datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sph-ecg-arrhythmia
SPH 12-Lead ECG Arrhythmia Dataset (PhysioNet Mirror Card)
⚠️ License: This dataset is subject to the
PhysioNet Restricted Health Data License.
You must sign the Data Use Agreement on PhysioNet before use.
Source
Shaoxing People's Hospital (SPH) 12-Lead ECG DatasetPhysioNet: https://physionet.org/content/ecg-arrhythmia/1.0.0/
Stats
Property
Value
Records
45,152 patients
Format
WFDB (.mat + .hea)
Leads
12 (I, II, III, aVR, aVL, aVF, V1–V6)… See the full description on the dataset page: https://huggingface.co/datasets/adzetto/sph-ecg-arrhythmia.ecg-arrhythmia-data
ECG Arrhythmia Dataset — MIT-BIH Processed
Preprocessed beat segments derived from the MIT-BIH Arrhythmia Database (PhysioNet).
Contents
File
Description
X.npy
Beat segments — shape (N, 180), float32
y.npy
Encoded labels — integers 0-4
y_raw.npy
Raw string labels — N, L, R, V, A
Classes
Label
Class
Description
0
N
Normal sinus rhythm
1
L
Left bundle branch block
2
R
Right bundle branch block
3
V
Premature ventricular… See the full description on the dataset page: https://huggingface.co/datasets/dheerajthuvara/ecg-arrhythmia-data.clinical-5node-qt-elec-lag-polypharm-arrhythmia-casc-v0.1
What this repo does
This dataset tests whether a model can predict when QT interval stress, electrolyte depletion, governance delay, and polypharmacy coupling push a case past the failure horizon into an arrhythmia cascade.
Core quad
qteleclagpolypharm
Prediction target
label_horizon_breach
Row structure
One row represents a short case vignette with numeric signals for QT stress, electrolyte buffer, response lag, and polypharmacy coupling, paired… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-5node-qt-elec-lag-polypharm-arrhythmia-casc-v0.1.ECG_Arrhythmia_Classification_Datasetheart-arrhythmias-symptoms