{"success":true,"database":"eegdash","data":{"_id":"69d16e05897a7725c66f4cb5","dataset_id":"nm000230","associated_paper_doi":null,"authors":["Chongwen Zuo","Yi Yin","Haochong Wang","Zhiyang Zheng","Xiaoyan Ma","Yuan Yang","Jue Wang","Shan Wang","Zi-gang Huang","Chaoqun Ye"],"bids_version":"1.9.0","contact_info":null,"contributing_labs":null,"data_processed":false,"dataset_doi":null,"datatypes":["eeg"],"demographics":{"subjects_count":30,"ages":[33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33,33],"age_min":33,"age_max":33,"age_mean":33.0,"species":null,"sex_distribution":null,"handedness_distribution":null},"experimental_modalities":null,"external_links":{"source_url":"https://nemar.org/dataexplorer/detail/nm000230","osf_url":null,"github_url":null,"paper_url":null},"funding":[],"ingestion_fingerprint":"fa124582801dcf212518eb7761b1298d77194762d07c6d4fa9f3d7c5f7cc6717","license":"CC-BY-4.0","n_contributing_labs":null,"name":"Lower-limb MI dataset for knee pain patients from Zuo et al. 2025","readme":"# Lower-limb MI dataset for knee pain patients from Zuo et al. 2025\nLower-limb MI dataset for knee pain patients from Zuo et al. 2025.\n## Dataset Overview\n- **Code**: Zuo2025\n- **Paradigm**: imagery\n- **DOI**: 10.1038/s41597-025-05767-2\n- **Subjects**: 30\n- **Sessions per subject**: 5\n- **Events**: left_leg=1, right_leg=2\n- **Trial interval**: [0, 4] s\n- **File format**: MAT\n## Acquisition\n- **Sampling rate**: 500.0 Hz\n- **Number of channels**: 30\n- **Channel types**: eeg=30\n- **Channel names**: Fp1, Fp2, Fz, F3, F4, F7, F8, FCz, FC3, FC4, FT7, FT8, Cz, C3, C4, T3, T4, CPz, CP3, CP4, TP7, TP8, Pz, P3, P4, T5, T6, Oz, O1, O2\n- **Montage**: standard_1005\n- **Hardware**: ZhenTec EEG system\n- **Reference**: CPz\n- **Ground**: FPz\n- **Line frequency**: 50.0 Hz\n## Participants\n- **Number of subjects**: 30\n- **Health status**: knee pain patients\n- **Clinical population**: knee_pain\n- **Age**: mean=33.5, min=24, max=45\n- **Gender distribution**: female=12, male=18\n- **Species**: human\n## Experimental Protocol\n- **Paradigm**: imagery\n- **Number of classes**: 2\n- **Class labels**: left_leg, right_leg\n- **Trial duration**: 4.0 s\n- **Study design**: 2-class lower-limb MI (left/right leg flexion/extension). 5 sessions, 100 trials per session.\n- **Feedback type**: none\n- **Stimulus type**: visual\n- **Stimulus modalities**: visual\n- **Primary modality**: visual\n- **Synchronicity**: cue-based\n- **Mode**: offline\n## HED Event Annotations\nSchema: HED 8.4.0 | Browse: https://www.hedtags.org/hed-schema-browser\n```\n  left_leg\n    ├─ Sensory-event\n    └─ Label/left_leg\n  right_leg\n    ├─ Sensory-event\n    └─ Label/right_leg\n```\n## Paradigm-Specific Parameters\n- **Detected paradigm**: motor_imagery\n- **Imagery tasks**: left_leg, right_leg\n- **Imagery duration**: 4.0 s\n## Data Structure\n- **Trials**: 500\n- **Trials per class**: left_leg=250, right_leg=250\n- **Trials context**: 5 sessions x 100 trials (50 left + 50 right)\n## Signal Processing\n- **Classifiers**: CSP+LDA, FBCSP+SVM, EEGNet, OTFWRGD\n- **Feature extraction**: CSP, FBCSP, deep_learning, Riemannian_geometry\n- **Frequency bands**: alpha_mu=[8.0, 15.0] Hz; beta=[15.0, 30.0] Hz\n- **Spatial filters**: CSP, FBCSP\n## Cross-Validation\n- **Method**: 10-fold\n- **Folds**: 10\n- **Evaluation type**: