Personalized Transfer Learning for Single-Lead ECG-Based Sleep Apnea Detection: Exploring the Label Mapping Length and Transfer Strategy Using Hybrid Transformer Model

Objective: Automatic sleep apnea (SA) detection based on deep learning (DL) and single-lead electrocardiogram (ECG) has been extensively studied. We aim to explore the impact of different DL model structures and label mapping length (LML) on personalized transfer learning (TL), providing personalized TL applicability conditions based on the proposed hybrid transformer model (HTM). Methods: Two DL models, a pure convolutional neural network (CNN)-based model (PCM) and a proposed HTM, are included in the study. Eight different LMLs are considered. Furthermore, various personalized TL strategies are introduced to thoroughly explore the impact. Finally, two-sided t-tests are utilized to evaluate the significance. Results: In the same database, the average accuracy and AUC for the personalized PCM are 0.8412 and 0.9002, respectively, with p < 0.001 , while the hybrid transformer-based personalized model achieves an average accuracy of 0.8537 and an average AUC of 0.9147 with p < 0.001 . Across databases, the accuracy and AUC of personalized HTM reach 0.8271 and 0.8724, respectively, and p < 0.001 . Conclusion: The increase in LML has a beneficial impact on the general model (GM) and personalized model for different model structures. The HTM exhibits better performance in both GM and personalized TL compared to the PCM. Additionally, personalized TL achieves significant improvement when utilizing only positive samples within the same database. However, it is more advantageous to utilize only negative samples when performing cross-database personalized TL. Significance: This article provides guidance for personalized TL in SA detection and provides an HTM-based personalized TL method.