Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Editorial
. 2015 Aug;36(8):1629-44.
doi: 10.1088/0967-3334/36/8/1629. Epub 2015 Jul 28.

Robust detection of heart beats in multimodal data

Ikaro Silva  1 , Benjamin Moody, Joachim Behar, Alistair Johnson, Julien Oster, Gari D Clifford, George B Moody
Affiliations
Editorial

Robust detection of heart beats in multimodal data

Ikaro Silva et al. Physiol Meas. 2015 Aug.

Abstract

This editorial reviews the background issues, the design, the key achievements, and the follow-up research generated as a result of the PhysioNet/Computing in Cardiology (CinC) Challenge 2014, published in the concurrent focus issue of Physiological Measurement. Our major focus was to accelerate the development and facilitate the comparison of robust methods for locating heart beats in long-term multi-channel recordings. A public (training) database consisting of 151 032 annotated beats was compiled from records that contained ECGs as well as pulsatile signals that directly reflect cardiac activity, and other signals that may have few or no observable markers of heart beats. A separate hidden test data set (consisting of 152 478 beats) is permanently stored at PhysioNet, and a public framework has been developed to provide researchers with the ability to continue to automatically score and compare the performance of their algorithms. A scoring criteria based on the averaging of gross sensitivity, gross positive predictivity, average sensitivity, and average positive predictivity is proposed. The top three scores (as of March 2015) on the hidden test data set were 93.64%, 91.50%, and 90.70%.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Example waveforms used in the Challenge. The beat annotations are marked in green. The RR interval time series derived from beat annotations is displayed for comparison with the RESP signal. Note that the EMG signal contains observable cardiac artifact. See Table 1 for definition of signal labels.
Figure 2
Figure 2
Example waveforms used by the Challenge containing abnormal beats. The beat annotations are marked in green. The RR interval time series derived from beat annotations is displayed for comparison with the CVP signal. The abnormal beats are labelled: S (Supraventricular premature or ectopic beat), and V (premature ventricular contraction). In addition, the normal beat also have tracings of pacemaker activity. See Table 1 for definition of signal labels.
Figure 3
Figure 3
Diagram describing the process for automatic evaluation of Challenge entries.
Figure 4
Figure 4
Top scores obtained on the revised data set for the 2014 Challenge. Both the C and M code sample entries are highlighted for comparison. A total of 83 entries from 12 teams were scored through the Sandbox environment on the revised data set as of March 2014 (2).
See this image and copyright information in PMC

References

    1. Antink CH, Bruser C, Leonhardt S. Computing in Cardiology Conference (CinC), 2014. IEEE; 2014. Multimodal sensor fusion of cardiac signals via blind deconvolution: A source-filter approach; pp. 805–808.
    1. Antink CH, Brüser C, Leonhardt S. Detection of heart beats in multimodal data: A robust beat-to-beat interval estimation approach. Physiological Measurement. 2015;x(x):x. - PubMed
    1. Behar J, Johnson AE, Oster J, Clifford G. An echo state neural network for foetal ECG extraction optimised by random search. Machine Learning for Clinical Data Analysis and Healthcare NIPS Workshop; Lake Tahoe, USA. 2013b.
    1. Behar J, Oster J, Clifford GD. Combining and benchmarking methods of foetal ECG extraction without maternal or scalp electrode data. Physiological Measurement. 2014;35(8):1569. - PubMed
    1. Behar J, Oster J, Li Q, Clifford GD. ECG signal quality during arrhythmia and its application to false alarm reduction. Biomedical Engineering, IEEE Transactions on. 2013;60(6):1660–1666. - PubMed

Publication types