The impact of the MIT-BIH Arrhythmia Database

By G. Moody, R. Mark. IEEE Engineering in Medicine and Biology Magazine, 2001

4,611 citations recorded by the source corpus.

Subfields: Cardiology and Cardiovascular Medicine, Surgery

View Paper: https://www.semanticscholar.org/paper/072a0db716fb6f8332323f076b71554716a7271c

How researchers see this paper

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

In Cardiology and Cardiovascular Medicine

In Surgery

Citations in the corpus

Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks (2017, methodology): “The most common dataset used to design and evaluate ECG algorithms is the MIT-BIH arrhythmia database (Moody & Mark, 2001) which consists of 48 half-hour strips of ECG data.”
End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things (2020, background): “2) Electrocardiogram (ECG): MIT-BIH arrhythmia [21] is a popular dataset for ECG signal classification or arrhythmia diagnosis detection models.”
Multiparameter Intelligent Monitoring in Intensive Care Ii (Mimic-Ii): A Public-Access Intensive Care Unit Database (2011, methodology): “For example, the ECG database that supported development and evaluation of automated arrhythmia algorithms included much smaller data collections (48 half-hour samples in the MIT-BIH Arrhythmia Database [21], and 80 3-hour records in the AHA ECG Database) [23].”
ECG-based heartbeat classification for arrhythmia detection: A survey (2016, background): “It was also the first database available for this goal and has been constantly refined along the years [148].”
Leveraging Fog Computing for Healthcare IoT (2018, methodology): “The algorithm of ECG signal processing for Q, R and T wave extraction is applied on MIT-BIT Arrhythmia database [45].”
ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network (2019, methodology): “Five types of ECG signals, of which the sampling rate was uniformly set as 360 Hz, were obtained from the MIT-BIH arrhythmia database [31].”
ECG Heartbeat Classification: A Deep Transferable Representation (2018, methodology): “In this paper, we use PhysioNet MIT-BIH Arrhythmia and PTB Diagnostic ECG Databases as data source for labeled ECG records [15], [16], [17].”
Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals (2016, methodology): “The source of the ECG records used in this study is the MIT-BIH arrhythmia database (Moody and Mark, 2001).”
Evaluation of a decided sample size in machine learning applications (2023, methodology): “The dataset was developed to evaluate and design algorithms for detecting arrhythmia by the Beth Israel Hospital Arrhyth-mia Laboratory between 1975 and 1979 [51, 52].”
Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets (2021, methodology): “[41] designed a six-layered 1D CNN to classify different types of cardiac arrhythmias consisting of an input layer, two convolutional layers, two down-sampling layers, one fully-connected layer and an output layer, using the MIT-BIH Arrhythmia Database [42,43].”
Deep Learning for Time Series Anomaly Detection: A Survey (2022, neutral): “Electrocardiography (ECG) signals are frequently used to assess the health of the heart.”
On handling negative transfer and imbalanced distributions in multiple source transfer learning (2014, methodology): “The data sets in the CAD problem come from MIT-BIH database [11].”