Comparative Study of Generative Models for Early Detection of Failures in Medical Devices

TL;DR

This work addresses fault detection in safety-critical medical devices by evaluating three generative-time-series approaches—HMM, VAE, and GAN—on real-world datasets (Airbus helicopter vibrations and a lab-tested surgical stapler). Through systematic preprocessing, model-specific training procedures, and reconstruction-based anomaly signals, the study demonstrates that VAE and GAN outperform the traditional HMM in detecting faults, with window-size and feature choices significantly impacting performance. The findings support a shift toward reconstruction-based anomaly detection for time-series data in medical devices, and point toward practical deployment considerations for edge hardware. Overall, the paper highlights the potential of generative models to enhance device safety and reliability while outlining data requirements and future hardware implementation challenges.

Abstract

The medical device industry has significantly advanced by integrating sophisticated electronics like microchips and field-programmable gate arrays (FPGAs) to enhance the safety and usability of life-saving devices. These complex electro-mechanical systems, however, introduce challenging failure modes that are not easily detectable with conventional methods. Effective fault detection and mitigation become vital as reliance on such electronics grows. This paper explores three generative machine learning-based approaches for fault detection in medical devices, leveraging sensor data from surgical staplers,a class 2 medical device. Historically considered low-risk, these devices have recently been linked to an increasing number of injuries and fatalities. The study evaluates the performance and data requirements of these machine-learning approaches, highlighting their potential to enhance device safety.