PTB-XL benchmark ECG classifier (xresnet1d101)

Fraunhofer HHI (Strodthoff et al.)

12-lead ECG

Filter catalog by Modality:
ECG

General Purpose / Multi-task

Filter catalog by Disease / Trait:
General / Foundation

Multi-label classification

Filter catalog by Task Type:
Classification

CNN (1D)

Filter catalog by Architecture:
Convolutional (CNN)

PyTorch

Filter catalog by Framework:
PyTorch

GPL 3.0

Filter catalog by License:
Copyleft

file_copy

View model files code View code

Reference benchmark suite for the PTB-XL ECG dataset, providing pretrained xresnet1d, InceptionTime, LSTM, and CPC-pretrained models for 71-label, diagnostic, sub-diagnostic, and super-diagnostic classification of ECG findings. Widely used as a standardized baseline for comparing new ECG classification methods. Developed by Strodthoff et al. at Fraunhofer HHI.

memory Specifications

gavel License

GPL 3.0

check_small Open source check_small Commercial use OK check_small Modifications allowed Attribution required Share-alike required

License for model weights only. Associated code may be licensed seperately, check code source for specific terms.

description Publication

Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL open_in_new

2021 · original paper

DOI: 10.1109/JBHI.2020.3022989

database Training & evaluation data

PTB-XL open_in_new

testtrain

public 18,885 subjects · Germany · 1989-1996

52% male / 48% female; age range 0-95 (median ~62). 21,837 10-second 12-lead ECG records.

science Capabilities & performance

All 71 SCP-statements (multi-label)

Multi-label classification General Purpose / Multi-task

0.925 AUROC PTB-XL · internal

CVAI Catalog

View Catalog