EEGdash›NeMAR›NM000225

Iss. 225 · 1983 subjects · 1983 recordings · Open Data Commons Attribution License v1.0

Dataset Brief · PhysioNet 2018 Challenge

NM000225: eeg dataset, 1983 subjects#

Name: PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)
Published: 2018-01-01
License: Open Data Commons Attribution License v1.0

PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)

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

1983-participant EEG dataset — PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training).

Data & curation Mohammad M. Ghassemi · Benjamin E. Moody · Li-wei H. Lehman · Christopher Song · Qiao Li · Haoqi Sun · …
Year 2018 · Distributed via NeMAR
Funding National Institute of Biomedical Imaging and Bioengineering (NIBIB) U24EB037545 · National Institute of Biomedical Imaging and Bioengineering (NIBIB) R01EB030362 · + 1 more

EEG · 13 ch200 HzBIDS 1.9.0Task · sleep2 sessions

Layer 01Study

What was asked

Hypothesis, independent & dependent variables, paradigm, cohort, and the editorial caveats around what the recordings can and cannot answer.

Layer 02Signal · BIDS

What was recorded

Sidecars, channels & electrodes, coordinate system, event semantics, and quality stats from the NEMAR pipeline when available.

Layer 03Training · ML

What you can train on

Recommended access modes — MNE Raw, braindecode windows, PyTorch DataLoader — plus the targets the metadata makes addressable.

§ 01Access · Get started

Quickstart#

Get Started

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)

Query & Filter

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'])

Cite This Dataset

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},
}

§ 02Study · The README

About This Dataset#

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

Referential montage against contralateral mastoids (M1/M2)

You Snooze You Win: PhysioNet/CinC Challenge 2018 PSG

Overview

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)

View full README

You Snooze You Win: PhysioNet/CinC Challenge 2018 PSG

Overview

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

§ 03Cohort · Participants

Cohort#

Dataset Statistics#

Age distribution by gender (n=1983, range 18–93 yr, mean 55.0 yr)

15202530354045505560657075808590

Female · 693Male · 1290

Sex composition

Female
693
Male
1290
F : M ratio
0.54 : 1

35% female · n = 1983 subjects with reported sex.

Channel counts: 13 ch (n=1983 recordings)

Sampling frequencies: 200.0 Hz (n=1983 recordings)

Total recording duration: 15261 h

§ 04Signal · Electrodes & trace

Signal · Electrodes & live trace#

Fig. 01 Signal & montage 13 ch · EEG · 200 Hz · 1983 subjects, 1983 recordings

Live trace viewer — sub-tr030187 · ses-training · task-sleep

Showing one representative recording out of 1983 subjects and 1983 recordings in this dataset. Browse the full set on OpenNeuro; drop any other _eeg.{set,edf,bdf,vhdr} file onto the viewer (or pass ?eeg=<url>) to inspect it.

No scalp electrode layout is currently indexed for this dataset. Once the eegdash montage registry ingests it, the interactive viewer will appear here automatically.

NEMAR Processing Statistics#

The plots below are generated by NEMAR’s automated EEG pipeline. The histogram shows pipeline success for data cleaning and ICA decomposition, the percentage of data frames and EEG channels retained after artefact removal, line noise per channel (RMS, dB), and the age/gender distribution of participants.

HED event descriptors word cloud

§ 05Manifest · BIDS tree

Manifest#

File Explorer#

Browse the BIDS file structure of this dataset. Records are fetched on demand from the EEGDash catalog the first time you open the explorer.

Recordings—

Files—

Subjects—

Modalities—

Click to load file structure…

§ 06API · Programmatic access

API Reference#

Signature

eegdash.dataset

class

eegdash.dataset.NM000225(cache_dir, query=None, s3_bucket=None, **kwargs)

Bases: EEGDashDataset

Author (year)Ghassemi2018

Canonical—

Importable asNM000225 · Ghassemi2018

Sourceeegdash/dataset/registry.py · [source ↗]

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

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: str, overwrite: bool = False, offset: int = 0)[source]#

Save datasets to files by creating one subdirectory for each dataset:

path/
    0/
        0-raw.fif | 0-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)
    1/
        1-raw.fif | 1-epo.fif
        description.json
        raw_preproc_kwargs.json (if raws were preprocessed)
        window_kwargs.json (if this is a windowed dataset)
        window_preproc_kwargs.json  (if windows were preprocessed)
        target_name.json (if target_name is not None and dataset is raw)

Parameters:

path (str) –

Directory in which subdirectories are created to store
-raw.fif | -epo.fif and .json files to.
overwrite (bool) – Whether to delete old subdirectories that will be saved to in this call.
offset (int) – If provided, the integer is added to the id of the dataset in the concat. This is useful in the setting of very large datasets, where one dataset has to be processed and saved at a time to account for its original position.

Access modesMNE → braindecode → PyTorch → ML

.rawMNE Raw object — standard tools (filter, epoch, ICA, plot_psd).mne

BaseConcatDatasetEach record is a lazy BaseDataset from braindecode — windowed via create_windows_from_events.braindecode

DataLoaderWraps the windowed dataset into a PyTorch DataLoader; supports parallel workers and on-the-fly augmentations.pytorch

Zarr cacheOptional braindecode Zarr mirror for fast resume; persisted to cache_dir.zarr

Hugging FaceNo per-dataset mirror published yet — browse the EEGDash org listing for sibling datasets. See the datasets loader API.huggingface

Croissant 1.0Machine-readable JSON-LD descriptor — NM000225.croissant.json (MLCommons schema, ingestible by PyTorch / TensorFlow / JAX).mlcommons

Examples using EEGDashcurated · start here

Find datasets with the EEGDash APIQuery the catalogue, filter by task or modality, list candidates.

Load one EEG recordingResolve a single record to an MNE Raw with channels and events.

EEG recording to PyTorch DataLoaderWrap braindecode windows in a DataLoader for model training.

Preprocess EEG and create windowsFilter, resample, epoch — and persist the windowed dataset.

Save and reload prepared dataCache a windowed dataset to disk and reattach it without recompute.

Download a dataset locallyPrefetch BIDS files to a local cache and validate the layout.

Swap any load_dataset(...) call for nm000225 to reproduce the tutorial on this dataset.

Citation

Mohammad M. Ghassemi, Benjamin E. Moody, Li-wei H. Lehman, Christopher Song, Qiao Li, … (2018). PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training). 10.13026/6phb-r450

Provenance

¹Contributed to nemar in BIDS format.

²Curated & ingested by the EEGDash catalog; see CITATION.cff for canonical reference.

³Persistent identifier: 10.13026/6phb-r450.

Related & sibling datasets

NM000181EEG · 2417 subj ON007181EEG · 59 subj ON003810EEG · 10 subj ON003825EEG · 50 subj ON007827EEG · 99 subj

+ 1 more — see See Also below →

BIDS

BIDS 1.9.0

Sidecars

channels · eeg.json

Provenance

Open Data Commons Attribution License v1.0 · 10.13026/6phb-r450

Machine-readable

schema.org/Dataset · Croissant

Mirrors

OpenNeuro · NEMAR · HF org

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

NM000225: eeg dataset, 1983 subjects#

Quickstart#

About This Dataset#

Cohort#

Dataset Statistics#

Signal · Electrodes & live trace#

NEMAR Processing Statistics#

Manifest#

File Explorer#

API Reference#

Citation

Provenance

Related & sibling datasets

See Also#