A novel adaptive insertable cardiac monitor algorithm improves the detection of atrial fibrillation and atrial tachycardia in silico

Self-Attention LSTM-FCN model for arrhythmia classification and uncertainty assessment

This paper presents ArrhyMon, a self-attention-based LSTM-FCN model for arrhythmia classification from ECG signal inputs. ArrhyMon targets to detect and classify six different types of arrhythmia apart from normal ECG patterns. To the best of our knowledge, ArrhyMon is the first end-to-end classification model that successfully targets the classification of six detailed arrhythmia types and compared to previous work does not require additional preprocessing and/or feature extraction operations separate from the classification model. ArrhyMon's deep learning model is designed to capture and exploit both global and local features embedded in ECG sequences by integrating fully convolutional network (FCN) layers and a self-attention-based long and short-term memory (LSTM) architecture. Moreover, to enhance its practicality, ArrhyMon incorporates a deep ensemble-based uncertainty model that generates a confidence-level measure for each classification result. We evaluate ArrhyMon's effectiveness using three publicly available arrhythmia datasets (i.e., MIT-BIH, Physionet Cardiology Challenge 2017 and 2020/2021) to show that ArrhyMon achieves state-of-the-art classification performance (average accuracy 99.63%), and that confidence measures show close correlation with subjective diagnosis made from practitioners.

Preliminary results from the LUX-Dx insertable cardiac monitor remote programming and performance (LUX-Dx PERFORM) study

Despite the wide adoption of insertable cardiac monitors (ICMs), high false-positive rates, suboptimal signal quality, limited ability to detect atrial flutter, and lack of remote programming remain challenging. The LUX-Dx PERFORM study was designed to evaluate novel technologies engineered to address these issues. Here, we present preliminary results from the trial focusing on the safety of ICM insertion, remote monitoring rates, and the feasibility of remote programming. LUX-Dx PERFORM is a multicenter, prospective, single-arm, post-market, observational study with planned enrollment of up to 827 patients from 35 sites in North America. A preliminary cohort consisting of the first 369 patients who were enrolled between March and October 2021 was selected for analysis. Three hundred sixty-three (363) patients had ICM insertions across inpatient and outpatient settings. The mean time followed was 103.4 ± 61.8 days per patient. The total infection rate was 0.8% (3/363). Interim results show high levels of remote monitoring with a median 94% of days with data transmission (interquartile range: 82-99). Thirteen (13) in-clinic and 24 remote programming sessions were reported in 34 subjects. Reprogramming examples are presented to highlight signal quality, the ability to detect atrial flutter, and the positive impact of remote programming on patient management. Interim results from LUX-Dx PERFORM study demonstrate the safety of insertion, high data transmission rates, the ability to detect atrial flutter, and the feasibility of remote programming to optimize arrhythmia detection and improve clinical workflow. Future results from LUX-Dx PERFORM will further characterize improvements in signal quality and arrhythmia detection.