PhysioNet/CinC Challenge 2013: Noninvasive Fetal ECG
- Provider
- Ikaro Silva, Joachim Behar, Reza Sameni, Tingting Zhu, Gari D. Clifford, George Moody
- License
- ODC-By-1.0 (source)
- Stored at
- Amazon S3, s3://physionet-open/challenge-2013 (us-east-1)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Physiology
- Source
- https://physionet.org/content/challenge-2013/1.0.0/
About PhysioNet/CinC Challenge 2013: Noninvasive Fetal ECG
The 2013 PhysioNet/Computing in Cardiology Challenge asked for software that detects fetal QRS complexes in multichannel noninvasive abdominal ECG recordings and estimates fetal heart rate, RR intervals and QT intervals. Each one-minute recording includes four noninvasive abdominal signals; reference fetal QRS annotations were produced with the help of a direct fetal scalp ECG that is not available except in the learning set. The open test set B has 100 recordings; set C was kept hidden. Measured 2026-11-13: set-a/ holds 75 records, each as .hea, .dat and .fqrs (reference fetal QRS annotations), with ANNOTATORS and RECORDS files; set-b/ is present, and the top level carries zip and tar.gz bundles of both sets in binary and text form (set-a-text, set-a-ext), the scoring code (physionet2013.m, score-2013.c), sources/ with entries, slides and the CinC papers. Read signals and .fqrs annotations with the wfdb Python package (wfdb.rdrecord, wfdb.rdann) or the text versions with pandas. Useful for fetal ECG extraction, maternal ECG cancellation, blind source separation and fetal heart rate monitoring. Released under the Open Data Commons Attribution License v1.0; cite the challenge paper and the standard PhysioNet reference (Goldberger et al., 2000) when using the data.
How to access PhysioNet/CinC Challenge 2013: Noninvasive Fetal ECG in Python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-east-1', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='physionet-open', Prefix='challenge-2013/', Delimiter='/')Lists the files with anonymous access. Runs on any machine, with no cloud account.
Data structure
Files
Example file: challenge-2013/1.0.0/papers/0149.pdf
Analyze this dataset without downloading it
On Scigantic, PhysioNet/CinC Challenge 2013: Noninvasive Fetal ECG opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Physiology datasets
- EEG Signals from an RSVP Task
- HAR70+: Thigh and Lower-Back Accelerometry of 18 Adults Aged 70 to 95 with Observer-Annotated Daily Activities (NTNU)
- VitalDB Arrhythmia Database: An Anesthesiologist-Validated Large-Scale Intraoperative Arrhythmia Dataset with Beat and Rhythm Labels
- PhysioNet/CinC Challenge 2006: QT Interval Reference Measurements for the PTB Diagnostic ECG Database
- Continuous Cuffless Monitoring of Arterial Blood Pressure via Graphene Bioimpedance Tattoos
- I-CARE: International Cardiac Arrest REsearch consortium Database
- EEG During Mental Arithmetic Tasks
- Human Balance Evaluation Database