Dataset of manually measured QT intervals in the electrocardiogram

Christov, Ivaylo; Dotsinsky, Ivan; Симова, Яна; Prokopova, Rada; Trendafilova, Elina; Naydenov, Stefan

doi:10.1186/1475-925x-5-31

Cited by 22 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TEMEO electronic center consists of a server with developed software for automatic R-R interval analysis [ 17 , 18 ]—for rhythm detection (including atrial fibrillation), heart rate, and premature beats.…”

Section: Methodsmentioning

confidence: 99%

Clinical Evaluation of a Mobile Heart Rhythm Telemonitoring System

et al. 2012

Self Cite

View full text Add to dashboard Cite

Purpose. To evaluate the clinical applicability of a telemonitoring system: telemetric system for collection and distant surveillance of medical information (TEMEO). Methods. We evaluated 60 patients, applying simultaneously standard Holter ECG and telemonitoring. Two different comparisons were performed: (1) TEMEO ECG with standard 12-lead ECG; (2) TEMEO Holter with standard ECG Holter. Results. We found a very high coincidence rate (99.3%) between TEMEO derived ECGs and standard ECGs. Intraclass correlation coefficient analysis revealed high and significant correlation coefficients regarding average, maximal, and minimal heart rate, % of time in tachycardia, single supraventricular ectopic beats (SVEB), and single and couplets of ventricular ectopic beats (VEB) between Holter ECG and TEMEO derived parameters. Couplets of SVEB were recorded as different by the two monitoring systems, however, with a borderline statistical significance. Conclusions. TEMEO derived ECGs have a very high coincidence rate with standard ECGs. TEMEO patient monitoring provides results that are similar to those derived from a standard Holter ECG.

show abstract

Section: Methodsmentioning

confidence: 99%

Clinical Evaluation of a Mobile Heart Rhythm Telemonitoring System

et al. 2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…Exceptionally, there is also a small number of shorter recordings, however, none of the records last less than 30 seconds. Diagnostic classification of recordings includes healthy and various disease categories such as MI, cardiomyopathy/heart failure, branch block, rhythm disturbance, myocardial and hypertrophy (Chen et al 2013;Christov et al 2006;M. Vozda, T. Peterek 2014).…”

Section: Data Collectionmentioning

confidence: 99%

A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals

Di̇ker

Cömert

Avcı³

2017

Bitlis Eren University Journal of Science and Technology

View full text Add to dashboard Cite

show abstract

“…In the context of QT annotation where baseline wander is frequent, it was observed that a few annotators consistently over-or under-estimated the QT interval [25]. Other studies have reported significant intra-and inter-observer variability in QT annotations, ranging from 10 to 30ms [3,8].…”

Section: Data Descriptionmentioning

confidence: 99%

Fusing Continuous-Valued Medical Labels Using a Bayesian Model

et al. 2015

View full text Add to dashboard Cite

With the rapid increase in volume of time series medical data available through wearable devices, there is a need to employ automated algorithms to label data. Examples of labels include interventions, changes in activity (e.g. sleep) and changes in physiology (e.g. arrhythmias). However, automated algorithms tend to be unreliable resulting in lower quality care. Expert annotations are scarce, expensive, and prone to significant interand intra-observer variance. To address these problems, a Bayesian Continuous-valued Label Aggregator(BCLA) is proposed to provide a reliable estimation of label aggregation while accurately infer the precision and bias of each algorithm.The BCLA was applied to QT interval (pro-arrhythmic indicator) estimation from the electrocardiogram using labels from the 2006 PhysioNet/Computing in Cardiology Challenge database. It was compared to the mean, median, and a previously proposed Expectation Maximization (EM) label aggregation approaches. While accurately predicting each labelling algorithm's bias and precision, the root-mean-square error of the BCLA was 11.78±0.63ms, significantly outperforming the best Challenge entry (15.37±2.13ms) as well as the EM, mean, and median voting strategies (14.76±0.52ms, 17.61±0.55ms, and 14.43±0.57ms respectively with p < 0.0001).The BCLA could therefore provide accurate estimation for medical continuous-valued label tasks in an unsupervised manner even when the ground truth is not available.

show abstract

Dataset of manually measured QT intervals in the electrocardiogram

Cited by 22 publications

References 19 publications

Clinical Evaluation of a Mobile Heart Rhythm Telemonitoring System

Clinical Evaluation of a Mobile Heart Rhythm Telemonitoring System

A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals

Fusing Continuous-Valued Medical Labels Using a Bayesian Model

Contact Info

Product

Resources

About