This dataset is composed of two collections of heartbeat signals derived from two famous PhysioNet datasets in heartbeat classification, the MIT-BIH Arrhythmia Dataset and the PTB Diagnostic ECG Database. The number of samples in both collections is large enough for training a deep neural network.

This dataset has been used in exploring heartbeat classification using deep neural network architectures, and observing some of the capabilities of transfer learning on it. The signals correspond to electrocardiogram (ECG) shapes of heartbeats for the normal case and the cases affected by different arrhythmias and myocardial infarction. These signals are preprocessed and segmented, with each segment corresponding to a heartbeat.

PTB-XL, a large publicly available electrocardiography dataset

The database contains 310 ECG recordings, obtained from 90 persons. Each recording contains:

ECG lead I, recorded for 20 seconds, digitized at 500 Hz with 12-bit resolution over a nominal ±10 mV range;
10 annotated beats (unaudited R- and T-wave peaks annotations from an automated detector);
information (in the .hea file for the record) containing age, gender and recording date.

For research purposes, the ECG signals were obtained from the PhysioNet service (http://www.physionet.org) from the MIT-BIH Arrhythmia database. The created database with ECG signals is described below. 1) The ECG signals were from 29 patients: 15 female (age: 23-89) and 14 male (age: 32-89). 2) The ECG signals contained 17 classes: normal sinus rhythm, pacemaker rhythm, and 15 types of cardiac dysfunctions (for each of which at least 10 signal fragments were collected). 3) All ECG signals were recorded at a sampling frequency of 360 [Hz] and a gain of 200 [adu / mV]. 4) For the analysis, 744, 10-second (3600 samples) fragments of the ECG signal (not overlapping) were randomly selected. 5) Only signals derived from one lead, the MLII, were used.

For research purposes, aforementioned ECG signals were obtained from one PhysioNet service (http://www.physionet.org) from the MIT-BIH Unexplained database. The created database on ECG signals has characterized below. 1) The ECG signals were from 45 patients: 19 womanly (age: 23-89) and 26 male (age: 32-89). 2) The ECG cue contained 17 classes: normal sinus rhythm, pacemaker rhythm, plus 15 types the cardiac dysfunctions (for each of which per slightest 10 signal fragments were collected). 3) All ECG signals were recorded along one sampling frequency of 360 [Hz] or adenine earn in 200 [adu / mV]. 4) For the scrutiny, 1000, 10-second (3600 samples) fragments of the ECG sign (not overlapping) were randomly selected. 5) Only signals derived from one lead, the MLII, were used. 6) Data are on doormat format (Matlab).

Gazi University ECG (GU-ECG) database is a set of ECG data acquired from 74 coronary artery disease patients with severe stenosis (>70%) in at least one coronary artery who had symptoms of chest pain and were planned to undergo elective percutaneous transluminal coronary angioplasty (PTCA) at Department of Cardiology, Faculty of Medicine, Gazi University. It is constructed as a result of a clinical research study performed to investigate morphological anomalies in ECG signals that occur during complete coronary artery occlusion caused by PTCA, which reduces myocardial blood flow and induces acute myocardial ischaemia (AMI), leading to significant changes in ST segment and T wave of ECG [1,2].

Before PTCA, 12-lead pre-inflation ECG recordings were continuously acquired prior to catheter insertion to coronary artery at cardiac catheterization laboratory. During PTCA, 12-lead inflation ECG recordings that started during balloon dilatation, then continued throughout balloon inflation period in a major coronary artery were continuously acquired from all patients. In order to achieve optimal angiographic and clinical results of PTCA, balloon was inflated for at least 60 sec. in each patient and it was deflated either due to the occurrence of chest pain, cardiac arrhythmia, hypotension or after a maximum inflation time of 300 sec. After PTCA, 12-lead post-inflation ECG recordings were continuously acquired at least 180 sec. after balloon deflation in coronary artery at catheterization laboratory.

A portable continuous 12-lead ECG device (microCOR, Infron Ltd), which amplifies, digitizes, processes and transmits data wirelessly to its software via a USB adapter in digital format, was used for data acquisition [3]. Recordings were digitized at a sampling rate of 8800 Hz with 24-bit sampling resolution and 0.1 µV amplitude resolution to produce high-resolution digital signals.

