and valid signals for developing cuffless blood pressure estimation algorithms. Raw electrocardiogram (ECG), photoplethysmography (PPG) and arterial blood pressure (ABP) signals were initially collected from physionet.org, followed by preprocessing and validation procedures. For more details about this process, please refer to our paper.

Attribute Information:
This database consists of a cell array of matrices, where each cell represents a recording segment. Within each matrix, each row corresponds to a signal channel:
1. PPG signal, sampling rate FS = 125 Hz; photoplethysmography acquired from the fingertip
2. ABP signal, sampling rate FS = 125 Hz; invasive arterial blood pressure (unit: mmHg)
3. ECG signal, sampling rate FS = 125 Hz; electrocardiogram from lead II

Note: The dataset is split into multiple segments to make it easier to load on machines with limited memory. Each cell corresponds to one recording. A single patient may have multiple recordings, but these are indistinguishable — that is, it is not possible to determine which recordings belong to the same patient. However, recordings from the same patient are stored adjacently. It is recommended to conduct N-fold cross-training and testing to reduce the risk of data leakage, where the training dataset is contaminated by samples from test patients.

搜集汇总

背景与挑战

背景概述

该数据集提供了预处理后的心电图、光电容积描记仪和动脉血压信号，用于无袖带血压估计算法的开发。数据集由多个记录部分组成，每个部分包含不同信号通道的数据，采样频率为125Hz，适合在内存有限的机器上使用。