NM000225: eeg dataset, 1983 subjects#

PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)

Access recordings and metadata through EEGDash.

Citation: Mohammad M. Ghassemi, Benjamin E. Moody, Li-wei H. Lehman, Christopher Song, Qiao Li, Haoqi Sun, Roger G. Mark, M. Brandon Westover, Gari D. Clifford (2018). PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training). 10.13026/6phb-r450

Modality: eeg Subjects: 1983 Recordings: 1983 License: Open Data Commons Attribution License v1.0 Source: nemar

Metadata: Complete (100%)

Quickstart#

Install

pip install eegdash

Access the data

from eegdash.dataset import NM000225

dataset = NM000225(cache_dir="./data")
# Get the raw object of the first recording
raw = dataset.datasets[0].raw
print(raw.info)

Filter by subject

dataset = NM000225(cache_dir="./data", subject="01")

Advanced query

dataset = NM000225(
    cache_dir="./data",
    query={"subject": {"$in": ["01", "02"]}},
)

Iterate recordings

for rec in dataset:
    print(rec.subject, rec.raw.info['sfreq'])

If you use this dataset in your research, please cite the original authors.

BibTeX

@dataset{nm000225,
  title = {PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)},
  author = {Mohammad M. Ghassemi and Benjamin E. Moody and Li-wei H. Lehman and Christopher Song and Qiao Li and Haoqi Sun and Roger G. Mark and M. Brandon Westover and Gari D. Clifford},
  doi = {10.13026/6phb-r450},
  url = {https://doi.org/10.13026/6phb-r450},
}

About This Dataset#

You Snooze You Win: PhysioNet/CinC Challenge 2018 PSG

Overview

1,983 overnight polysomnographic (PSG) recordings from subjects monitored at the Massachusetts General Hospital (MGH) sleep laboratory for sleep disorder diagnosis. The dataset was created for the PhysioNet/Computing in Cardiology Challenge 2018 on automatic arousal detection.

View full README

You Snooze You Win: PhysioNet/CinC Challenge 2018 PSG

Overview

1,983 overnight polysomnographic (PSG) recordings from subjects monitored at the Massachusetts General Hospital (MGH) sleep laboratory for sleep disorder diagnosis. The dataset was created for the PhysioNet/Computing in Cardiology Challenge 2018 on automatic arousal detection. - Training set: 994 subjects (with expert annotations) - Test set: 989 subjects (PSG signals only, no annotations) - Demographics: mean age 55 +/- 14 years (range 18-93), 65% male, 35% female - Clinical population: subjects with suspected obstructive sleep apnea

Channels (13 total, all at 200 Hz)

  • EEG (6): F3-M2, F4-M1, C3-M2, C4-M1, O1-M2, O2-M1 Referential montage against contralateral mastoids (M1/M2)

  • EOG (1): E1-M2 (left electrooculogram)

  • EMG (1): Chin1-Chin2 (submental chin electromyogram)

  • Respiratory (3): ABD (abdominal effort), CHEST (thoracic effort), AIRFLOW (nasal/oral airflow)

  • SpO2 (1): SaO2 (pulse oximetry, resampled to 200 Hz)

  • ECG (1): ECG (single-lead electrocardiogram)

Annotations (training set only, in events.tsv)

Sleep staging (AASM standard, 30-second contiguous epochs):

Wake, N1, N2, N3, REM

Respiratory events (with onset and duration):

resp_obstructiveapnea — complete upper airway obstruction resp_centralapnea — absent respiratory effort resp_mixedapnea — combined obstructive + central resp_hypopnea — partial airway obstruction (>=30% flow reduction)

Arousal events:

arousal_rera — respiratory effort-related arousal arousal_spontaneous — spontaneous cortical arousal arousal_snore — snoring-related arousal arousal_plm — periodic leg movement arousal

Participants metadata (in participants.tsv)

Per-subject: age, sex, split (training/test), recording duration, sleep architecture (epoch counts per stage), and respiratory/arousal event counts.

Sessions

  • ses-training: 994 subjects with PSG + annotations

  • ses-test: 989 subjects with PSG only (no annotations)

Notes

  • Original format: WFDB (.mat + .hea + .arousal)

  • All signals originally at 200 Hz; SaO2 was resampled to match

  • Annotators: certified sleep technologists at MGH, following AASM manual

  • Updated arousal annotations (new-arousals.zip) supersede originals

Reference

Ghassemi, M.M., Moody, B.E., Lehman, L.H., Song, C., Li, Q., Sun, H., Mark, R.G., Westover, M.B. & Clifford, G.D. (2018). You Snooze, You Win: the PhysioNet/Computing in Cardiology Challenge 2018. Computing in Cardiology, 45, 1-4. doi:10.22489/CinC.2018.049 Goldberger, A. et al. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215-e220. https://physionet.org/content/challenge-2018/1.0.0/