Time instants related to balloon inflation and deflation during PTCA, occluded coronary artery in which PTCA is performed and patient's history of previous myocardial infarction were annotated by experienced cardiologists to facilitate the development and performance evaluation of various signal processing and artificial intelligence techniques that will utilize the GU-ECG database [4,5,6,7]. Only patients receiving elective PTCA in one of major coronary arteries were included in the database, whereas patients who had atrial fibrillation, ventricular tachycardia, paced rhythm, or myocardial infarction during data acquisition were excluded.

12-lead pre-inflation, inflation, and post-inflation ECG recordings of each patient are included in experiment data files section with file extension *.ekg, which is data format of microCOR ECG device. Computer software which receives data from ECG device, displays, saves, and exports it to different file formats is included in experiment data files section with file extension *.exe, which is executable file format of microCOR PC software.

Dataset with annotated 12-lead ECG records. The exams were taken in 811 counties in the state of Minas Gerais/Brazil by the Telehealth Network of Minas Gerais (TNMG) between 2010 and 2016. And organized by the CODE (Clinical outcomes in digital electrocardiography) group.Requesting accessResearchers affiliated to educational or research institutions might make requests to access this data dataset. Requests will be analyzed on an individual basis and should contain: Name of PI and host organisation; Contact details (including your name and email); and, the scientific purpose of data access request.If approved, a data user agreement will be forwarded to the researcher that made the request (through the email that was provided). After the agreement has been signed (by the researcher or by the research institution) access to the dataset will be granted.Openly available subset:A subset of this dataset (with 15% of the patients) is openly available. See: "CODE-15%: a large scale annotated dataset of 12-lead ECGs" https://doi.org/10.5281/zenodo.4916206.ContentThe folder contains: A column separated file containing basic patient attributes. The ECG waveforms in the wfdb format.Additional referencesThe dataset is described in the paper "Automatic diagnosis of the 12-lead ECG using a deep neural network". https://www.nature.com/articles/s41467-020-15432-4. Related publications also using this dataset are:- [1] G. Paixao et al., “Validation of a Deep Neural Network Electrocardiographic-Age as a Mortality Predictor: The CODE Study,” Circulation, vol. 142, no. Suppl_3, pp. A16883–A16883, Nov. 2020, doi: 10.1161/circ.142.suppl_3.16883.- [2] A. L. P. Ribeiro et al., “Tele-electrocardiography and bigdata: The CODE (Clinical Outcomes in Digital Electrocardiography) study,” Journal of Electrocardiology, Sep. 2019, doi: 10/gf7pwg.- [3] D. M. Oliveira, A. H. Ribeiro, J. A. O. Pedrosa, G. M. M. Paixao, A. L. P. Ribeiro, and W. Meira Jr, “Explaining end-to-end ECG automated diagnosis using contextual features,” in Machine Learning and Knowledge Discovery in Databases. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), Ghent, Belgium, Sep. 2020, vol. 12461, pp. 204--219. doi: 10.1007/978-3-030-67670-4_13.- [4] D. M. Oliveira, A. H. Ribeiro, J. A. O. Pedrosa, G. M. M. Paixao, A. L. Ribeiro, and W. M. Jr, “Explaining black-box automated electrocardiogram classification to cardiologists,” in 2020 Computing in Cardiology (CinC), 2020, vol. 47. doi: 10.22489/CinC.2020.452.- [5] G. M. M. Paixão et al., “Evaluation of mortality in bundle branch block patients from an electronic cohort: Clinical Outcomes in Digital Electrocardiography (CODE) study,” Journal of Electrocardiology, Sep. 2019, doi: 10/dcgk.- [6] G. M. M. Paixão et al., “Evaluation of Mortality in Atrial Fibrillation: Clinical Outcomes in Digital Electrocardiography (CODE) Study,” Global Heart, vol. 15, no. 1, p. 48, Jul. 2020, doi: 10.5334/gh.772.- [7] G. M. M. Paixão et al., “Electrocardiographic Predictors of Mortality: Data from a Primary Care Tele-Electrocardiography Cohort of Brazilian Patients,” Hearts, vol. 2, no. 4, Art. no. 4, Dec. 2021, doi: 10.3390/hearts2040035.- [8] G. M. Paixão et al., “ECG-AGE FROM ARTIFICIAL INTELLIGENCE: A NEW PREDICTOR FOR MORTALITY? THE CODE (CLINICAL OUTCOMES IN DIGITAL ELECTROCARDIOGRAPHY) STUDY,” Journal of the American College of Cardiology, vol. 75, no. 11 Supplement 1, p. 3672, 2020, doi: 10.1016/S0735-1097(20)34299-6.- [9] E. M. Lima et al., “Deep neural network estimated electrocardiographic-age as a mortality predictor,” Nature Communications, vol. 12, 2021, doi: 10.1038/s41467-021-25351-7.- [10] W. Meira Jr, A. L. P. Ribeiro, D. M. Oliveira, and A. H. Ribeiro, “Contextualized Interpretable Machine Learning for Medical Diagnosis,” Communications of the ACM, 2020, doi: 10.1145/3416965.- [11] A. H. Ribeiro et al., “Automatic diagnosis of the 12-lead ECG using a deep neural network,” Nature Communications, vol. 11, no. 1, p. 1760, 2020, doi: 10/drkd.- [12] A. H. Ribeiro et al., “Automatic Diagnosis of Short-Duration 12-Lead ECG using a Deep Convolutional Network,” Machine Learning for Health (ML4H) Workshop at NeurIPS, 2018.- [13] A. H. Ribeiro et al., “Automatic 12-lead ECG classification using a convolutional network ensemble,” 2020. doi: 10.22489/CinC.2020.130.- [14] V. Sangha et al., “Automated Multilabel Diagnosis on Electrocardiographic Images and Signals,” medRxiv, Sep. 2021, doi: 10.1101/2021.09.22.21263926.- [15] S. Biton et al., “Atrial fibrillation risk prediction from the 12-lead ECG using digital biomarkers and deep representation learning,” European Heart Journal - Digital Health, 2021, doi: 10.1093/ehjdh/ztab071.Code:The following github repositories perform analysis that use this dataset:- https://github.com/antonior92/automatic-ecg-diagnosis- https://github.com/antonior92/ecg-age-predictionRelated Datasets:- CODE-test: An annotated 12-lead ECG dataset (https://doi.org/10.5281/zenodo.3765780)- CODE-15%: a large scale annotated dataset of 12-lead ECGs (https://doi.org/10.5281/zenodo.4916206)- Sami-Trop: 12-lead ECG traces with age and mortality annotations (https://doi.org/10.5281/zenodo.4905618)Ethics declarationsThe CODE Study was approved by the Research Ethics Committee of the Universidade Federal de Minas Gerais, protocol 49368496317.7.0000.5149.

