PTB-XL, a large publicly available electrocardiography dataset

Abstract

Electrocardiography (ECG) is a key non-invasive diagnostic tool for cardiovascular diseases which is increasingly supported by algorithms based on machine learning. Major obstacles for the development of automatic ECG interpretation algorithms are both the lack of public datasets and well-defined benchmarking procedures to allow comparison s of different algorithms. To address these issues, we put forward PTB-XL, the to-date largest freely accessible clinical 12-lead ECG-waveform dataset comprising 21837 records from 18885 patients of 10 seconds length. The ECG-waveform data was annotated by up to two cardiologists as a multi-label dataset, where diagnostic labels were further aggregated into super and subclasses. the dataset covers a broad range of diagnostic classes including, in particular, a large fraction of healthy records. the combination with additional metadata on demographics, additional diagnostic statements, diagnosis likelihoods, manually annotated signal properties as well as suggested folds for splitting training and test sets turns the dataset into a rich resource for the development and the evaluation of automatic ECG interpretation algorithms.

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

“…In this section, we briefly introduce the PTB-XL dataset [15] that underlies most experiments presented below. The PTB-XL dataset comprises 21837 clinical 12-lead ECG records of 10 seconds length from 18885 patients, where 52 % were male and 48 % were female.…”

“…The ECG statements used for annotation are conform to the SCP-ECG standard [20] and Fig. 1: Summary of the PTB-XL dataset [15] in terms of diagnostic superclasses, where NORM: normal ECG, MI: myocardial infarction, CD: conduction disturbance, STTC: ST/Tchanges, HYP: hypertrophy.…”

“…For diagnostic statements also a hierarchical organization into five coarse superclasses and 24 sub-classes is provided, see Figure 1 for a graphical summary in terms of diagnostic superclasses. For further details on the dataset, the annotation scheme, and other ECG datasets we refer the reader to the original publication [15]. To summarize, PTB-XL does not only stand out by its size as the to-date largest publicly accessible clinical ECG dataset but also through its rich set of ECG annotations and further metadata, which turns the dataset into an ideal resource for the training and evaluation of machine learning algorithms.…”

“…In reverse, we see these two aspects as two major issues that hamper the progress in algorithmic ECG analysis: First, open ECG datasets are typically very small [13] and existing large datasets remain inaccessible for the general public. This issue has been at least partially resolved by the publication of the PTB-XL dataset [14], [15] hosted by PhysioNet [16], which represents the to-date largest freely accessible ECG dataset. In addition, many of the freely accessible databases contain only single lead recordings, which makes comprehensive diagnosis and clinical validation difficult.…”

“…• We propose different benchmarking tasks on the recently published PTB-XL dataset [15] ranging from ECG statement prediction from different subsets of ECG statements and label granularities to age and sex prediction within a structured evaluation methodology. • We implement and adapt different state-of-the-art deeplearning-based time series classification algorithms and adapt recent image classification algorithms to the ECG context including a new resnet-adaptation (xresnet1d101) that turns out to be the best-performing algorithm across all tasks.…”