Survey of Machine Learning Techniques To Predict Heartbeat Arrhythmias

TL;DR

This survey reviews various machine learning methods for heartbeat arrhythmia prediction, emphasizing the importance of balancing accuracy with real-time processing constraints in healthcare applications.

Contribution

It compares multiple machine learning techniques to identify those suitable for real-time arrhythmia detection considering accuracy, latency, and memory use.

Findings

Certain algorithms achieve high accuracy with low latency.

Trade-offs between model complexity and real-time feasibility are highlighted.

Recommendations for deploying ML in healthcare systems are provided.

Abstract

Many works in biomedical computer science research use machine learning techniques to give accurate results. However, these techniques may not be feasible for real-time analysis of data pulled from live hospital feeds. In this project, different machine learning techniques are compared from various sources to find one that provides not only high accuracy but also low latency and memory overhead to be used in real-world health care systems.