ECG images dataset of Cardiac Patients created under the auspices of Ch. Pervaiz Elahi Institute of Cardiology Multan, Pakistan that aims to help the scientific community for conducting the research for Cardiovascular diseases.

A beginner-friendly version of the MIT-BIH Arrhythmia Database, which contains 48 electrocardiograms (EKGs) from 47 patients that were at Beth Israel Deaconess Medical Center in Boston, MA in 1975-1979.

There are 48 CSVs, each of which is a 30-minute echocardiogram (EKG) from a single patient (record 201 and 202 are from the same patient). Data was collected at 360 Hz, meaning that 360 rows is equal to 1 second of time.

Banner photo by Joshua Chehov on Unsplash.

How to Analyze the Heart with Python

1. How the Heart Works (and What is a "QRS" Complex?)
2. How to Identify and Label the Waves of an EKG
3. How to Flatten a Wandering EKG
4. How to Calculate the Heart Rate

What is a 12-lead EKG?

EKGs, or electrocardiograms, measure the heart's function by looking at its electrical activity. The electrical activity in each part of the heart is supposed to happen in a particular order and intensity, creating that classic "heartbeat" line (or "QRS complex") you see on monitors in medical TV shows.

There are a few types of EKGs (4-lead, 5-lead, 12-lead, etc.), which give us varying detail about the heart. A 12-lead is one of the most detailed types of EKGs, as it allows us to get 12 different outputs or graphs, all looking at different, specific parts of the heart muscles.

This dataset only publishes two leads from each patient's 12-lead EKG, since that is all that the original MIT-BIH database provided.

What does each part of the QRS complex mean?

