Physionet: components of a new research resource for complex physiologic signals

By A. Goldberger, L. N. A. Amaral, Leon Glass, Shlomo Havlin, J. M. Hausdorg, Plamen Ch. Ivanov, R. G. Mark, J. Mietus, George B. Moody, Chung-Kang Peng and 2 more. 2000

8,302 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning Credible Models (2017, methodology): “To further validate our approach, we turn to a publicly available benchmark dataset from PhysioNet [9].”
GRAM: Graph-based Attention Model for Healthcare Representation Learning (2016, methodology): “2) MIMIC-III dataset (Johnson et al., 2016; Goldberger et al., 2000), which is a publicly available dataset consisting of medical records of 7.5K intensive care unit (ICU) patients over 11 years.”
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks (2017, methodology): “…health organization, which consists of 10-years of longitudinal medical records of 258K patients, B) the MIMIC-III dataset (Johnson et al., 2016; Goldberger et al., 2000), which is a publicly available dataset consisting of the medical records of 46K intensive care unit (ICU) patients over 11…”
Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks (2017, methodology): “We construct a dataset 500 times larger than other datasets of its kind (Moody & Mark, 2001; Goldberger et al., 2000).”
Deep Learning on 1-D Biosignals: a Taxonomy-based Survey (2018, methodology): “Similarly, Rahhal et al., [44] validated their method on two other databases, namely the St. Pe-tersburg Institute of Cardiological Technics (INCART) database [112] and the supra-ventricular arrhythmia database (SVDB) [113].”
Quick and Easy Time Series Generation with Established Image-based GANs (2019, methodology): “1 Data Collection The data used in this experiment was gathered from PhysioNet [4] and generated using a sinusoidal generator.”
An Attention-Based Deep Learning Approach for Sleep Stage Classification With Single-Channel EEG (2021, methodology): “Sleep-EDF-20 and Sleep-EDF-78 were obtained from the PhysioBank [36].”
Synthesis of Realistic ECG using Generative Adversarial Networks (2019, methodology): “In this work, we focus on synthesising the lead II signal of normal ECG as found in the MIT-BIH Arrhythmia Database [9, 10].”
Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing (2022, methodology): “We conduct experiments on the MIMIC-CXR v2 [34,24] chest radio-graph dataset, which provides 227,835 imaging studies with associated radiology reports for 65,379 patients, all collected in routine clinical practice.”
A review of channel selection algorithms for EEG signal processing (2015, methodology): “…database (6 patients: 1, 3, 6, 7, 10, 22) which is a scalp EEG database with a 256 Hz sampling rate and more than 22 channels for most of them [23], and National Taiwan University Hospital database (one patient) which is also a scalp EEG database with 200 Hz sampling rate and 18 channels [24].”
A Multivariate Approach for Patient-Specific EEG Seizure Detection Using Empirical Wavelet Transform (2017, methodology): “Long-duration EEG signal records studied in this paper have been collected from PhysioNet [22] CHB-MIT scalp EEG database (website: https://physionet.org/physiobank/ database/chbmit/), which is described in [23].”
Cuffless Blood Pressure Estimation Algorithms for Continuous Health-Care Monitoring (2017, methodology): “Consequently, compared to original signals, down-sampled signals might have at most about 8 ms time jitter [20].”