The UCR Time Series Archive - introduced in 2002, has become an important resource in the time series data mining community, with at least one thousand published papers making use of at least one data set from the archive. The original incarnation of the archive had sixteen data sets but since that time, it has gone through periodic expansions. The last expansion took place in the summer of 2015 when the archive grew from 45 to 85 data sets. This paper introduces and will focus on the new data expansion from 85 to 128 data sets. Beyond expanding this valuable resource, this paper offers pragmatic advice to anyone who may wish to evaluate a new algorithm on the archive. Finally, this paper makes a novel and yet actionable claim: of the hundreds of papers that show an improvement over the standard baseline (1-nearest neighbor classification), a large fraction may be misattributing the reasons for their improvement. Moreover, they may have been able to achieve the same improvement with a much simpler modification, requiring just a single line of code.

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

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.

Electrocardiography (ECG) is a key diagnostic tool to assess the cardiac condition of a patient. Automatic ECG interpretation algorithms as diagnosis support systems promise large reliefs for the medical personnel - only on the basis of the number of ECGs that are routinely taken. However, the development of such algorithms requires large training datasets and clear benchmark procedures. In our opinion, both aspects are not covered satisfactorily by existing freely accessible ECG datasets. The PTB-XL ECG dataset is a large dataset of 21799 clinical 12-lead ECGs from 18869 patients of 10 second length. The raw waveform data was annotated by up to two cardiologists, who assigned potentially multiple ECG statements to each record. The in total 71 different ECG statements conform to the SCP-ECG standard and cover diagnostic, form, and rhythm statements. To ensure comparability of machine learning algorithms trained on the dataset, we provide recommended splits into training and test sets. In combination with the extensive annotation, this turns the dataset into a rich resource for the training and the evaluation of automatic ECG interpretation algorithms. The dataset is complemented by extensive metadata on demographics, infarction characteristics, likelihoods for diagnostic ECG statements as well as annotated signal properties. Source: PTB-XL

A dataset of 12-lead ECGs with annotations. The dataset contains 345 779 exams from 233 770 patients. It was obtained through stratified sampling from the CODE dataset ( 15% of the patients). The data was collected by the Telehealth Network of Minas Gerais in the period between 2010 and 2016. Source: CODE-15%