Check out Ninja Nerd's EKG Basics tutorial on YouTube to understand what each part of the QRS complex (or heartbeat) means from an electrical standpoint.

Filenames

Each file's name is the ID of the patient (except for 201 and 202, which are the same person).

Columns

• index
• calculated elapsed milliseconds (index / 360 * 1000)
• the first lead
• the second lead

The two leads are often lead MLII and another lead such as V1, V2, or V5, though some datasets do not use MLII at all. MLII is the lead most often associated with the classic QRS Complex (the medical name for a single heartbeat).

Milliseconds were calculated and added as a secondary index to each dataset. Calculations were made by dividing the index by 360 Hz then multiplying by 1000. The original index was preserved, since the calculation of milliseconds as digital signals processing (e.g. filtering) occurs may cause issues with the correlation and merging of data. You are encouraged to try whichever index is most suitable for your analysis and/or recalculate a time index with Pandas' to_timedelta().

Patient information

Info about each of the 47 patients is available here, including age, gender, medications, diagnoses, etc.

Getting Started

Physionet has some online tutorials and tips for analyzing EKGs and other time series / digital signals.

Check out our notebook for opening and visualizing the data.

How the CSVs were obtained

A write-up on how the data was converted from .dat to .csv files is available on Medium.com. Data was downloaded from the MIT-BIH Arrhythmia Database then converted to CSV.

The MIMIC-IV-ECG module contains approximately 800,000 diagnostic electrocardiograms across nearly 160,000 unique patients. These diagnostic ECGs use 12 leads and are 10 seconds in length. They are sampled at 500 Hz. This subset contains all of the ECGs for patients who appear in the MIMIC-IV Clinical Database. When a cardiologist report is available for a given ECG, we provide the needed information to link the waveform to the report. The patients in MIMIC-IV-ECG have been matched against the MIMIC-IV Clinical Database, making it possible to link to information across the MIMIC-IV modules.

Fall is a prominent issue due to its severe consequences both physically and mentally. Fall detection and prevention is a critical area of research because it can help elderly people to depend less on caregivers and allow them to live and move more independently. Using electrocardiograms (ECG) signals independently for fall detection and activity classification is a novel approach used in this paper. An algorithm has been proposed which uses pre-trained convolutional neural networks AlexNet and GoogLeNet as a classifier between the fall and no fall scenarios using electrocardiogram signals. The ECGs for both falling and no falling cases were obtained as part of the study using eight volunteers. The signals are pre-processed using an elliptical filter for signal noises such as baseline wander and power-line interface. As feature extractors, frequency-time representations (scalograms) were obtained by applying a continuous wavelet transform on the filtered ECG signals. These scalograms were used as inputs to the neural network and a significant validation accuracy of 98.08% was achieved in the first model. The trained model is able to distinguish ECGs with a fall activity from an ECG with a no fall activity with an accuracy of 98.02%. For the verification of the robustness of the proposed algorithm, our experimental dataset was augmented by adding two different publicly available datasets to it. The second model can classify fall, daily activities and no activities with an accuracy of 98.44%. These models were developed by transfer learning from the domain of real images to the medical images. In comparison to traditional deep learning approaches, the transfer learning not only avoids “reinventing the wheel,” but also presents a lightweight solution to otherwise computationally heavy problems.

The Harvard-Emory ECG database (HEEDB) is a large collection of 12-lead electrocardiography (ECG) recordings, prepared through a collaboration between Harvard University and Emory University investigators.

These ECGs are provided without labels or metadata for now, to enable pre-training of ECG analysis models. Labels and metadata will be provided in a subsequent installment of this dataset. Labels and metadata are withheld for now while we prepare them for a public computing challenge. Stay tuned for an announcement about the challenge.

HEEDB is published as part of the Human Sleep Project (HSP), funded by a grant (R01HL161253) from the National Heart Lung and Blood Institute (NHLBI) of the NIH to Massachusetts General Hospital, Emory University, Stanford University, Kaiser Permanente, Boston Children's Hospital, and Beth Israel Deaconess Medical Center.

Abstract

The NCKU CBIC ECG database collects ECG data from 6 different patients. Each patient collects lead II ECG for four hours a day to highlight patients' different physiological meanings at different times of the day, and the database provides the labels for motion artifact and baseline wandering, which are invalid signal for diagnosis. Prevent physicians from using the noise signal to diagnose. These data were collected using Patch[1] at Tainan Hospital.

