Authors: Guang Jun Nicholas Ang, Aritejh Kr Goil, Henryk Chan, Jieyi Jeric Lew, Xin Chun Lee, Raihan Bin Ahmad Mustaffa, Timotius Jason, Ze Ting Woon, Bingquan Shen

Published on: May 26, 2023

Impact Score: 8.22

Arxiv code: Arxiv:2305.16727

Summary

• What is new: Introduction of a loss-modified YOLOv8 model for real-time arrhythmia detection from ECGs.
• Why this is important: The need for affordable, accurate, real-time remote monitoring of cardiovascular health.
• What the research proposes: A novel YOLOv8-based algorithm fine-tuned for single-lead ECG signals for arrhythmia detection.
• Results: Achieved an average accuracy of 99.5% and 0.992 mAP@50 with a detection time of 0.002 seconds.

Technical Details

Technological frameworks used: YOLOv8

Models used: Loss-modified YOLOv8

Data used: MIT-BIH arrhythmia dataset

Potential Impact

Healthcare sector, remote cardiovascular monitoring companies, ECG technology developers, AI in healthcare solutions.

Want to implement this idea in a business?

We have generated a startup concept here: HeartSecure.