DeepBoost-AF: A Novel Unsupervised Feature Learning and Gradient Boosting Fusion for Robust Atrial Fibrillation Detection in Raw ECG Signals

2025-05-30

AI Summary

To address the limitations of manual feature engineering and poor generalizability in automated atrial fibrillation (AF) detection, this paper proposes an end-to-end unsupervised deep feature learning framework integrated with a gradient-boosting model. Specifically, we design a 19-layer deep convolutional autoencoder (DCAE) for unsupervised representation learning directly from raw electrocardiogram (ECG) signals. A novel feature distillation mechanism enables joint optimization between the DCAE and LightGBM, facilitating end-to-end collaborative training. The resulting DCAE-LightGBM model achieves state-of-the-art performance on standard benchmarks: an F1-score of 95.20% and sensitivity of 99.99%, with only 4 seconds of inference latency per sample. These results demonstrate substantial improvements over existing methods, balancing high diagnostic accuracy with clinical feasibility for real-time deployment.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with elevated health risks, where timely detection is pivotal for mitigating stroke-related morbidity. This study introduces an innovative hybrid methodology integrating unsupervised deep learning and gradient boosting models to improve AF detection. A 19-layer deep convolutional autoencoder (DCAE) is coupled with three boosting classifiers-AdaBoost, XGBoost, and LightGBM (LGBM)-to harness their complementary advantages while addressing individual limitations. The proposed framework uniquely combines DCAE with gradient boosting, enabling end-to-end AF identification devoid of manual feature extraction. The DCAE-LGBM model attains an F1-score of 95.20%, sensitivity of 99.99%, and inference latency of four seconds, outperforming existing methods and aligning with clinical deployment requirements. The DCAE integration significantly enhances boosting models, positioning this hybrid system as a reliable tool for automated AF detection in clinical settings.

Problem

• Detecting atrial fibrillation in raw ECG signals accurately
• Combining unsupervised deep learning with gradient boosting models
• Eliminating manual feature extraction for end-to-end AF identification

Innovation

• Unsupervised deep learning with 19-layer DCAE
• Combines DCAE with gradient boosting classifiers
• End-to-end AF detection without manual features