Key result
A metalearning-based personalization method achieved 8.2%, 2.5%, and 6.4% higher accuracy in VF detection, AF detection, and human activity recognition compared with existing DL methods.
Why the study?
Individual patient differences cause accuracy degradation in pretrained deep learning models for biosignal health monitoring, and fine-tuning does not generalize well to new data.
Does a metalearning-based personalization method improve detection accuracy for VF, AF, and human activity compared to existing deep learning methods?
Does a metalearning-based personalization method improve detection accuracy for VF, AF, and human activity compared to existing deep learning methods?
A novel metalearning-based personalization method for neural networks improves the accuracy of patient-specific health monitoring, including VF and AF detection, compared to conventional deep learning approaches.
Answers are grounded in this paper and cite their sources.
May enhance personalized VF/AF detection on devices; leaves open validation in larger prospective trials.
The Internet of Things (IoT) has been widely applied in personal health monitoring on biosignals. Conventional detection methods in the field count on a variety of heuristic criteria by utilizing extracted features, which are carefully selected through extensive clinical trials and experts’ experiences. Recently, deep learning (DL) gains rapidly growing attention in health monitoring. The most significant advantage of DL-based methods is that DL could execute feature engineering automatically with only labeled data, which results in a great reduction in the expertise involved and manual works in the detection method’s design. However, individual differences among various patients (subjects) can lead to accuracy degradation of the pretrained deep model. Simply fine-tuning the deep model with the patient-specific data cannot alleviate the problem since the pretrained model may not generalize well to new data. To address the problem, we propose a metalearning-based personalization method to generate the personalized neural network for each patient to conduct patient-specific detection. Specifically, the proposed metalearning method leverages a novel patientwise training tasks formatting strategy to train the neural network that ends up with a well-generalized model initialization containing across-patient knowledge. The well-generalized model initialization would then be utilized to perform a quick adaptation to the specific patient’s data domain. In this way, a new patient could be immediately assigned with a personalized neural network using limited labeled data. Experimental results show that the proposed metalearning-based personalization method achieves 8.2%, 2.5%, and 6.4% higher accuracy when compared with the existing DL detection methods in VF detection, AF detection, and human activity recognition, respectively.
No takes yet. Share an insight, caveat, or question.
Jia et al. (2022) studied Ventricular fibrillation, atrial fibrillation, and human activity recognition. Metalearning-based personalization method for neural networks vs. Existing deep learning detection methods was evaluated on Accuracy in VF detection, AF detection, and human activity recognition (8.2%, 2.5%, and 6.4% higher accuracy). A metalearning-based personalization method achieved 8.2%, 2.5%, and 6.4% higher accuracy in VF detection, AF detection, and human activity recognition compared with existing DL methods.
Synapse has enriched 10 related papers. Consider them for comparative context: