{"dataset":{"id":"411","dataset_id":"nm000225","name":"PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)","description":"A polysomnographic dataset comprising 1,983 overnight sleep recordings from Massachusetts General Hospital, including 994 training subjects with expert annotations and 989 test subjects. The dataset was created for the PhysioNet/Computing in Cardiology Challenge 2018 and contains 13 channels of physiological signals (EEG, EOG, EMG, respiratory, SpO2, ECG) sampled at 200 Hz, with annotations for sleep stages, respiratory events, and arousal types in the training set.","owner_user_id":19,"status":"active","github_repo":"nemarDatasets/nm000225","concept_doi":"10.82901/nemar.nm000225","latest_version_doi":"10.82901/nemar.nm000225.v1.1.0","created_at":"2026-04-09 21:08:21","updated_at":"2026-07-10 21:58:06","zenodo_concept_id":"20519369","is_sandbox":0,"visibility":"public","ezid_status":"public","enrichment_json":"{\n  \"version\": \"2.0\",\n  \"pipeline_stage\": \"validated\",\n  \"authors\": {\n    \"Mohammad M. Ghassemi\": {},\n    \"Benjamin E. Moody\": {},\n    \"Li-wei H. Lehman\": {},\n    \"Christopher Song\": {},\n    \"Qiao Li\": {},\n    \"Haoqi Sun\": {},\n    \"Roger G. Mark\": {},\n    \"M. Brandon Westover\": {},\n    \"Gari D. Clifford\": {}\n  },\n  \"related_identifiers\": [\n    {\n      \"identifier\": \"10.13026/6phb-r450\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsDerivedFrom\"\n    },\n    {\n      \"identifier\": \"10.22489/CinC.2018.049\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"References\"\n    },\n    {\n      \"identifier\": \"https://github.com/nemarDatasets/nm000225\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"https://nemar.org/dataexplorer/detail?dataset_id=nm000225\",\n      \"identifier_type\": \"URL\",\n      \"relation_type\": \"IsDescribedBy\"\n    },\n    {\n      \"identifier\": \"10.21105/joss.01896\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsReferencedBy\"\n    },\n    {\n      \"identifier\": \"10.1038/s41597-019-0104-8\",\n      \"identifier_type\": \"DOI\",\n      \"relation_type\": \"IsReferencedBy\"\n    }\n  ],\n  \"funding_references\": [\n    {\n      \"funder_name\": \"The MathWorks (equipment sponsorship)\"\n    },\n    {\n      \"funder_name\": \"National Institute of Biomedical Imaging and Bioengineering (NIBIB)\",\n      \"award_number\": \"U24EB037545\"\n    },\n    {\n      \"funder_name\": \"National Institute of Biomedical Imaging and Bioengineering (NIBIB)\",\n      \"award_number\": \"R01EB030362\"\n    }\n  ],\n  \"title\": \"PhysioNet 2018 Challenge: Sleep Arousal Detection PSG (Training)\",\n  \"license\": \"Open Data Commons Attribution License v1.0\",\n  \"dataset_type\": \"raw\",\n  \"resource_type_general\": \"Dataset\",\n  \"modalities\": [\n    \"eeg\"\n  ],\n  \"resource_type_specific\": \"EEG Dataset\",\n  \"sizes\": [\n    \"430.7 GB (1985 files)\"\n  ],\n  \"formats\": [\n    \".bak\",\n    \".bdf\",\n    \".json\",\n    \".md\",\n    \".tsv\",\n    \".yml\"\n  ],\n  \"description\": \"A polysomnographic dataset comprising 1,983 overnight sleep recordings from Massachusetts General Hospital, including 994 training subjects with expert annotations and 989 test subjects. The dataset was created for the PhysioNet/Computing in Cardiology Challenge 2018 and contains 13 channels of physiological signals (EEG, EOG, EMG, respiratory, SpO2, ECG) sampled at 200 Hz, with annotations for sleep stages, respiratory events, and arousal types in the training set.