Detail publikace

Fully automatic detection of strict left bundle branch block

Originální název

Fully automatic detection of strict left bundle branch block

Anglický název

Fully automatic detection of strict left bundle branch block

Jazyk

en

Originální abstrakt

Background Strict left bundle branch block (tLBBB) is a diagnostic marker that was proposed for the detection of complete LBBB from ECG. The criteria for tLBBB include the presence of QS- or rS-configurations of QRS in V1 and V2, the presence of mid-QRS notching or slurring in at least two of leads V1, V2, V5, V6, I and avL, and finally a QRS duration (QRSd) of >130 ms (women) or 140 ms (men). Purpose The main objective was to develop an automatic detector of tLBBB. This work was involved in the competition LBBB Initiative of the ICSE 2018. Methods A total of 300 ECG recordings (10 s, 1000 Hz, 12 leads) from the MADIT-CRT database were used to develop the detector. QRS notching and slurring were detected by thresholding several features, e.g. width and prominence of local extremes in QRS (for QRS notching detection) and the width and prominence of the local extremes in the first derivative of QRS (for QRS slurring detection). The QRS configuration was evaluated according to the dominant deflection of the QRS. A publicly available algorithm (ECG SEEKER, Brno University of Technology) was used for measurement of QRS duration. Tests were performed using a hidden dataset (302 recordings). Results The accuracy, sensitivity and specificity of tLBBB were 0.88, 0.86 and 0.90, respectively for the training dataset and 0.81, 0.69 and 0.87, respectively for the hidden testing dataset. The sensitivity and specificity of QRS configuration detection were 1.00 and 0.99, respectively for the training dataset. The average deviation of the reference values and measured QRSd is 9.8 ms. The positive predictive value (PPV) of QRS notching and slurring detection is 0.92 and 0.60, respectively for the training dataset. Conclusion Although the created detector was the best in the competition LBBB Initiative of the ICSE 2018, the description of individual markers requires improvements prior to use in practice. More specifically, neither QRS notching and slurring nor the determination of the beginning and end of QRS notching/slurring are exactly defined. Our results also showed that the accuracy of tLBBB detection is also highly dependent on QRS onset and offset measurement which is generally problematic.

Anglický abstrakt

Background Strict left bundle branch block (tLBBB) is a diagnostic marker that was proposed for the detection of complete LBBB from ECG. The criteria for tLBBB include the presence of QS- or rS-configurations of QRS in V1 and V2, the presence of mid-QRS notching or slurring in at least two of leads V1, V2, V5, V6, I and avL, and finally a QRS duration (QRSd) of >130 ms (women) or 140 ms (men). Purpose The main objective was to develop an automatic detector of tLBBB. This work was involved in the competition LBBB Initiative of the ICSE 2018. Methods A total of 300 ECG recordings (10 s, 1000 Hz, 12 leads) from the MADIT-CRT database were used to develop the detector. QRS notching and slurring were detected by thresholding several features, e.g. width and prominence of local extremes in QRS (for QRS notching detection) and the width and prominence of the local extremes in the first derivative of QRS (for QRS slurring detection). The QRS configuration was evaluated according to the dominant deflection of the QRS. A publicly available algorithm (ECG SEEKER, Brno University of Technology) was used for measurement of QRS duration. Tests were performed using a hidden dataset (302 recordings). Results The accuracy, sensitivity and specificity of tLBBB were 0.88, 0.86 and 0.90, respectively for the training dataset and 0.81, 0.69 and 0.87, respectively for the hidden testing dataset. The sensitivity and specificity of QRS configuration detection were 1.00 and 0.99, respectively for the training dataset. The average deviation of the reference values and measured QRSd is 9.8 ms. The positive predictive value (PPV) of QRS notching and slurring detection is 0.92 and 0.60, respectively for the training dataset. Conclusion Although the created detector was the best in the competition LBBB Initiative of the ICSE 2018, the description of individual markers requires improvements prior to use in practice. More specifically, neither QRS notching and slurring nor the determination of the beginning and end of QRS notching/slurring are exactly defined. Our results also showed that the accuracy of tLBBB detection is also highly dependent on QRS onset and offset measurement which is generally problematic.

BibTex


@article{BUT148811,
  author="Radovan {Smíšek} and Ivo {Viščor} and Pavel {Jurák} and Josef {Halámek} and Filip {Plešinger}",
  title="Fully automatic detection of strict left bundle branch block",
  annote="Background
Strict left bundle branch block (tLBBB) is a diagnostic marker that was proposed for the detection of complete LBBB from ECG. The criteria for tLBBB include the presence of QS- or rS-configurations of QRS in V1 and V2, the presence of mid-QRS notching or slurring in at least two of leads V1, V2, V5, V6, I and avL, and finally a QRS duration (QRSd) of >130 ms (women) or 140 ms (men).

Purpose
The main objective was to develop an automatic detector of tLBBB. This work was involved in the competition LBBB Initiative of the ICSE 2018.

Methods
A total of 300 ECG recordings (10 s, 1000 Hz, 12 leads) from the MADIT-CRT database were used to develop the detector. QRS notching and slurring were detected by thresholding several features, e.g. width and prominence of local extremes in QRS (for QRS notching detection) and the width and prominence of the local extremes in the first derivative of QRS (for QRS slurring detection). The QRS configuration was evaluated according to the dominant deflection of the QRS. A publicly available algorithm (ECG SEEKER, Brno University of Technology) was used for measurement of QRS duration. Tests were performed using a hidden dataset (302 recordings).

Results
The accuracy, sensitivity and specificity of tLBBB were 0.88, 0.86 and 0.90, respectively for the training dataset and 0.81, 0.69 and 0.87, respectively for the hidden testing dataset. The sensitivity and specificity of QRS configuration detection were 1.00 and 0.99, respectively for the training dataset. The average deviation of the reference values and measured QRSd is 9.8 ms. The positive predictive value (PPV) of QRS notching and slurring detection is 0.92 and 0.60, respectively for the training dataset.

Conclusion
Although the created detector was the best in the competition LBBB Initiative of the ICSE 2018, the description of individual markers requires improvements prior to use in practice. More specifically, neither QRS notching and slurring nor the determination of the beginning and end of QRS notching/slurring are exactly defined. Our results also showed that the accuracy of tLBBB detection is also highly dependent on QRS onset and offset measurement which is generally problematic.",
  chapter="148811",
  doi="10.1016/j.jelectrocard.2018.06.013",
  howpublished="online",
  number="5",
  volume="51",
  year="2018",
  month="december",
  pages="1--17",
  type="journal article"
}