within_subject\n## BCI Application\n- **Applications**: rehabilitation\n- **Environment**: clinical\n- **Online feedback**: False\n## Tags\n- **Pathology**: Knee Pain\n- **Modality**: Motor\n- **Type**: Clinical, Motor Imagery\n## Documentation\n- **DOI**: 10.1038/s41597-025-05767-2\n- **License**: CC-BY-4.0\n- **Investigators**: Chongwen Zuo, Yi Yin, Haochong Wang, Zhiyang Zheng, Xiaoyan Ma, Yuan Yang, Jue Wang, Shan Wang, Zi-gang Huang, Chaoqun Ye\n- **Institution**: Air Force Medical Center, Beijing\n- **Country**: CN\n- **Data URL**: https://figshare.com/articles/dataset/28740260\n- **Publication year**: 2025\n## References\nZuo, C., Yin, Y., Wang, H., et al. (2025). Enhancing classification of a large lower-limb motor imagery EEG dataset for BCI in knee pain patients. Scientific Data, 12, 1451. https://doi.org/10.1038/s41597-025-05767-2\nNotes\n.. versionadded:: 1.2.0\nAppelhoff, S., Sanderson, M., Brooks, T., Vliet, M., Quentin, R., Holdgraf, C., Chaumon, M., Mikulan, E., Tavabi, K., Hochenberger, 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\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---\nGenerated by MOABB 1.5.0 (Mother of All BCI Benchmarks)\nhttps://github.com/NeuroTechX/moabb","recording_modality":["eeg"],"senior_author":null,"sessions":["01","02","03","04","05"],"size_bytes":6175864620,"source":"nemar","storage":{"backend":"nemar","base":"s3://nemar/nm000230","raw_key":"dataset_description.json","dep_keys":["README.md","participants.json","participants.tsv"]},"study_design":null,"study_domain":null,"tasks":["imagery"],"timestamps":{"digested_at":"2026-04-30T14:09:17.480761+00:00","dataset_created_at":null,"dataset_modified_at":"2026-03-25T16:39:52Z"},"total_files":118,"computed_title":"Lower-limb MI dataset for knee pain patients from Zuo et al. 2025","nchans_counts":[{"val":30,"count":118}],"sfreq_counts":[{"val":500.0,"count":118}],"stats_computed_at":"2026-05-01T13:49:34.645893+00:00","total_duration_s":137079.764,"tagger_meta":{"config_hash":"3557b68bca409f28","metadata_hash":"9daf4724b8d61f90","model":"openai/gpt-5.2","tagged_at":"2026-04-07T09:32:40.872789+00:00"},"tags":{"pathology":["Other"],"modality":["Visual"],"type":["Motor"],"confidence":{"pathology":0.9,"modality":0.9,"type":0.9},"reasoning":{"few_shot_analysis":"Most similar few-shot example by paradigm is the \"EEG Motor Movement/Imagery Dataset\" (healthy volunteers) which is explicitly motor imagery with on-screen targets/cues; it is labeled Modality=Visual and Type=Motor. This guides the convention that motor imagery studies are categorized as Type=Motor (research purpose: movement/imagery) while Modality reflects the stimulus/cue channel (often Visual), not the motor response system. The Parkinson’s reinforcement learning example also shows that Pathology should follow explicit recruitment diagnosis; here the clinical recruitment is knee pain (not in allowed pathology list), so it maps to Pathology=Other.","metadata_analysis":"Key explicit metadata facts:\n- Clinical population: \"Health status: knee pain patients\" and \"Clinical population: knee_pain\" and title \"Lower-limb MI dataset for knee pain patients\".\n- Stimulus channel: \"Stimulus type: visual\", \"Stimulus modalities: visual\", and \"Primary modality: visual\".