# MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

arXiv: https://arxiv.org/abs/1905.11333 · HTML: https://mlsanity.com/paper/1905.11333/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 21 of 21)

- [Voice2Series: Reprogramming Acoustic Models for Time Series Classification](https://mlsanity.com/paper/2106.09296/) (2021)
- [Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model](https://mlsanity.com/paper/2502.10707/) (2025)
- [Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals](https://mlsanity.com/paper/2109.08908/) (2021)
- [SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models](https://mlsanity.com/paper/2103.03945/) (2021)
- [PyHealth: A Python Library for Health Predictive Models](https://mlsanity.com/paper/2101.04209/) (2021)
- [Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks](https://mlsanity.com/paper/2202.07679/) (2022)
- [Physics Inspired Hybrid Attention for SAR Target Recognition](https://mlsanity.com/paper/2309.15697/) (2023)
- [MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring](https://mlsanity.com/paper/2301.12178/) (2023)
- [MambaCapsule: Towards Transparent Cardiac Disease Diagnosis with Electrocardiography Using Mamba Capsule Network](https://mlsanity.com/paper/2407.20893/) (2024)
- [PPG-to-ECG Signal Translation for Continuous Atrial Fibrillation Detection via Attention-based Deep State-Space Modeling](https://mlsanity.com/paper/2309.15375/) (2023)
- [UniECG: Understanding and Generating ECG in One Unified Model](https://mlsanity.com/paper/2509.18588/) (2025)
- [IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification](https://mlsanity.com/paper/2204.05116/) (2022)
- [MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs](https://mlsanity.com/paper/2202.12450/) (2022)
- [Deep Latent Variable Modeling of Physiological Signals](https://mlsanity.com/paper/2405.19277/) (2024)
- [Hierarchical Attention Network for Interpretable ECG-based Heart Disease Classification](https://mlsanity.com/paper/2504.03703/) (2025)
- [Manifold-Aware Diffusion-Augmented Contrastive Learning for Noise-Robust Biosignal Representation](https://mlsanity.com/paper/2509.20048/) (2025)
- [EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification](https://mlsanity.com/paper/2512.03804/) (2025)
- [BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis](https://mlsanity.com/paper/2601.07316/) (2026)
- [MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection](https://mlsanity.com/paper/2606.06718/) (2026)
- [Diagnosing as Cardiologists Do: ECG Agents with Doctor-Grounded Priors for Clinical Reasoning Across Diseases and Populations](https://mlsanity.com/paper/2608.09053/) (2026)
- [Test-Time Adaptation for ECG Classification via SQI-Gated Self-Training and Beat-Rhythm Consistency](https://mlsanity.com/paper/2608.23347/) (2026)

## Abstract (arXiv)

Electrocardiography (ECG) signals are commonly used to diagnose various cardiac abnormalities. Recently, deep learning models showed initial success on modeling ECG data, however they are mostly black-box, thus lack interpretability needed for clinical usage. In this work, we propose MultIlevel kNowledge-guided Attention networks (MINA) that predict heart diseases from ECG signals with intuitive explanation aligned with medical knowledge. By extracting multilevel (beat-, rhythm- and frequency-level) domain knowledge features separately, MINA combines the medical knowledge and ECG data via a multilevel attention model, making the learned models highly interpretable. Our experiments showed MINA achieved PR-AUC 0.9436 (outperforming the best baseline by 5.51%) in real world ECG dataset. Finally, MINA also demonstrated robust performance and strong interpretability against signal distortion and noise contamination.