arXiv subjects

Maedeh H. Toosi

Publications and source records attributed to Maedeh H. Toosi.

3 recordsLinked to original sources

arXiv2026

Domain-Adaptive Arrhythmia Classification Using a Hybrid Transformer on Wearable Heart Signals

Cardiovascular disease remains the leading cause of death globally, underscoring the need for effective, accessible monitoring solutions, particularly through wearable devices that enable continuous, real-time tracking of heart rhythms in home settings. However, deploying deep learning models trained on clinical electrocardiogram (ECG) datasets to wearable devices remains challenging, as differences in recording equipment, signal quality, and patient populations introduce domain shifts that degrade model performance. We propose a hybrid transformer model that processes continuous ECG signals alongside seven heart rate variability (HRV) features, where the raw signal path captures beat-level morphological patterns and the HRV path encodes rhythm regularity statistics, allowing the model to jointly leverage complementary information from both representations. To enhance the model's ability to generalize across domains, we employ representation learning techniques, including Maximum Mean Discrepancy (MMD), a non-parametric kernel-based metric that quantifies the distance between feature distributions of different domains, to align feature distributions between source and target domains, addressing the challenge of domain shifts between public datasets and wearable device data. By leveraging five public ECG datasets for training, the model learns robust, generalized representations that mitigate domain-specific biases. When tested on wearable device data with an unseen domain, the model achieved an F1-macro 95% and balanced accuracy of 96.15%. These results demonstrate minimal performance degradation, with only a 2% drop in F1-macro compared to seen-domain evaluation, highlighting the model's generalization capabilities and its potential for reliable, real-time heart monitoring applications in home and ambulatory settings.

eess.SP↗

arXiv2025

Using Test-Time Data Augmentation for Cross-Domain Atrial Fibrillation Detection from ECG Signals

Atrial fibrillation (AF) detection from electrocardiogram (ECG) signals is crucial for early diagnosis and management of cardiovascular diseases. However, deploying robust AF detection models across different datasets with significant domain variations remains a challenge. In this paper, we use test-time data augmentation (TTA) to address the cross-domain problem and enhance AF detection performance. We use a publicly available dataset for training - Physionet Computing in Cardiology Challenge 2017 -, while collecting a distinct test set, creating a cross-domain scenario. We employ a neural network architecture that integrates transformer-based encoding of ECG signals and convolutional layers for spectrogram feature extraction. The model combines the latent representations obtained from both encoders to classify the input signals. By incorporating TTA during inference, we enhance the model's performance, achieving an F1 score of 76.6\% on our test set. Furthermore, our experiments demonstrate that the model becomes more resilient to perturbations in the input signal, enhancing its robustness. We show that TTA can be effective in addressing the cross-domain problem, where training and test data originate from disparate sources. This work contributes to advancing the field of AF detection in real-world scenarios.

eess.SP↗

arXiv2024

MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots

Wearable systems provide continuous health monitoring and can lead to early detection of potential health issues. However, the lifecycle of wearable systems faces several challenges. First, effective model training for new wearable devices requires substantial labeled data from various subjects collected directly by the wearable. Second, subsequent model updates require further extensive labeled data for retraining. Finally, frequent model updating on the wearable device can decrease the battery life in long-term data monitoring. Addressing these challenges, in this paper, we propose MetaWearS, a meta-learning method to reduce the amount of initial data collection required. Moreover, our approach incorporates a prototypical updating mechanism, simplifying the update process by modifying the class prototype rather than retraining the entire model. We explore the performance of MetaWearS in two case studies, namely, the detection of epileptic seizures and the detection of atrial fibrillation. We show that by fine-tuning with just a few samples, we achieve 70% and 82% AUC for the detection of epileptic seizures and the detection of atrial fibrillation, respectively. Compared to a conventional approach, our proposed method performs better with up to 45% AUC. Furthermore, updating the model with only 16 minutes of additional labeled data increases the AUC by up to 5.3%. Finally, MetaWearS reduces the energy consumption for model updates by 456x and 418x for epileptic seizure and AF detection, respectively.

cs.LG↗