Datasets › PTB Diagnostic ECG Database

PTB Diagnostic ECG Database

1 Jan 1995 archive 2025-07-28

The ECGs in this collection were obtained using a non-commercial, PTB prototype recorder with the following specifications:

16 input channels, (14 for ECGs, 1 for respiration, 1 for line voltage) Input voltage: ±16 mV, compensated offset voltage up to ± 300 mV Input resistance: 100 Ω (DC) Resolution: 16 bit with 0.5 μV/LSB (2000 A/D units per mV) Bandwidth: 0 - 1 kHz (synchronous sampling of all channels) Noise voltage: max. 10 μV (pp), respectively 3 μV (RMS) with input short circuit Online recording of skin resistance Noise level recording during signal collection The database contains 549 records from 290 subjects (aged 17 to 87, mean 57.2; 209 men, mean age 55.5, and 81 women, mean age 61.6; ages were not recorded for 1 female and 14 male subjects). Each subject is represented by one to five records. There are no subjects numbered 124, 132, 134, or 161. Each record includes 15 simultaneously measured signals: the conventional 12 leads (i, ii, iii, avr, avl, avf, v1, v2, v3, v4, v5, v6) together with the 3 Frank lead ECGs (vx, vy, vz). Each signal is digitized at 1000 samples per second, with 16 bit resolution over a range of ± 16.384 mV. On special request to the contributors of the database, recordings may be available at sampling rates up to 10 KHz.

Within the header (.hea) file of most of these ECG records is a detailed clinical summary, including age, gender, diagnosis, and where applicable, data on medical history, medication and interventions, coronary artery pathology, ventriculography, echocardiography, and hemodynamics. The clinical summary is not available for 22 subjects.

Source: PTB

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Constituency Grammar Induction PTB Diagnostic ECG Database Ensemble (Generative MBR) Mean F1 (WSJ) 70.4 Ensemble Distillation for Unsupervised Constituency Parsing manga-uofa/ed4ucp 24 Compare
ECG Patient Identification (gallery-probe) PTB Diagnostic ECG Database ElectroCardioGuard Accuracy 77.0% ElectroCardioGuard: Preventing Patient Misidentification... captaintrojan/electrocardioguard 1 Compare
Language Modelling PTB Diagnostic ECG Database I-DARTS PPL 56.0 Improved Differentiable Architecture Search for Language... jiangyingjunn/i-darts 1 Compare
Myocardial infarction detection PTB Diagnostic ECG Database ConvNetQuake Accuracy (%) 99.43% Deep Learning for Cardiologist-level Myocardial... arjung128/mi_detection 1 Compare

Papers archive 2025-07-28

21 shown of 21 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 22. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
On Eliciting Syntax from Language Models via Hashing 1 1 5 Oct 2024 not harvested
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information 1 1 3 Oct 2024 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction 1 2 23 Jul 2024 not harvested
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale 2 1 13 Mar 2024 ran 4 of 7 samples (3 unverified)
Ensemble Distillation for Unsupervised Constituency Parsing 1 2 3 Oct 2023 ran 16 of 22 samples (6 unverified; 22 pointer-only for licence)
Augmenting Transformers with Recursively Composed Multi-grained Representations 1 1 28 Sep 2023 ran 3 of 3 samples (0 unverified)
ElectroCardioGuard: Preventing Patient Misidentification in Electrocardiogram Databases through Neural Networks 1 1 9 Jun 2023 not harvested
Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs 2 1 1 May 2022 not harvested
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation 2 1 1 Mar 2022 ran 0 of 1 samples (1 unverified)
Co-training an Unsupervised Constituency Parser with Weak Supervision 1 1 5 Oct 2021 ran 2 of 3 samples (1 unverified; 1 pointer-only for licence)
Neural Bi-Lexicalized PCFG Induction 1 1 31 May 2021 not harvested
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols 1 1 28 Apr 2021 not harvested
Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders 0 1 1 Nov 2020 not harvested
Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms 1 1 16 Dec 2019 not harvested
Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition 1 1 1 Nov 2019 not harvested
Compound Probabilistic Context-Free Grammars for Grammar Induction 2 2 24 Jun 2019 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders 1 2 1 Jun 2019 not harvested
Unsupervised Recurrent Neural Network Grammars 1 1 7 Apr 2019 not harvested
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks 7 2 22 Oct 2018 ran 3 of 12 samples (9 unverified)
Unsupervised Learning of Syntactic Structure with Invertible Neural Projections 1 1 28 Aug 2018 not harvested
Neural Language Modeling by Jointly Learning Syntax and Lexicon 1 2 2 Nov 2017 ran 0 of 5 samples (5 unverified)

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

Open Data Commons Attribution License v1.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • PTB Diagnostic ECG Database

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections