---
title: "Learning to Learn Personalized Neural Network for Ventricular Arrhythmias Detection on Intracardiac EGMs"
authors:
  - "Zhenge Jia"
  - "Zhepeng Wang"
  - "Feng Hong"
  - "Lichuan PING"
  - "Yiyu Shi"
  - "Jingtong Hu"
doi: "10.24963/ijcai.2021/359"
url: "https://ijcai.org/proceedings/2021/359"
pdf: "https://ijcai.org/proceedings/2021/0359.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "2606-2613"
track: "Main Track"
keywords:
  - "Machine Learning: Transfer, Adaptation, Multi-task Learning"
  - "Machine Learning Applications: Bio/Medicine"
  - "Multidisciplinary Topics and Applications: Biology and Medicine"
---

# Learning to Learn Personalized Neural Network for Ventricular Arrhythmias Detection on Intracardiac EGMs

Zhenge Jia, Zhepeng Wang, Feng Hong, Lichuan PING, Yiyu Shi, Jingtong Hu

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 2606-2613. DOI: [10.24963/ijcai.2021/359](https://doi.org/10.24963/ijcai.2021/359)

## Abstract

Life-threatening ventricular arrhythmias (VAs) detection on intracardiac electrograms (IEGMs) is essential to Implantable Cardioverter Defibrillators (ICDs). However, current VAs detection methods count on a variety of heuristic detection criteria, and require frequent manual interventions to personalize criteria parameters for each patient to achieve accurate detection. In this work, we propose a one-dimensional convolutional neural network (1D-CNN) based life-threatening VAs detection on IEGMs. The network architecture is elaborately designed to satisfy the extreme resource constraints of the ICD while maintaining high detection accuracy. We further propose a meta-learning algorithm with a novel patient-wise training tasks formatting strategy to personalize the 1D-CNN. The algorithm generates a well-generalized model initialization containing across-patient knowledge, and performs a quick adaptation of the model to the specific patient's IEGMs. In this way, a new patient could be immediately assigned with personalized 1D-CNN model parameters using limited input data. Compared with the conventional VAs detection method, the proposed method achieves 2.2% increased sensitivity for detecting VAs rhythm and 8.6% increased specificity for non-VAs rhythm.