Background

Technology and medical treatment are highly developed in the 21st century, and people have more irregular daily routines and greater life pressure. Cardiovascular disease has become a tough nut to crack when the changing of lifestyle is coupled with the aging of society. The age distribution of patients is wider than ever. A wealth of health information can be obtained through electrocardiogram (ECG) measurement, including cardiac arrhythmias. Severe arrhythmias will lead to many life problems, including palpitations, chest tightness, dizziness, shock, and even life-threatening conditions. Therefore, the monitoring of ECG signal is quite essential.
To do our part in the study of arrhythmia, our team started the patient enrollment after gaining the permission of the National Cheng Kung University Hospital Institutional Review Board (NCKUH IRB No. B-ER-104-379) from 2018. We have selected total 128 patients' 24 hours ECG data until now. The results of the arrhythmia label are confirmed by the cardiologist Ju-Yi Chen in NCKUH. Finally, We selected 6 patients from the received signals and made them into a database for researchers to access.

Methods

The NCKU CBIC ECG database contains the ECG recordings from 6 subjects. The signals were collected in Tainan Hospital (Ministry of Health and Welfare) via an ECG acquisition device[1] developed by Your health technology Co., Ltd. The sampling frequency is 400Hz, and the ADC resolution is 12 bits. The age distribution of subjects was from 24 to 76 years old, and each patient was measured at the lead II for 24 hours. After the signal is recorded, four cleaner segments in the morning, noon, evening, and midnight are selected, and each segment is one hour long. The heartbeat of human body is different when sleeping and awake, and some arrhythmia type occurs at sleeping period often. It's hard to detect some arrhythmia at specific time of a day, therefore, we choose signal segments from different time period for a patient, which is more representative of the daily heartbeat condition. It's worth mentioning that the ECG signals from the 6th subject contains too many noise signals in the daytime due to his career type, so the segments from 22:00 to 02:00 are selected.
We have collected total 128 patients from Tainan Hospital since 2018. Since most of the ECG data of patients are normal beats, we finally selected the ECG data of six patients which contain clinically significant arrhythmia. The database provides two particular label type for motion artifact and baseline wandering, which are caused by body movement during ECG acquisition. In actual situations, cardiologist doesn't use the noise signals as a basis for diagnosis, therefore, these two specific labels prevent physicians from using noise to make a diagnosis. The original data is first compared with the holter report, and the R peak position and beat labels are manually marked. And then the data were given to a professional cardiologist, Ju-Yi, Chen, for verification. The cardiologist checked the correction and position of beat labels, and chose the acceptable signal segmentation for high quality.

Introduction of Ju-Yi, Chen :
JU-YI CHEN was born in Tainan, Taiwan, in 1974. He received the M.S. degree from Chang Gung University, Taoyuan City, Taiwan, in 1999 and the Ph.D. degree from the National Cheng Kung University, Tainan, in 2013. Since 2021, he has been a Professor at the Department of Internal Medicine, National Cheng Kung University. His current research interests include the cardiovascular diseases, including arrhythmias, hypertension, arterial stiffness, and cardiac implantable electric devices.

Data Description

The file structure and naming rule are described as follows : [The subject number]_[The measurement time] : The directory name

OUTPUT_ECG_data.csv : The one-hour ECG signals ( unit : 0.1V ) OUTPUT_peak_label.csv : The arrhythmia type label of R-peak OUTPUT_peak_position.csv : The position of R-peak

ex : 1_0100 directory contains subject No. 1's data which is measured at 01:00.

Arrhythmia diseases and the corresponding label codes :

Code Arrhythmia Disease ————————————————————— 0 Normal 1 Atrial Fibrillation 2 Supraventricular Tachycardia 3 Premature Ventricular Contraction 4 Atrial Premature Contraction 5 Motion Artifact 6 Wandering 7 First degree AV block 8 Atrial Flutter

PS : Wandering represents baseline drifted by 1mV.

Patient information :

Subject 1: Male，61 years Subject 2: Female，77 years Subject 3: Male，63 years Subject 4: Male，64 years Subject 5: Male，24 years Subject 6: Male，64 years

Usage Notes

Few public ECG databases provide long-term ECG, our goal in creating the database is to help understand what a person's ECG looks like in a day, and this database is more valuable in obtaining long-term ECG.

