# Hierarchical Transformer for Electrocardiogram Diagnosis

arXiv: https://arxiv.org/abs/2411.00755 · HTML: https://mlsanity.com/paper/2411.00755/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 1 Nov 2024.

## Builds on (most cited first, 5 of 5)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning](https://mlsanity.com/paper/2206.02647/) (2022)
- [DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention](https://mlsanity.com/paper/2407.13920/) (2024)

## Built on by (most cited first, 3 of 3)

- [ECG-Soup: Harnessing Multi-Layer Synergy for ECG Foundation Models](https://mlsanity.com/paper/2509.00102/) (2025)
- [How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Research](https://mlsanity.com/paper/2601.06443/) (2026)
- [HeartBeatAI: An Interpretable and Robust Deep Learning Framework for Multi-Label ECG Arrhythmia Detection](https://mlsanity.com/paper/2605.24588/) (2026)

## Abstract (arXiv)

We propose a hierarchical Transformer for ECG analysis that combines depth-wise convolutions, multi-scale feature aggregation via a CLS token, and an attention-gated module to learn inter-lead relationships and enhance interpretability. The model is lightweight, flexible, and eliminates the need for complex attention or downsampling strategies.