Data Description The training data contains twelve-lead ECGs. The validation and test data contains twelve-lead, six-lead, four-lead, three-lead, and two-lead ECGs: 1. Twelve leads: I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, V6 2. Six leads: I, II, III, aVR, aVL, aVF 3. Four leads: I, II, III, V2 4. Three leads: I, II, V2 5. Two leads: I, II Each ECG recording has one or more labels that describe cardiac abnormalities (and/or a normal sinus rhythm). We mapped the labels for each recording to SNOMED-CT codes. The lists of scored labels and unscored labels are given with the evaluation code; see the scoring section for details. # Data Sources The Challenge data include recordings from last year’s Challenge and many new recordings for this year’s Challenge: 1. CPSC Database and CPSC-Extra Database 2. INCART Database 3. PTB and PTB-XL Database 4. The Georgia 12-lead ECG Challenge (G12EC) Database 5. Augmented Undisclosed Database 6. Chapman-Shaoxing and Ningbo Database 7. The University of Michigan (UMich) Database The Challenge data include annotated twelve-lead ECG recordings from six sources in four countries across three continents. These databases include over 100,000 twelve-lead ECG recordings with over 88,000 ECGs shared publicly as training data, 6,630 ECGs retained privately as validation data, and 36,266 ECGs retained privately as test data. - The first source is the China Physiological Signal Challenge in 2018 (CPSC 2018), which was held during the 7th International Conference on Biomedical Engineering and Biotechnology in Nanjing, China. This source contains two databases: the data from CPSC 2018 (the CPSC Database) and unused data from CPSC 2018 (the CPSC-Extra Database). Together, these databases contain 13,256 ECGs (10,330 ECGs shared as training data, 1,463 retained as validation data, and 1,463 retained as test data). We shared the training set and an unused dataset from CPSC 2018 as training data, and we split the test set from CPSC 2018 into validation and test sets. Each recording is between 6 and 144 seconds long with a sampling frequency of 500 Hz. - The second source is the St Petersburg INCART 12-lead Arrhythmia Database. This source contains 74 annotated ECGs (all shared as training data) extracted from 32 Holter monitor recordings. Each recording is 30 minutes long with a sampling frequency of 257 Hz. - The third source is the Physikalisch-Technische Bundesanstalt (PTB) and includes two public datasets: the PTB and the PTB-XL databases. The source contains 22,353 ECGs (all shared as training data). Each recording is between 10 and 120 seconds long with a sampling frequency of either 500 or 1,000 Hz. - The fourth source is a Georgia database which represents a unique demographic of the Southeastern United States. This source contains 20,672 ECGs (10,344 ECGs shared as training data, 5,167 retained as validation data, and 5,161 retained as test data). Each recording is between 5 and 10 seconds long with a sampling frequency of 500 Hz. - The fifth source is an undisclosed American database that is geographically distinct from the Georgia database. This source contains 10,000 ECGs (all retained as test data). - The sixth source is the Chapman University, Shaoxing People’s Hospital (Chapman-Shaoxing) and Ningbo First Hospital (Ningbo) database. This source contains 45,152 ECGS (all shared as training data). Each recording is 10 seconds long with a sampling frequency of 500 Hz. - The seventh source is UMich Database from the University of Michigan. This source contains 19,642 ECGs (all retained as test data). Each recording is 10 seconds long with a sampling frequency of either 250 Hz or 500 Hz. Like other real-world datasets, different databases may have different proportions of cardiac abnormalities, but all of the labels in the validation or test data are represented in the training data. Moreover, while this is a curated dataset, some of the data and labels are likely to have errors, and an important part of the Challenge is to work out these issues. In particular, some of the databases have human-overread machine labels with single or multiple human readers, so the quality of the labels varies between databases. You can find more information about the label mappings of the Challenge training data in this table. The six-lead, four-lead, three-lead, and two-lead validation data are reduced-lead versions of the twelve-lead validation data: the same recordings with the same header data but only with signal data for the relevant leads. We are not planning to release the test data at any point, including after the end of the Challenge. Requests for the test data will not receive a response. We do not release test data to prevent overfitting on the test data and claims or publications of inflated performances. We will entertain requests to run code on the test data after the Challenge on a limited basis based on publication necessity and capacity. (The Challenge is largely staged by volunteers.) # Data Format All data was formatted in WFDB format. Each ECG recording uses a binary MATLAB v4 file (see page 27) for the ECG signal data and a plain text file in WFDB header format for the recording and patient attributes, including the diagnosis, i.e., the labels for the recording. The binary files can be read using the load function in MATLAB and the scipy.io.loadmat function in Python; see our MATLAB and Python example code for working examples. The first line of the header provides information about the total number of leads and the total number of samples or time points per lead, the following lines describe how each lead was encoded, and the last lines provide information on the demographics and diagnosis of the patient. For example, a header file A0001.hea may have the following contents: A0001 12 500 7500 05-Feb-2020 11:39:16 A0001.mat 16+24 1000/mV 16 0 28 -1716 0 I A0001.mat 16+24 1000/mV 16 0 7 2029 0 II A0001.mat 16+24 1000/mV 16 0 -21 3745 0 III A0001.mat 16+24 1000/mV 16 0 -17 3680 0 aVR A0001.mat 16+24 1000/mV 16 0 24 -2664 0 aVL A0001.mat 16+24 1000/mV 16 0 -7 -1499 0 aVF A0001.mat 16+24 1000/mV 16 0 -290 390 0 V1 A0001.mat 16+24 1000/mV 16 0 -204 157 0 V2 A0001.mat 16+24 1000/mV 16 0 -96 -2555 0 V3 A0001.mat 16+24 1000/mV 16 0 -112 49 0 V4 A0001.mat 16+24 1000/mV 16 0 -596 -321 0 V5 A0001.mat 16+24 1000/mV 16 0 -16 -3112 0 V6 #Age: 74 #Sex: Male #Dx: 426783006 #Rx: Unknown #Hx: Unknown #Sx: Unknown From the first line of the file, we see that the recording number is A0001, and the recording file is A0001.mat. The recording has 12 leads, each recorded at a 500 Hz sampling frequency, and contains 7500 samples. From the next 12 lines of the file (one for each lead), we see that each signal was written at 16 bits with an offset of 24 bits, the floating point number (analog-to-digital converter (ADC) units per physical unit) is 1000/mV, the resolution of the analog-to-digital converter (ADC) used to digitize the signal is 16 bits, and the baseline value corresponding to 0 physical units is 0. The first value of the signal (-1716, etc.), the checksum (0, etc.), and the lead name (I, etc.) are the last three entries of each of these lines. From the final 6 lines, we see that the patient is a 74-year-old male with a diagnosis (Dx) of 426783006, which is the SNOMED-CT code for sinus rhythm. The medical prescription (Rx), history (Hx), and symptom or surgery (Sx) are unknown. Please visit WFDB header format for more information on the header file and variables.