Ethics

Our team has cooperated with National Cheng Kung University Hospital and Tainan Hospital. All the patients enrolled gave their informed consent to participate in the study. The certification of safety-related IEC standards and human study approval are all acquired.

Conflicts of Interest The authors declare that there are no known conflicts of interest.

References

S.-Y. Lee, P.-W. Huang, M.-C. Liang, J.-H. Hong, and J.-Y. Chen, "Development of an arrhythmia monitoring system and human study," IEEE Transactions on Consumer Electronics, vol. 64, no. 4, pp. 442-451, 2018.

This dataset contains ECG images of Cardiac Patients . The Cardiac data have been pre-classified .

Abstract The Norwegian Endurance Athlete ECG Database contains 12-lead ECG recordings from 28 elite athletes from various sports in Norway. All recordings are 10 seconds resting ECGs recorded with a General Electric (GE) MAC VUE 360 electrocardiograph. All ECGs are interpreted with both the GE Marquette SL12 algorithm (version 23 (v243)) and one cardiologist with training in interpretation of athlete's ECG. The data was collected at the University of Oslo in February and March 2020.

Background Athletes often have increased thickness in the left ventricular wall and extended chambers in both the left and right ventricle compared to untrained people at the same age [1]. These changes occur as a result of the heart adapting to large amounts of exercise. These changes can be seen on an echocardiogram, but the changes also give electrical manifestations that can be observed on an electrocardiogram (ECG). Even if these changes are considered healthy, they can be confused with pathological changes that are related to sudden cardiac death (SCD) [2]. In addition, studies show that the incidence of SCD is higher in athletes than in non-athletes of the same age [3,4]. Current measures and procedures for detecting athletes with an increased risk of SCD are characterized by low accuracy and low precision. This emphasizes that ECG interpretation of athletes is an area that requires increased focus.

Methods Twenty-eight healthy athletes were recruited for this study. 19 (68%) of the participants were men and 9 (32%) were women. Participant's ages ranged from 20 to 43 years (Mean = 25 years, standard deviation = 4.7 years). The distribution among sports was 24 rowers (86%), 2 kayakers (7%) and 2 cyclists (7%). The average amount of training hours for 2017 was 822 hours with a standard deviation of 117 hours, in 2018 the average amount of training was 820 hours with a standard deviation of 113 hours and in 2019 the average amount of training was 798 hours with a standard deviation of 171 hours.

The study protocol and consent form were approved by the Norwegian Centre for Research Data (application ID: 389013) and the University of Oslo, and the ethical considerations were approved by the Regional Committees for Medical and Health Research Ethics (application ID: 51205). All participants were informed and gave written consent before the test was initiated, they also agreed to have their ECG shared in an open database after the project was finished. The test subjects were lying horizontally on a bed, relaxing, while electrodes were attached to perform a 12-lead ECG recording. The recordings were performed as a standard 10 seconds resting ECG. The device used was a GE MAC VUE 360. The device's built-in interpretation algorithm, Marquette 12SL (version 23 (v243)), performed automatic interpretation of all ECGs.

All ECG recordings were examined by a cardiologist, with specialization in athletes' hearts, after the recordings were completed. The cardiologist interpreted the ECGs according to the international criteria for ECG interpretation of athletes.

Data Description Each of the 28 waveform files consists of 12 arrays, representing the twelve leads. The ECGs were obtained using a General Electric (GE) MAC VUE 360 electrocardiograph and interpreted using the built-in ECGs are GE Marquette SL12 algorithm (version 23 (v243)) and a cardiologist with training in interpretation of athlete's ECG.

The waveform files are stored in .dat -files with a corresponding .hea file containing all the metadata. This file formats are compatible with the Python WaveForm DataBase (WFDB) package and this makes it easy to import the data.

