FARAPULSE™ PFA Platform

BeatLogic™ AI algorithm​

Automates beat and rhythm-level analysis for accurate reports and critical event notifications.

Precision reporting for proactive care​

BeatLogic is the suite of artificial intelligence (AI) algorithms that make up the Boston Scientific Cardiac Diagnostics cloud-based ECG analysis platform. It leverages AI to automate ECG interpretation, enabling technicians to quickly deliver accurate reports and critical notifications. Developed using 125,000+ patient records and 7.5+ million ECG records, BeatLogic applies multiple specialized deep-learning models to detect and classify 34 distinct arrythmias with precision.1

From urgent arrhythmia detection to waveform segmentation, BeatLogic delivers timely, accurate reports and critical notifications to help inform therapy decisions and care pathways.

>96%

Beat detection

>97%

Sinus sensitivity

>99.7%

VT sensitivity

>97%

AFib Sensitivity

Dive deeper with powerful AI capabilities

BeatLogic provides built-in deep learning and advanced algorithms across all BodyGuardian remote cardiac monitors.

alt text

7.5M+ ECG records​

alt text

125k+ patients​

alt text

5 deep learning models with 380+ processing layers

alt text

34 rhythm classifications​

alt text

BodyGuardian MINI and MINI PLUS monitors​

Accurate, high-quality ECG monitors that support every available modality.

Explore the devices

Featured BeatLogic publications

Srivastava et al., Heart Rhythm, 2025​

Artificial intelligence-based ECG rhythm classification of tachyarrhythmias according to duration thresholds​

Applying minimum duration thresholds improves the BeatLogic AIalgorithm’s performance detecting atrial fibrillation (AFib) andventricular tachycardia (VT). Near real time, alert-based monitoring and threshold adjustment may allow for a more tailored approach to alert management while ensuring serious rhythm abnormalities are not missed.​

Teplitzky et al., Heart Rhythm, 2020​

Deep learning for comprehensive ECG annotation​

The BeatLogic algorithm advances state-of-the-art performance for ECG analysis on real-world data. Multiple specialized deep learning models work in concert to accurately identify and classify beats and rhythms from raw ECG data like AFib and VT with near‑perfect precision.

Additional publications​

2025

Andrade et al., Heart Rhythm, 2025​

Artificial intelligence versus electrophysiologist adjudication of atrial arrhythmias: a validation study​

Compare AI and EP adjudication​

2024

Craig et al., Journal of the American College of Cardiology​

Deep learning for automated QTc measurement​

Download the poster​

2023

Verrier et al., Annals of Noninvasive Electrocardiology, 2023​

Continuous multi-day tracking of post-myocardial infarction recovery of cardiac electrical stability and autonomic tone using electrocardiogram patch monitors​

Read: multi-day ECG patch monitoring​

2021

Li et al., Heart Rhythm, 2021​

Predicting atrial fibrillation episodes with rapid ventricular rates associated with low levels of activity

Explore risk identification approach​

2019

Tian et al., Circulation: Cardiovascular Interventions, 2019​

Utility of 30-day continuous ambulatory monitoring to identify patients with delayed occurrence of atrioventricular block after transcatheter aortic valve replacement (TAVR)​

See detection timing & yield​

 

Mehta et al., Heart Rhythm, 2019​​

Impact of study duration on detection of atrial fibrillation (Afib) in patients undergoing ambulatory external ECG monitoring​

See why duration matters​

2018

Teplitzky et al., Heart Rhythm, 2018​

Real-world validation of a deep learning algorithm for fully-automated premature ventricular beat classification during ambulatory external ECG monitoring​

See PVC classification results​

 

Teplitzky et al., IEEE, 2018​

Fully-automated ventricular ectopic beat classification for use with mobile cardiac telemetry​

Explore model architecture​

 

Castelletti et al., International Journal of Cardiology, 2018​​

A wearable remote monitoring system for the identification of subjects with a prolonged QT interval or at risk for drug-induced long QT syndrome​

Read: Wearable QT study​

Want more information?

Connect with us to learn more about the BodyGuardian family of remote cardiac monitors.

Request a Rep

1. Teplitzky BA, McRoberts M, Ghanbari H. Deep learning for comprehensive ECG annotation. Heart Rhythm. 2020 May;17(5 Pt B):881-888. doi: 10.1016/j.hrthm.2020.02.015. PMID: 32354454; PMCID: PMC9247885.