A novel semi-supervised learning method for automatic AF detection achieved 97.9% accuracy, which was only 0.5% lower than fully supervised learning while reducing annotation workload by over 98%.
Does a semi-supervised learning method using a 1D CNN-LSTM neural network accurately detect paroxysmal atrial fibrillation in 24-hour Holter monitoring data compared to fully supervised learning?
A novel semi-supervised deep learning method can accurately detect paroxysmal AF from Holter monitor data while drastically reducing the need for manual data annotation.
Absolute Event Rate: 97.9% vs 98.4%
Paroxysmal atrial fibrillation (AF) is generally diagnosed by long-term dynamic electrocardiogram (ECG) monitoring. Identifying AF episodes from long-term ECG data can place a heavy burden on clinicians. Many machine-learning-based automatic AF detection methods have been proposed to solve this issue. However, these methods require numerous annotated data to train the model, and the annotation of AF in long-term ECG is extremely time-consuming. Reducing the demand for labeled data can effectively improve the clinical practicability of automatic AF detection methods. In this study, we developed a novel semi-supervised learning method that generated modified low-entropy labels of unlabeled samples for training a deep learning model to automatically detect paroxysmal AF in 24 h Holter monitoring data. Our method employed a 1D CNN-LSTM neural network with RR intervals as input and used few labeled training data with numerous unlabeled data for training the neural network. This method was evaluated using a 24 h Holter monitoring dataset collected from 1000 paroxysmal AF patients. Using labeled samples from only 10 patients for model training, our method achieved a sensitivity of 97.8%, specificity of 97.9%, and accuracy of 97.9% in five-fold cross-validation. Compared to the supervised learning method with complete labeled samples, the detection accuracy of our method was only 0.5% lower, while the workload of data annotation was significantly reduced by more than 98%. In general, this is the first study to apply semi-supervised learning techniques for automatic AF detection using ECG. Our method can effectively reduce the demand for AF data annotations and can improve the clinical practicability of automatic AF detection.
Zhang et al. (Tue,) conducted a other in Paroxysmal atrial fibrillation (n=1,000). Semi-supervised learning method (1D CNN-LSTM neural network) vs. Supervised learning method with complete labeled samples was evaluated on Detection accuracy. A novel semi-supervised learning method for automatic AF detection achieved 97.9% accuracy, which was only 0.5% lower than fully supervised learning while reducing annotation workload by over 98%.