PhysioNet/CinC Challenge 2018: You Snooze You Win (Sleep Arousal Detection)

Provider
Mohammad Ghassemi, Benjamin Moody, Li-wei Lehman, Roger Mark, Gari D. Clifford
License
ODC-By-1.0 (source)
Stored at
Amazon S3, s3://physionet-open/challenge-2018 (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.13026/6phb-r450
Category
Physiology
Source
https://physionet.org/content/challenge-2018/1.0.0/

About PhysioNet/CinC Challenge 2018: You Snooze You Win (Sleep Arousal Detection)

The 2018 PhysioNet/Computing in Cardiology Challenge asked for algorithms that detect non-apnea sleep arousals in overnight polysomnography (PSG). The data come from 1,985 subjects monitored at the Massachusetts General Hospital (MGH) sleep laboratory for diagnosis of sleep disorders. Signals include electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), electrocardiography (ECG) and oxygen saturation (SaO2), all sampled at 200 Hz (SaO2 resampled to 200 Hz). Clinical staff annotated sleep stages following the AASM manual, and certified sleep technologists annotated arousals. Each record has a .mat signal file and .hea header in WFDB format, a .arousal annotation file in WFDB annotation format, and an arousal .mat target file. Measured 2026-11-13: training/ holds 994 per-subject folders (for example tr03-0005), test/ holds the test subjects without labels, and age-sex.csv, RECORDS, score2018.py and sample entries are at the top level. Read signals with wfdb.rdrecord, annotations with wfdb.rdann and arousal targets with scipy.io.loadmat. Useful for sleep arousal detection, sleep staging, PSG deep learning and respiratory event research. 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 this dataset 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-2018/', Delimiter='/')

Lists the files with anonymous access. Runs on any machine, with no cloud account.

Data structure

Files

Example file: challenge-2018/1.0.0/papers/CinC2018-040.pdf

Analyze this dataset without downloading it

On Scigantic, PhysioNet/CinC Challenge 2018: You Snooze You Win (Sleep Arousal Detection) 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