References

Appelhoff, S., Sanderson, M., Brooks, T., Vliet, M., Quentin, R., Holdgraf, C., Chaumon, M., Mikulan, E., Tavabi, K., Höchenberger, R., Welke, D., Brunner, C., Rockhill, A., Larson, E., Gramfort, A. and Jas, M. (2019). MNE-BIDS: Organizing electrophysiological data into the BIDS format and facilitating their analysis. Journal of Open Source Software 4: (1896).https://doi.org/10.21105/joss.01896 Pernet, C. R., Appelhoff, S., Gorgolewski, K. J., Flandin, G., Phillips, C., Delorme, A., Oostenveld, R. (2019). EEG-BIDS, an extension to the brain imaging data structure for electroencephalography. Scientific Data, 6, 103.https://doi.org/10.1038/s41597-019-0104-8

Dataset Information#

Dataset ID

NM000225

Title

PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)

Author (year)

Ghassemi2018

Canonical

—

Importable as

NM000225, Ghassemi2018

Year

2018

Authors

Mohammad M. Ghassemi, Benjamin E. Moody, Li-wei H. Lehman, Christopher Song, Qiao Li, Haoqi Sun, Roger G. Mark, M. Brandon Westover, Gari D. Clifford

License

Open Data Commons Attribution License v1.0

Citation / DOI

doi:10.13026/6phb-r450

Source links

OpenNeuro | NeMAR | Source URL
Copy-paste BibTeX
@dataset{nm000225,
  title = {PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)},
  author = {Mohammad M. Ghassemi and Benjamin E. Moody and Li-wei H. Lehman and Christopher Song and Qiao Li and Haoqi Sun and Roger G. Mark and M. Brandon Westover and Gari D. Clifford},
  doi = {10.13026/6phb-r450},
  url = {https://doi.org/10.13026/6phb-r450},
}

Found an issue with this dataset?

If you encounter any problems with this dataset (missing files, incorrect metadata, loading errors, etc.), please let us know!

Report an Issue on GitHub

Technical Details#

Subjects & recordings

  • Subjects: 1983

  • Recordings: 1983

  • Tasks: 1

Channels & sampling rate

  • Channels: 13

  • Sampling rate (Hz): 200

  • Duration (hours): 15261.231134722222

Tags

  • Pathology: Not specified

  • Modality: —

  • Type: —

Files & format

  • Size on disk: 401.1 GB

  • File count: 1983

  • Format: BIDS

License & citation

  • License: Open Data Commons Attribution License v1.0

  • DOI: doi:10.13026/6phb-r450

Provenance

API Reference#

Use the NM000225 class to access this dataset programmatically.

class eegdash.dataset.NM000225(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#

Bases: EEGDashDataset

PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)

Study:

nm000225 (NeMAR)

Author (year):

Ghassemi2018

Canonical:

—

Also importable as: NM000225, Ghassemi2018.

Modality: eeg. Subjects: 1983; recordings: 1983; tasks: 1.

Parameters:

  • cache_dir (str | Path) – Directory where data are cached locally.

  • query (dict | None) – Additional MongoDB-style filters to AND with the dataset selection. Must not contain the key dataset.

  • s3_bucket (str | None) – Base S3 bucket used to locate the data.

  • **kwargs (dict) – Additional keyword arguments forwarded to EEGDashDataset.

data_dir#

Local dataset cache directory (cache_dir / dataset_id).

Type:

Path

query#

Merged query with the dataset filter applied.

Type:

dict

records#

Metadata records used to build the dataset, if pre-fetched.

Type:

list[dict] | None

Notes

Each item is a recording; recording-level metadata are available via dataset.description. query supports MongoDB-style filters on fields in ALLOWED_QUERY_FIELDS and is combined with the dataset filter. Dataset-specific caveats are not provided in the summary metadata.

References

OpenNeuro dataset: https://openneuro.org/datasets/nm000225 NeMAR dataset: https://nemar.org/dataexplorer/detail?dataset_id=nm000225 DOI: https://doi.org/10.13026/6phb-r450

Examples

>>> from eegdash.dataset import NM000225
>>> dataset = NM000225(cache_dir="./data")
>>> recording = dataset[0]
>>> raw = recording.load()
__init__(cache_dir: str, query: dict | None = None, s3_bucket: str | None = None, **kwargs)[source]#
save(path, overwrite=False)[source]#

Save the dataset to disk.

Parameters:

  • path (str or Path) – Destination file path.

  • overwrite (bool, default False) – If True, overwrite existing file.

Return type:

None

See Also#