Skip to main content

ECG library with pretrained models and tools for ECG analysis

Project description


Table of contents


Ecg library (ecglib) is a tool for ECG signal analysis. The library helps with preprocessing ECG signals, downloading the datasets, creating Dataset classes to train models to detect ECG pathologies. The library allows researchers to use model architectures pretrained on more than 500,000 ECG records to fine-tune them on their own datasets.


This module allows user to load and store ECG datasets in different formats and to extract meta-information about each single ECG signal (i.e. frequency, full path to file, scp-codes, patient age etc.).

Via one can download PTB-XL ECG database in its original wfdb format and to store information concerning each record in a csv file.

# download PTB-XL ECG dataset

from ecglib.datasets import load_ptb_xl

ptb_xl_info = load_ptb_xl(download=True) script contains classes for storing ECG datasets.

  • ECGDataset is a general class for storing main features of your ECG dataset such as number of leads, number of classes to predict, augmentation etc..
  • PTBXLDataset is a child class with respect to ECGDataset; one can load each record from wfdb or npz format and preprocess it before further utilization. It is also possible to create a png picture of each record using ecg-plot.
# create PTBXLDataset class from PTB-XL map file
# fit targets for 'AFIB' binary classification

from ecglib.datasets import PTBXLDataset 

targets = [[0.0] if 'AFIB' in eval(ptb_xl_info.iloc[i]['scp_codes']).keys() else [1.0] 
           for i in range(ptb_xl_info.shape[0])]
ecg_data = PTBXLDataset(ecg_data=ptb_xl_info, target=targets)


This module comprises components of model architectures and open weights for models derived from binary classification experiments in several pathologies.

create_model function allows user to create a model from scratch (currently supported architectures include densenet1d121, densenet1d201) as well as load a pretrained model checkpoint from weights folder (currently supported architectures include densenet1d121).

# create 'densenet1d121' model from scratch for binary classification 12-lead experiment

from ecglib.models import create_model

model = create_model(model_name='densenet1d121', pathology='1AVB', pretrained=False, leads_num=12)
# load pretrained 'densenet1d121' model from 'weights' folder for binary classification 12-lead experiment

from ecglib.models import create_model

model = create_model(model_name='densenet1d121', pathology='AFIB', pretrained=True, leads_num=12)

architectures folder includes model architectures.

config folder contains default parameter dataclasses for building a model.

In weights folder one can find file with paths to the models derived from the following binary classification 12-lead experiments. Currently avaliable pathologies (scp-codes): AFIB, 1AVB, STACH, SBRAD, RBBB, LBBB, PVC, LVH.


This module includes framework inspired by Albumentations Python library for preprocessing and augmenting ECG data. script contains SomeOf, OneOf and Compose structures for building your own preprocessing and augmentation pipeline. and both comprise classes and functions respectively describing different preprocessing and augmentation techniques. For more information see code commentary.

# augmentation example
import torch
from ecglib.preprocessing.preprocess import *
from ecglib.preprocessing.composition import *

# provide an ecg-record in `numpy.ndarray` form
ecg_record = read_any_ECG_ndarray_type

augmented_record = Compose(transforms=[
    SumAug(leads=[0, 6, 11]), 
    OneOf(transforms=[ButterworthFilter(), IIRNotchFilter()], transform_prob=[0.8, 0.2])
], p=0.5)(ecg_record)


Next release in December 2022

  • Datasets: add support for more data formats and datasets. Change TisDataset/PTBXLDataset to remove duplicates
  • Models: add more model architectures and weights of these models for different pathologies
  • Preprocessing: add class ECGrecord and update preprocessing methods
  • Add possibility to use metadata for analysis
  • Add complex segmentation methods


This project is made possible by:

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ecglib-1.0.1.tar.gz (20.6 kB view hashes)

Uploaded Source

Built Distribution

ecglib-1.0.1-py3-none-any.whl (22.2 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page