\",\n  \"methods_description\": \"Polysomnographic recordings acquired at 200 Hz from a clinical population with suspected obstructive sleep apnea. Signals include 6 EEG channels (referential montage against contralateral mastoids), 1 EOG channel, 1 EMG channel, 3 respiratory channels, SpO2, and single-lead ECG. Sleep staging and respiratory/arousal events were annotated by certified sleep technologists following AASM standards.\",\n  \"keywords\": [\n    {\n      \"term\": \"Polysomnography\",\n      \"subject_scheme\": \"MeSH\",\n      \"value_uri\": \"http://id.nlm.nih.gov/mesh/D017286\"\n    },\n    {\n      \"term\": \"sleep arousal detection\"\n    },\n    {\n      \"term\": \"EEG\"\n    },\n    {\n      \"term\": \"Sleep Stages\",\n      \"subject_scheme\": \"MeSH\",\n      \"value_uri\": \"http://id.nlm.nih.gov/mesh/D012894\"\n    },\n    {\n      \"term\": \"obstructive sleep apnea\"\n    },\n    {\n      \"term\": \"respiratory events\"\n    }\n  ],\n  \"source_hash\": \"bd63f249f54b9e8f6cbdac0f63cd9691921db5e4223b5e3d762051f7d3e3a677\"\n}","last_activity_at":"2026-04-10 08:27:55","source":null,"source_id":null,"subject_count":1983,"modalities":"eeg","age_min":18,"age_max":93,"file_size":430698977731,"total_files":1985,"tasks":"sleep","metadata_columns_error":null,"staleness_warn_stage":null,"staleness_admin_notified_at":null,"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","readme":"[![DOI](https://img.shields.io/badge/DOI-10.82901%2Fnemar.nm000225-blue)](https://doi.org/10.82901/nemar.nm000225)\n\nYou Snooze You Win: PhysioNet/CinC Challenge 2018 PSG\n=======================================================\n\nOverview\n--------\n1,983 overnight polysomnographic (PSG) recordings from subjects monitored at\nthe Massachusetts General Hospital (MGH) sleep laboratory for sleep disorder\ndiagnosis. The dataset was created for the PhysioNet/Computing in Cardiology\nChallenge 2018 on automatic arousal detection.\n\n- Training set: 994 subjects (with expert annotations)\n- Test set: 989 subjects (PSG signals only, no annotations)\n- Demographics: mean age 55 +/- 14 years (range 18-93), 65% male, 35% female\n- Clinical population: subjects with suspected obstructive sleep apnea\n\nChannels (13 total, all at 200 Hz)\n-----------------------------------\n- EEG (6): F3-M2, F4-M1, C3-M2, C4-M1, O1-M2, O2-M1\n  Referential montage against contralateral mastoids (M1/M2)\n- EOG (1): E1-M2 (left electrooculogram)\n- EMG (1): Chin1-Chin2 (submental chin electromyogram)\n- Respiratory (3): ABD (abdominal effort), CHEST (thoracic effort),\n  AIRFLOW (nasal/oral airflow)\n- SpO2 (1): SaO2 (pulse oximetry, resampled to 200 Hz)\n- ECG (1): ECG (single-lead electrocardiogram)\n\nAnnotations (training set only, in events.tsv)\n------------------------------------------------\nSleep staging (AASM standard, 30-second contiguous epochs):\n  Wake, N1, N2, N3, REM\n\nRespiratory events (with onset and duration):\n  resp_obstructiveapnea  — complete upper airway obstruction\n  resp_centralapnea      — absent respiratory effort\n  resp_mixedapnea        — combined obstructive + central\n  resp_hypopnea          — partial airway obstruction (>=30% flow reduction)\n\nArousal events:\n  arousal_rera           — respiratory effort-related arousal\n  arousal_spontaneous    — spontaneous cortical arousal\n  arousal_snore          — snoring-related arousal\n  arousal_plm            — periodic leg movement arousal\n\nParticipants metadata (in participants.tsv)\n--------------------------------------------\nPer-subject: age, sex, split (training/test), recording duration, sleep\narchitecture (epoch counts per stage), and respiratory/arousal event counts.