A meta-learning method with reduced data requirements for training and updating deep learning models on wearable devices

Abstract Background 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. Methods Addressing these challenges, in this paper, we propose 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 our proposed method in two case studies, namely, the detection of epileptic seizures and the detection of atrial fibrillation (AF). Results 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 AF, 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, the proposed method reduces the energy consumption for model updates by 456x and 418x for epileptic seizure and AF detection, respectively. Conclusions Our findings demonstrate that the proposed method effectively overcomes the critical barriers of data scarcity and energy constraints, offering a practical and efficient solution for the lifecycle management of deep learning models on wearable health devices.