\n- Task/construct: \"Study design: 2-class lower-limb MI (left/right leg flexion/extension)\", \"Detected paradigm: motor_imagery\", and \"Paradigm: imagery\" / \"Imagery tasks: left_leg, right_leg\".\nThese directly support (1) a non-healthy clinical cohort, (2) visually cued trials, and (3) motor imagery as the main construct.","paper_abstract_analysis":"No useful paper information (abstract not provided in the input metadata).","evidence_alignment_check":"Pathology:\n- Metadata says: \"Health status: knee pain patients\" / \"Clinical population: knee_pain\" (explicit clinical recruitment).\n- Few-shot pattern suggests: use the named diagnosis/condition as Pathology; if not available in allowed labels, map to closest allowed bucket.\n- Alignment: ALIGNS. Final is \"Other\" because knee pain is not an allowed specific pathology label.\n\nModality:\n- Metadata says: \"Stimulus type: visual\", \"Stimulus modalities: visual\", \"Primary modality: visual\".\n- Few-shot pattern suggests: in motor imagery with screen cues/targets, Modality=Visual (e.g., EEG Motor Movement/Imagery Dataset labeled Visual).\n- Alignment: ALIGNS.\n\nType:\n- Metadata says: \"Detected paradigm: motor_imagery\" and \"2-class lower-limb MI (left/right leg flexion/extension)\".\n- Few-shot pattern suggests: motor imagery paradigms map to Type=Motor.\n- Alignment: ALIGNS (even though dataset is in a clinical cohort, the primary experimental construct is motor imagery for BCI/rehabilitation rather than an intervention study description).","decision_summary":"Top-2 candidates with head-to-head comparison:\n\nPathology:\n1) Other — Supported by: \"Health status: knee pain patients\", \"Clinical population: knee_pain\", and title indicating knee pain patients. Knee pain is a clinical condition but not present as a dedicated allowed label.\n2) Healthy — Would only apply if no disorder focus; contradicted by explicit \"knee pain patients\".\nSelected: Other. (Alignment: aligns with few-shot convention to follow explicit recruitment condition.)\nConfidence (0.9): 3+ explicit metadata quotes for a clinical cohort, with clear mapping necessity to \"Other\".\n\nModality:\n1) Visual — Supported by: \"Stimulus type: visual\", \"Stimulus modalities: visual\", \"Primary modality: visual\"; also matches the motor imagery few-shot convention (motor imagery with screen cues labeled Visual).\n2) Motor — Possible because task is motor imagery, but guidelines specify Modality is stimulus/input channel, not the imagined movement itself.\nSelected: Visual. (Alignment: aligns with both metadata and few-shot convention.)\nConfidence (0.9): 3 explicit modality statements + strong few-shot analog.\n\nType:\n1) Motor — Supported by: \"Detected paradigm: motor_imagery\", \"Paradigm: imagery\", and \"2-class lower-limb MI\".\n2) Clinical/Intervention — Plausible due to \"knee pain patients\" and \"Applications: rehabilitation\", but the dataset description emphasizes motor imagery classification rather than an intervention outcome.\nSelected: Motor. (Alignment: aligns with metadata and motor imagery few-shot example.)\nConfidence (0.9): 3+ explicit motor imagery/task-design cues + strong few-shot analog."}},"canonical_name":null,"name_confidence":0.78,"name_meta":{"suggested_at":"2026-04-14T10:18:35.344Z","model":"openai/gpt-5.2 + openai/gpt-5.4-mini + deterministic_fallback"},"name_source":"author_year","author_year":"Zuo2025"}}