All ECG waveforms are sampled and stored with a sampling frequency of 500Hz and a length of 5000 samples (10 seconds). The header file contains information about the total amount of leads, samples per lead and additional information about each lead. The last two lines in the header file contains the diagnose given by the Marquette SL12 (SL12) algorithm and the cardiologist (C). ``` ath_001 12 500 5000 ath_001.dat 16 50000/mV 16 0 10251 49595 0 I ath_001.dat 16 50000/mV 16 0 -1096 35223 0 II ath_001.dat 16 50000/mV 16 0 -10267 60826 0 III ath_001.dat 16 50000/mV 16 0 -3724 3505 0 AVR ath_001.dat 16 50000/mV 16 0 9391 26379 0 AVL ath_001.dat 16 50000/mV 16 0 -5395 57481 0 AVF ath_001.dat 16 50000/mV 16 0 13580 61759 0 V1 ath_001.dat 16 50000/mV 16 0 11410 33501 0 V2 ath_001.dat 16 50000/mV 16 0 14721 52508 0 V3 ath_001.dat 16 50000/mV 16 0 16103 51083 0 V4 ath_001.dat 16 50000/mV 16 0 6662 44197 0 V5 ath_001.dat 16 50000/mV 16 0 -3806 11333 0 V6

SL12: sinus bradycardia with marked sinus arrhythmia, Right Axis Deviation, Borderline ECG C: Sinus arrhythmia, Normal ECG ```

Usage Notes The intended use of this database is for the development of better algorithms designed to make better diagnostics for athletes based on ECG. One of the unique features of this database is that the ECGs are annotated by both a trained cardiologist and by a state-of-the-art ECG software (GE Marquette SL12).

To get started in Python you can use this code to import the ECG-signals and metadata ``` import wfdb import numpy as np import os

directory = "./your/directory/" ECGs = [] for ecgfilename in sorted(os.listdir(directory )): if ecgfilename.endswith(".dat"): ecg = wfdb.rdsamp(directory + ecgfilename.split(".")[0]) ECGs.append(ecg) ECGs = np.asarray(ECGs) ``` The numpy array (ECGs) now contains all ECG signals and metadata.

Despite the fact that the measurements were taken from top-trained athletes it is not confirmed whether they had athletic remodeling of the heart or not. No echocardiographic or other examinations were performed to investigate the structure of the heart.

Release Notes 1.0.0 Initial release of the dataset.

Ethics The authors declare no ethics concerns.

Acknowledgements I will thank Professor Emeritus Knut Gjessdal for providing his medical expertise and interpreting all of the ECGs. This work was done at the University of Oslo and I will thank Professor Ørjan Grrøttem Martinsen for providing appropriate facilities for ECG measurements.

Study sample

The sample consisted of 71 university students, average age 20.38 years (SD = 2.96), 78.8% female. Subjects with previous cardio-vascular disorders and irregular ECG were excluded (analysis was performed in 70 records). The study has been approved by the Institutional Review Board of the Department of Psychology, University of Belgrade No. 2018-19. All participants signed Informed Consents in accordance with the Declaration of Helsinki.

In the course of visual examination, it was decided to discard ECG from one subject due to the presence of bigeminial arythmia, so further analysis was performed on 70 subjects instead of 71.

Measurement setup

BIOPAC sensors (Biopac Systems Inc., Camino Goleta, CA, USA) were used for recording biosignals in another study (Bjegojević et al., 2020). Here, we used only ECG signals recorded in sitting relaxed position from standard bipolar Lead I using the BIOPAC MP150 unit with AcqKnowledge software and ECG 100C module with surface H135SG Ag/AgCl electrodes (Kendall/Covidien, Dublin, Ireland). In order to decrease skin-electrode impedance, the skin was cleaned with Nuprep gel (Weaver & Co., Aurora, USA) to reduce skin-electrode impedance. The sampling frequency was set at 2000 Hz and gain was set to 1000.

Dataset and code contents

1. ecg_70.txt, .txt data file, text format
2. main.R, main program written in R programming language (will be published ...)
3. analysis.R, code with analysis procedures written in R programming language (will be published ...)

Citing instruction

If you find these signals and code useful for your own research or teaching class, please cite both relevant dataset, paper, and paper under review as:

1. Bjegojević, B., Milosavljević, N., Dubljević, O., Purić, D., & Knežević, G. (2020). In pursuit of objectivity: Physiological measures as a means of emotion induction procedure validation. XXIVI Scientific Conference on Empirical Studies in Psychology, p. 17-19.

