Key result
Personalized knowledge-incorporated learning detects AF with ~95% accuracy, surpassing standard pre-trained models.
Why the study?
Pre-trained deep learning models cannot adapt to individual patient rhythm variability, and fine-tuning on limited patient ECG data is prone to overfitting.
Incorporating prior cardiological knowledge into deep learning models for personalized AF detection on edge devices significantly improves detection accuracy compared to standard pre-trained or fine-tuned models.
Answers are grounded in this paper and cite their sources.
May improve edge-based personalized AF detection; leaves open prospective clinical validation before practice adoption.
Atrial Fibrillation (AF), one of the most prevalent arrhythmias, is an irregular heart-rate rhythm causing serious health problems such as stroke and heart failure. Deep learning based methods have been exploited to provide an end-to-end AF detection by automatically extracting features from Electrocardiogram (ECG) signal and achieve state-of-the-art results. However, the pre-trained models cannot adapt to each patient’s rhythm due to the high variability of rhythm characteristics among different patients. Furthermore, the deep models are prone to overfitting when fine-tuned on the limited ECG of the specific patient for personalization. In this work, we propose a prior knowledge incorporated learning method to effectively personalize the model for patient-specific AF detection and alleviate the overfitting problems. To be more specific, a prior-incorporated portion importance mechanism is proposed to enforce the network to learn to focus on the targeted portion of the ECG, following the cardiologists’ domain knowledge in recognizing AF. A prior-incorporated regularization mechanism is further devised to alleviate model overfitting during personalization by regularizing the fine-tuning process with feature priors on typical AF rhythms of the general population. The proposed personalization method embeds the well-defined prior knowledge in diagnosing AF rhythm into the personalization procedure, which improves the personalized deep model and eliminates the workload of manually adjusting parameters in conventional AF detection method. The prior knowledge incorporated personalization is feasibly and semi-automatically conducted on the edge, device of the cardiac monitoring system. We report an average AF detection accuracy of 95.3% of three deep models over patients, surpassing the pre-trained model by a large margin of 11.5% and the fine-tuning strategy by 8.6%.
No takes yet. Share an insight, caveat, or question.
Jia et al. (2021) studied Atrial Fibrillation. Prior knowledge incorporated learning method vs. Pre-trained model and fine-tuning strategy was evaluated on Average AF detection accuracy. A prior knowledge incorporated learning method for personalized atrial fibrillation detection achieved 95.3% accuracy, surpassing pre-trained models by 11.5% and fine-tuning by 8.6%.
Synapse has enriched 10 related papers. Consider them for comparative context: