The Lock Generative Adversarial Network for Medical Waveform Anomaly Detection

2025-01-23

AI Summary

This work addresses unsupervised detection of ventilator asynchronies and ECG abnormalities. We propose Lock GAN, a generative adversarial framework featuring alternating optimization between generator and discriminator to mitigate training instability inherent in standard GANs. To enhance fidelity in synthesizing sparse anomalous waveforms, we introduce a time-series SMOTE strategy tailored to waveform characteristics. Lock GAN learns normal physiological patterns directly from raw or aggregated waveforms without labels and localizes anomalies via reconstruction error. Evaluated on ventilator asynchrony data and two public ECG benchmarks—MIT-BIH Arrhythmia and PTBDB—the method achieves state-of-the-art performance in F1-score and other key metrics. Results demonstrate both clinical efficacy and strong generalizability across diverse physiological waveform modalities.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Security and Privacy: Large-scale security measurements

Abstract

Waveform signal analysis is a complex and important task in medical care. For example, mechanical ventilators are critical life-support machines, but they can cause serious injury to patients if they are out of synchronization with the patients' own breathing reflex. This asynchrony is revealed by the waveforms showing flow and pressure histories. Likewise, electrocardiograms record the electrical activity of a patients' heart as a set of waveforms, and anomalous waveforms can reveal important disease states. In both cases, subtle variations in a complex waveform are important information for patient care; signals which may be missed or mis-interpreted by human caregivers. We report on the design of a novel Lock Generative Adversarial Network architecture for anomaly detection in raw or summarized medical waveform data. The proposed architecture uses alternating optimization of the generator and discriminator networks to solve the convergence dilemma. Furthermore, the fidelity of the generator networks' outputs to the actual distribution of anomalous data is improved via synthetic minority oversampling. We evaluate this new architecture on one ventilator asynchrony dataset, and two electrocardiogram datasets, finding that the performance was either equal or superior to the state-of-the art on all three.

Problem

• Abnormality Detection
• Medical Waveform Signals
• Assisted Diagnostics

Innovation

• Locked Generative Adversarial Network
• Anomaly Detection
• Medical Waveforms