# An Artificial Intelligence QRS Detection Algorithm for Wearable Electrocardiogram Devices

## TL;DR

This paper introduces an AI-based QRS detection algorithm for wearable ECG devices that automatically processes multiple leads with high accuracy and low computational cost.

## Contribution

A novel QRS detection method that automatically fuses multi-lead signals using a leads-distillation module and U-Net architecture.

## Key findings

- The method achieves an F1 score of 99.83 on the MITBIHA database and 99.77 on the INCART database in the inter-patient pattern.
- It maintains strong performance with an F1 score of 99.22 on INCART and 99.09 on MITBIHA in the cross-database pattern.
- The algorithm uses only 5216 parameters, offering reduced computational load and enhanced precision.

## Abstract

At the core of AI-driven electrocardiogram diagnosis lies the precise localization of the QRS complex. While QRS detection methods for multiple leads have been researched adequately in the last few decades, their multi-lead strategies still need to be designed manually. Therefore, a QRS detector that can fuse multiple leads automatically is still worth investigating. Methods: The proposed QRS detector comprises a leads-distillation module (LDM) and a QRS detection module. The LDM can distill multi-lead signals into single-lead ones. This procedure minimizes the weight proportions assigned to noisy leads, enabling the network to generate a novel signal that facilitates the recognition of QRS waves. The QRS detection module, utilizing U-Net, is capable of discerning QRS complexes from the novel signal. Results: Our method demonstrates outstanding performance with a parameter count of only 5216. It achieves an excellent F1 score of 99.83 on the MITBIHA database and 99.77 on the INCART database, specifically in the inter-patient pattern. In the cross-database pattern, our approach maintains a strong performance with an F1 score of 99.22 on the INCART database and an F1 score of 99.09 on the MITBIHA database. Conclusion: Our method provides a novel idea for universal multi-lead QRS detection. It possesses advantages, such as reduced computational parameters, enhanced precision, and heightened compatibility. Significance: Our method canceled the repeated deployment of the QRS detection function to different lead configurations in the electrocardiogram (ECG) diagnostic system. Moreover, the scaling operation may become a simple tool to decrease the computational load of the network.