MIT-BIH Noise Stress Test Database

@article{pollard_physionet_2026, title = {{PhysioNet} as a global platform for biomedical research}, volume = {1}, issn = {3005-0693}, url = {https://doi.org/10.1038/s44360-026-00096-z}, doi = {10.1038/s44360-026-00096-z}, abstract = {Twenty-five years after its first public repository was established, the PhysioNet resource for biomedical and clinical data has enabled tens of thousands of research papers. Further efforts are ongoing to advance secure data sharing, community engagement and scalable research infrastructure.}, number = {8}, journal = {Nature Health}, author = {Pollard, Tom and Moody, Benjamin E. and Lehman, Li-wei H. and Gow, Brian J. and Fernandes, Chrystinne and Xie, Chen and Johnson, Alistair and Mark, Roger G. and Heldt, Thomas}, month = aug, year = {2026}, pages = {792--795},}

Abstract

This database includes 12 half-hour ECG recordings and 3 half-hour recordings of noise typical in ambulatory ECG recordings. The noise recordings were made using physically active volunteers and standard ECG recorders, leads, and electrodes; the electrodes were placed on the limbs in positions in which the subjects’ ECGs were not visible.

Data Description

The three noise records were assembled from the recordings by selecting intervals that contained predominantly baseline wander (in record 'bw'), muscle (EMG) artifact (in record 'ma'), and electrode motion artifact (in record 'em'). Electrode motion artifact is generally considered the most troublesome, since it can mimic the appearance of ectopic beats and cannot be removed easily by simple filters, as can noise of other types.

The ECG recordings were created by the script nstdbgen- using two clean recordings (118 and 119) from the MIT-BIH Arrhythmia Database, to which calibrated amounts of noise from record 'em' were added using nst. (The process of making such records is now simpler; the simplified script nstdbgen can be used with current versions of the WFDB software package to recreate these records.) Noise was added beginning after the first 5 minutes of each record, during two-minute segments alternating with two-minute clean segments. The signal-to-noise ratios (SNRs) during the noisy segments of these records are:

Since the original ECG recordings are clean, the correct beat annotations are known even when the noise makes the recordings visually unreadable. The reference annotations for these records are simply copies of those for the original clean ECGs.

Cited by

91 publications cite this project. The most recent are listed below.

• BLiSS: A Beat-Local, Signal-Quality-Informed Kalman Smoother for ECG Denoising under Non-Stationary Muscle Artifact, with Ectopic-Beat Reconstruction Assessment
  Khanh Duy Tran. Research Square, 2026.
• DT4ECG: a subject-aware ECG monitoring framework for joint user attribution and human activity recognition
  Siyu You, Boyuan Gu, Yanhui Yang et al. Biomedical Physics & Engineering Express, 2026.
• Patient and database shift in lightweight ECG arrhythmia classification: a controlled evaluation of noise, quantization, and embedded inference
  Hyun Mok Park, Woojin Cho, Seok-Oh Bang et al. Medical Engineering & Physics, 2026.
• Energy-efficient spiking neural network-based ECG signal quality assessment framework through comparative spike encoding analysis
  Soumen Maity, Manas Rakshit, Goutam Kumar Gupta. Biomedical Signal Processing and Control, 2026.
• Multi-Noise Removal from ECG Signals Using Residual Block-Based Generative Adversarial Networks with Customized Loss Function
  Mohamed Sraitih, Amir Hajjam El Hassani, Younes Jabrane et al. Research Square, 2026.

View all 91 publications

Citation data from OpenAlex. Papers that use the project without citing it may be missing.