Skip to main content
PhysioNet

MIT-BIH Arrhythmia Database

Healthcare & Medical IoT Health & Wearable IoT
1,782 views
2 min read
License
Catalog metadata: This page is a discovery record, not publisher documentation. Verify the description, schema, provenance, version, licence, and citation at the linked source before use.

Catalog Summary

"48 half-hour excerpts of two-channel ambulatory ECG recordings from 47 subjects (1975–1979), digitized at 360 Hz with expert annotations for approximately 110,000 heartbeats, widely used for arrhythmia detection research.[page:2][web:219]"

Catalog Notes

Overview

The MIT-BIH Arrhythmia Database is one of the first publicly available sets of annotated ECG recordings, created by the Beth Israel Hospital (now Beth Israel Deaconess Medical Center) and MIT in 1980 and made fully open on PhysioNet in 2005.[page:2][web:219]

Data Collection

  • 48 half-hour (30-minute) two-channel ambulatory ECG excerpts from 47 subjects studied between 1975 and 1979.[page:2]
  • 23 recordings were chosen randomly from a set of 4,000 24-hour ambulatory ECGs from a mixed inpatient (≈60%) and outpatient (≈40%) population; the remaining 25 were selected to include less common but clinically significant arrhythmias.[page:2]
  • Recordings were digitized at 360 samples per second per channel with 11-bit resolution over a 10 mV range.[page:2]

Annotations

  • Two or more cardiologists independently annotated each record; disagreements were resolved to produce reference annotations for each beat.[page:2]
  • Approximately 110,000 beat annotations in total, labeling normal sinus rhythm, premature ventricular contractions, atrial fibrillation, and many other arrhythmia types.[page:2][web:219]

Use Cases

  • Benchmarking arrhythmia detection algorithms and wearable ECG devices.[page:2][web:219]
  • Training supervised machine learning and deep learning models for cardiac event classification.[page:2]
  • Fundamental research into cardiac dynamics and heart rate variability.[page:2]

License

The PhysioNet page states that this database is available under the Open Data Commons Attribution License v1.0, allowing free use with proper attribution.[page:2]

View Data Structure

To explore column names, data types, and sample rows, visit the official dataset page on PhysioNet.

Preview on PhysioNet

Cite This Dataset

Moody, G. B., & Mark, R. G. (2005). MIT-BIH Arrhythmia Database. [Dataset]. PhysioNet. https://doi.org/10.13026/C2F305

Source metadata: PhysioNet (2005) · DOI: 10.13026/C2F305

Indexed by IoTDataset.com on Jan 29, 2026

Review the Source Record

Confirm the licence, version, access conditions, file format, and provenance at the source before use.

Open Source Page

Related Topics & Keywords

Browse all Healthcare & Medical IoT datasets

Share This Research

More in Healthcare & Medical IoT

View All
Healthcare Other

MIMIC-III-Ext-PPG — ICU Wearable PPG Benchmark [Large-Scale, WFDB Format]

Large-scale quality-assessed ICU PPG benchmark derived from MIMIC-III, with ECG, ABP, and respiration signals in 30-second WFDB segments. Multi-task format supporting cardiovascular and respiratory signal analysis for wearable algorithm development.

Apr 10, 2026
Health & Medical IoT PhysioNet

MIMIC-III Waveform Database

67,830 record sets of multi-channel physiologic waveforms (ECG, ABP, respiration, PPG) and vital sign time series from approximately 30,000 ICU patients, supporting clinical research and ML model development for critical care.

Jan 30, 2026
Healthcare UCI

WESAD — Wearable Stress and Affect Detection [15 Subjects, 700 Hz]

Multimodal physiological dataset from 15 subjects wearing chest and wrist sensors. Includes ECG, EDA, EMG, respiration, temperature, and accelerometry. CSV/pickle format. Used for stress detection and affective computing research.

Apr 10, 2026
Healthcare Government

FDA Wearable Gait Dataset — Synchronized Smartphone IMU & Pressure Walkway [400 Trials]

Open-access wearable gait dataset with 400 CSV files from 20 healthy participants across 5 smartphone orientations and 2 gait trial types. 100 Hz IMU sampling. Used for smartphone-based gait metric validation and wearable sensor accuracy studies.

Apr 10, 2026
Wearable Cardiovascular Health IoT JMIR Cardio / Microsoft Research

Causal Inference for Hypertension Prediction with Wearable Devices - Aurora Project ECG/PPG Dataset

Large public dataset from Microsoft Research Aurora Project with ECG and PPG signals from wrist-worn wearables, balanced for gender, age, and hypertension status, enabling causal inference research for non-invasive blood pressure prediction with 205 extracted features.

Feb 01, 2026
Healthcare Kaggle

Nurse Stress Prediction — Wearable Sensors in Hospital [11.5M Records]

Real-world wearable dataset from 15 nurses over one week in a hospital. Contains 11.5 million entries of EDA, heart rate, skin temperature, and orientation data collected via Empatica E4. CSV format. Used for occupational stress detection research.

Apr 10, 2026

Explore other topics

All topics →