2. Boljanić, T., Miljković, N., Lazarević B. Lj., Knežević, G., & Milašinović, G. (2021). Surface electrocardiogram (ECG) dataset recorded during relaxation in 70 healthy subjects (Version 1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.5599239

3. Boljanić, T., Miljković, N., Lazarević, B. Lj., Knežević, G., & Milašinović, G. (2021). Relationship between electrocardiogram-based features and personality traits: Machine learning approach. Annals of Noninvasive Electrocardiology, under review.

The data presented here was extracted from a larger dataset collected through a collaboration between the Embedded Systems Laboratory (ESL) of the Swiss Federal Institute of Technology in Lausanne (EPFL), Switzerland and the Institute of Sports Sciences of the University of Lausanne (ISSUL). In this dataset, we report the extracted segments used for an analysis of R peak detection algorithms during high intensity exercise.

Protocol of the experiments The protocol of the experiment was the following.

22 subjects performing a cardio-pulmonary maximal exercise test on a cycle ergometer, using a gas mask. A single-lead electrocardiogram (ECG) was measured using the BIOPAC system. An initial 3 min of rest were recorded. After this baseline, the subjects started cycling at a power of 60W or 90W depending on their fitness level. Then, the power of the cycle ergometer was increased by 30W every 3 min till exhaustion (in terms of maximum oxygen uptake or VO2max). Finally, physiology experts assessed the so-called ventilatory thresholds and the VO2max based on the pulmonary data (volume of oxygen and CO2).

Description of the extracted dataset

The characteristics of the dataset are the following:

We report only 20 out of 22 subjects that were used for the analysis, because for two subjects the signals were too corrupted or not complete. Specifically, subjects 5 and 12 were discarded. The ECG signal was sampled at 500 Hz and then downsampled at 250 Hz. The original ECG signal were measured at maximum 10 mV. Then, they were scaled down by a factor of 1000, hence the data is represented in uV. For each subject, 5 segments of 20 s were extracted from the ECG recordings and chosen based on different phases of the maximal exercise test (i.e., before and after the so-called second ventilatory threshold or VT2, before and in the middle of VO2max, and during the recovery after exhaustion) to represent different intensities of physical activity.

seg1 --> [VT2-50,VT2-30] seg2 --> [VT2+60,VT2+80] seg3 --> [VO2max-50,VO2max-30] seg4 --> [VO2max-10,VO2max+10] seg5 --> [VO2max+60,VO2max+80]

The R peak locations were manually annotated in all segments and reviewed by a physician of the Lausanne University Hospital, CHUV. Only segment 5 of subject 9 could not be annotated since there was a problem with the input signal. So, the total number of segments extracted were 20 * 5 - 1 = 99.

Format of the extracted dataset

The dataset is divided in two main folders:

The folder ecg_segments/ contains the ECG signals saved in two formats, .csv and .mat. This folder includes both raw (ecg_raw) and processed (ecg) signals. The processing consists of a morphological filtering and a relative energy non filtering method to enhance the R peaks. The .csv files contain only the signal, while the .mat files include the signal, the time vector within the maximal stress test, the sampling frequency and the unit of the signal amplitude (uV, as we mentioned before). The folder manual_annotations/ contains the sample indices of the annotated R peaks in .csv format. The annotation was done on the processed signals.

The provided database of 260 ECG signals was collected from patients with out-of-hospital cardiac arrest while treated by the emergency medical services. Each ECG signal contains a 9 second waveform showing ventricular fibrillation, followed by 1 minute of post-shock waveform. Patients’ ECGs are made available in multiple formats. All ECGs recorded during the prehospital treatment are provided in PFD files, after being anonymized, printed in paper, and scanned. For each ECG, the dataset also includes the whole digitized waveform (9 s pre- and 1 min post-shock each) and numerous features in temporal and frequency domain extracted from the 9 s episode immediately prior to the first defibrillation shock. Based on the shock outcome, each ECG file has been annotated by three expert cardiologists, - using majority decision -, as successful (56 cases), unsuccessful (195 cases), or indeterminable (9 cases). The code for preprocessing, for feature extraction, and for limiting the investigation to different temporal intervals before the shock is also provided. These data could be reused to design algorithms to predict shock outcome based on ventricular fibrillation analysis, with the goal to optimize the defibrillation strategy (immediate defibrillation versus cardiopulmonary resuscitation and/or drug administration) for enhancing resuscitation.