DEEP LEARNING FOR ECG ANNOTATION

Outpatient ambulatory electrocardiographic (ECG) monitoring has grown in popularity due to technological advancements, which have decreased monitor size, increased battery life, and enabled mobile telemetry. Modern ambulatory ECG monitors allow for up to 30 days of continuous monitoring, producing far too much data for physicians to comprehensively analyze. For this reason, service providers are commonly used to annotate ECG recordings and create reports that summarize and highlight ectopic activity. These reports provide clinical decision support for prescribing physicians. Service providers rely on certified technicians and supporting algorithms to process and annotate the data from ECG monitoring studies. Historically, supporting algorithms have achieved levels of performance well below that of humans 1 but high enough to be used for prioritization and conservative filtering of ECG as it is queued for human interpretation 2 . Better supporting algorithms have the potential to improve this process by more accurately detecting the presence and absence of cardiac arrhythmias.

This work details and validates the Preventice BeatLogic® platform, a comprehensive ECG annotation platform that leverages DL for beat and rhythm detection/classification. Performance was measured using the EC57 standard and compared to a commercial state-of-the-art ECG interpretation algorithm using realworld gold standard data and also compared to previously published work using publicly available validation datasets.

ecg-1

VALIDATION DATA

Methods and Training Data: Training data were captured as 20,932 individual records with duration between 15 seconds and 4 minutes. Annotations were made in accordance with standard practice by a dedicated team of (CCT)-certified ECG technicians.

Annotations were individually adjudicated by 3 board-certified electrophysiologists. The gold validation dataset included 515, 1- to 4-minute records from 505 patients (Table 1). No patient overlap was allowed between the training and gold standard validation datasets.

ecg-2

BEATLOGIC® PLATFORM

The BeatLogic® platform consists of 2 DL models—BeatNet and RhythmNet—the results of which are consolidated using rules-based logic to produce a single contiguous annotation file (Figure 1).

BeatNet performs artifact detection, beat detection, and beat classification. RhythmNet performs detection and classification of Sinus rhythm (Sinus), Atrial fibrillation/flutter (AFib), Supraventricular tachycardia (SVT), Junctional rhythm (Junc), Second-degree heart block type 1 (BII1), Second-degree heart block type 2 (BII2), Third-degree heart block (BIII), and Other. The consolidation algorithm generates Ventricular tachycardia (VT), Idioventricular rhythm (IVR), Intraventricular conduction delay (IVCD), Ventricular bigeminy (VBigem), Ventricular trigeminy (VTrigem), and Pause annotations using the BeatNet output and then splices together RhythmNet rhythms, ventricular rhythms, and artifact to create contiguous annotation files.

ecg-3

DL ARCHITECTURE

Both DL models rely on a similar architecture, which produces a sequence of classification results from a time series of single-channel ECG voltage values (Figure 2). The architecture is derived from preactivation ResNet,13,14 a popular image classification architecture. The highest probability was selected as the label for each sequential output.

ECG SIGNAL PROCESSING AND VALIDATION PROCEDURE

ECG recordings were preprocessed using a wavelet highpass (fc 5 0.5 Hz) filter15 to remove baseline wander and 2 second-order Butterworth band-stop (fc 5 50 and 60 Hz) filters to remove powerline interference. After filtering, MITBIH and AFDB data were resampled to 256 Hz using linear interpolation.

Algorithm validation was performed in accordance with the EC57 guidelines.10 EC57 is the FDA-recognized consensus standard and provides detailed instructions for measuring beat and rhythm detection/classification sensitivity (Se), and positive predictive value (PPV). Additionally, F1 scores (0–100) were calculated for each validation metric per Equation 1.

ecg-4

RESULTS - BEAT DETECTION

  • On the MIT-BIH dataset, the BeatLogic® platform performed equal to or better than 5 of the 8 previously published algorithms, whereas the state-of-the art algorithm out-performed only 1 published algorithm (Table 2).
  • On the gold validation dataset, BeatLogic® sensitivity was 99.84%, which exceeded the state-of-the-art algorithm by >4 percentage points.
  • BeatLogic® PPV was 99.78%, which exceeded the state-of-the-art algorithm by >3 percentage points (Table 2).
ecg-5

VEB CLASSIFICATION PERFORMANCE

  • On the 11- record MIT-BIH data subset for measuring VEB performance, BeatLogic® outperformed all other algorithms, achieving an F1 score of 98.4, which is 0.
  • On the gold validation dataset, BeatLogic® outperformed the state-of-the-art algorithm, achieving sensitivity of 89.4% and PPV of 97.8% (Table 3).
ecg-6

ecg-7

RHYTHM DETECTION AND CLASSIFICATION

  • On the AFDB dataset, BeatLogic® outperformed the previously published algorithms. The BeatLogic® platform achieved episode Se/PPV of 97.7%/99.3% and duration sensitivity/PPV of 97.7%/99.7% (Table 4).
  • On the gold validation dataset, BeatLogic® outperformed the state-of-the-art algorithm for all 14 rhythms in measures of episode and duration sensitivity and PPV (Table 4). Three rhythm classes (junctional rhythm, second-degree heart block type 1, third-degree heart block) were not called at all by the state-of-the-art algorithm.
  • State-of-the-art episode and duration F1 scores exceeded 70 for 7 rhythms and exceeded 80 for episode detection of 3 rhythms.
  • BeatLogic® episode and duration F1 scores exceeded 70 for all 14 rhythms, exceeded 80 for 11 rhythms, exceeded 90 for 7 rhythms, and exceeded 95 for the following 5 rhythms: atrial fibrillation/flutter, ventricular tachycardia, ventricular bigeminy, ventricular trigeminy, and third-degree heart block.

CONCLUSION

As the popularity of long-term ambulatory ECG monitoring continues to grow, reliance on ECG interpretation algorithms will increase. Initial applications of DL to ECG interpretation focused on only beat detection, beat classification, or rhythm classification have shown promising results. By leveraging high-quality comprehensive training data and multiple DL models to create a system that can perform all 3 tasks, Beat-Logic® represents the next stage of advancement for algorithmic ECG interpretation. Real-world gold standard validation demonstrates the superiority of this approach over the current state of the art.

1. Teplitzky, B., McRoberts, M., Ghanbari, H. Deep learning for comprehensive ECG annotation. Heart Rhythm 2020, Vol 17, No 5PB, pp:881–888.