Data ## The data for this Challenge are from multiple sources: CPSC Database and CPSC-Extra Database INCART Database PTB and PTB-XL Database The Georgia 12-lead ECG Challenge (G12EC) Database Undisclosed Database The first source is the public (CPSC Database) and unused data (CPSC-Extra Database) from the China Physiological Signal Challenge in 2018 (CPSC2018), held during the 7th International Conference on Biomedical Engineering and Biotechnology in Nanjing, China. The unused data from the CPSC2018 is NOT the test data from the CPSC2018. The test data of the CPSC2018 is included in the final private database that has been sequestered. This training set consists of two sets of 6,877 (male: 3,699; female: 3,178) and 3,453 (male: 1,843; female: 1,610) of 12-ECG recordings lasting from 6 seconds to 60 seconds. Each recording was sampled at 500 Hz. The second source set is the public dataset from St Petersburg INCART 12-lead Arrhythmia Database. This database consists of 74 annotated recordings extracted from 32 Holter records. Each record is 30 minutes long and contains 12 standard leads, each sampled at 257 Hz. The third source from the Physikalisch Technische Bundesanstalt (PTB) comprises two public databases: the PTB Diagnostic ECG Database and the PTB-XL, a large publicly available electrocardiography dataset. The first PTB database contains 516 records (male: 377, female: 139). Each recording was sampled at 1000 Hz. The PTB-XL contains 21,837 clinical 12-lead ECGs (male: 11,379 and female: 10,458) of 10 second length with a sampling frequency of 500 Hz. The fourth source is a Georgia database which represents a unique demographic of the Southeastern United States. This training set contains 10,344 12-lead ECGs (male: 5,551, female: 4,793) of 10 second length with a sampling frequency of 500 Hz. The fifth source is an undisclosed American database that is geographically distinct from the Georgia database. This source contains 10,000 ECGs (all retained as test data). All data is provided in WFDB format. Each ECG recording has a binary MATLAB v4 file (see page 27) for the ECG signal data and a text file in WFDB header format describing the recording and patient attributes, including the diagnosis (the labels for the recording). The binary files can be read using the load function in MATLAB and the scipy.io.loadmat function in Python; please see our baseline models for examples of loading the data. The first line of the header provides information about the total number of leads and the total number of samples or points per lead. The following lines describe how each lead was saved, and the last lines provide information on demographics and diagnosis. Below is an example header file A0001.hea: A0001 12 500 7500 05-Feb-2020 11:39:16 A0001.mat 16+24 1000/mV 16 0 28 -1716 0 I A0001.mat 16+24 1000/mV 16 0 7 2029 0 II A0001.mat 16+24 1000/mV 16 0 -21 3745 0 III A0001.mat 16+24 1000/mV 16 0 -17 3680 0 aVR A0001.mat 16+24 1000/mV 16 0 24 -2664 0 aVL A0001.mat 16+24 1000/mV 16 0 -7 -1499 0 aVF A0001.mat 16+24 1000/mV 16 0 -290 390 0 V1 A0001.mat 16+24 1000/mV 16 0 -204 157 0 V2 A0001.mat 16+24 1000/mV 16 0 -96 -2555 0 V3 A0001.mat 16+24 1000/mV 16 0 -112 49 0 V4 A0001.mat 16+24 1000/mV 16 0 -596 -321 0 V5 A0001.mat 16+24 1000/mV 16 0 -16 -3112 0 V6 #Age: 74 #Sex: Male #Dx: 426783006 #Rx: Unknown #Hx: Unknown #Sx: Unknown From the first line, we see that the recording number is A0001, and the recording file is A0001.mat. The recording has 12 leads, each recorded at 500 Hz sample frequency, and contains 7500 samples. From the next 12 lines, we see that each signal was written at 16 bits with an offset of 24 bits, the amplitude resolution is 1000 with units in mV, the resolution of the analog-to-digital converter (ADC) used to digitize the signal is 16 bits, and the baseline value corresponding to 0 physical units is 0. The first value of the signal, the checksum, and the lead name are included for each signal. From the final 6 lines, we see that the patient is a 74-year-old male with a diagnosis (Dx) of 426783006. The medical prescription (Rx), history (Hx), and symptom or surgery (Sx) are unknown. Each ECG recording has one or more labels from different type of abnormalities in SNOMED-CT codes. The full list of diagnoses for the challenge has been posted here as a 3 column CSV file: Long-form description, corresponding SNOMED-CT code, abbreviation. Although these descriptions apply to all training data there may be fewer classes in the test data, and in different proportions. However, every class in the test data will be represented in the training data.

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.