July 17, 2019Open Access

PGANs: Personalized Generative Adversarial Networks for ECG Synthesis to Improve Patient-Specific Deep ECG Classification

TGTomer GolanyErnst & Young (Israel)KRKira RadinskyTechnion – Israel Institute of Technology

Structured PICO

Does synthesizing patient-specific ECG signals using PGANs improve patient-specific deep ECG classification?

Population

Patient-specific ECG signals

Intervention

Personalized Generative Adversarial Networks (PGANs) for ECG synthesis as additional training data

Comparator

Standard patient-specific classifier without synthesized training data

Outcome

ECG classification performance

Using Personalized Generative Adversarial Networks to synthesize patient-specific ECG signals improves the performance of deep learning ECG classification models.

Abstract

The Electrocardiogram (ECG) is performed routinely by medical personnel to identify structural, functional and electrical cardiac events. Many attempts were made to automate this task using machine learning algorithms including classic supervised learning algorithms and deep neural networks, reaching state-of-the-art performance. The ECG signal conveys the specific electrical cardiac activity of each subject thus extreme variations are observed between patients. These variations are challenging for deep learning algorithms, and impede generalization. In this work, we propose a semisupervised approach for patient-specific ECG classification. We propose a generative model that learns to synthesize patient-specific ECG signals, which can then be used as additional training data to improve a patient-specific classifier performance. Empirical results prove that the generated signals significantly improve ECG classification in a patient-specific setting.

KI fragen

Bookmark

View Full Paper