\n\nSessions\n--------\n- ses-training: 994 subjects with PSG + annotations\n- ses-test: 989 subjects with PSG only (no annotations)\n\nNotes\n-----\n- Original format: WFDB (.mat + .hea + .arousal)\n- All signals originally at 200 Hz; SaO2 was resampled to match\n- Annotators: certified sleep technologists at MGH, following AASM manual\n- Updated arousal annotations (new-arousals.zip) supersede originals\n\nReference\n---------\nGhassemi, M.M., Moody, B.E., Lehman, L.H., Song, C., Li, Q., Sun, H.,\nMark, R.G., Westover, M.B. & Clifford, G.D. (2018). You Snooze, You Win:\nthe PhysioNet/Computing in Cardiology Challenge 2018. Computing in\nCardiology, 45, 1-4. doi:10.22489/CinC.2018.049\n\nGoldberger, A. et al. (2000). PhysioBank, PhysioToolkit, and PhysioNet:\nComponents of a new research resource for complex physiologic signals.\nCirculation, 101(23), e215-e220.\nhttps://physionet.org/content/challenge-2018/1.0.0/\n\n\nReferences\n----------\nAppelhoff, 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\n\nPernet, 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\n\n","bids_version":"1.9.0","sessions_count":2,"publish_date":"2026-04-09 21:08:21","embedding_dirty":0,"license_tier":"attribution","zarr_status":"ready","zarr_converted_at":"2026-09-04 05:07:42","zarr_store_count":1983,"zarr_index_etag":"0411fed0d724d4195579603299676463","zarr_source_commit":"40c423eb4a52ba82fef8053c8589ee8505d784b5","archive_status":null,"archive_size":null,"archive_retry_count":0,"records_status":null,"archive_skip_reason":null,"zarr_errors":0,"zarr_failure_count":0,"zarr_deterministic":0,"zarr_failed_at":null,"num_dataset_citations":0,"num_datapaper_citations":91,"n_channels":6,"electrode_system":"other","has_hed":0,"hed_version":"8.2.0","is_exemplar":0,"bytes_present":null,"data_complete":null,"withdrawn_at":null,"withdrawn_reason":null,"archive_complete":null,"archive_absent_files":null,"archive_declared_files":null,"zarr_pool_breaks":0,"total_recording_duration":54940442,"recording_duration_min":18470,"recording_duration_max":35784,"recording_count":1983,"recordings_unavailable":0,"recordings_measured":1983,"channel_count_min":13,"channel_count_max":13,"sampling_frequency":200,"power_line_frequency":60,"eeg_reference":"Contralateral mastoid (M1/M2)","placement_scheme":"10-20 subset (F3, F4, C3, C4, O1, O2)","sweep_stamps":"{\"enrichment_updated_at\":\"2026-06-03 02:49:42\",\"metadata_updated_at\":\"2026-06-03 02:51:05\",\"archive_checked_at\":\"2026-06-05 01:33:07\",\"zarr_checked_at\":\"2026-06-07 17:58:33\",\"records_checked_at\":null,\"citations_updated_at\":\"2026-09-08 03:00:46\",\"channel_montage_checked_at\":\"2026-06-28 22:58:50\",\"hed_checked_at\":\"2026-06-30 04:28:55\",\"data_checked_at\":null,\"availability_report_at\":\"2026-07-23 01:08:38\",\"signal_defaults_at\":\"2026-09-02 11:46:02\",\"recording_stats_at\":\"2026-09-05 03:01:38\"}","participants":1983,"num_citations":91,"latest_version":"v1.1.0","zarr_verify_status":null,"zarr_verified_at":null,"owner_username":"bruaristimunha","owner_github":"bruAristimunha","file_size_formatted":"401 GB","zarr_data_failures":null,"zarr_index_url":"https://zarr.nemar.org/nm000225/zarr/index.json","attestation_deposit_type":null,"attestation_key_status":null,"attestation_deidentified":null,"attestation_no_duplicate":null,"attestation_upstream_source":null,"attestation_accepted_at":null}}