Semi-Supervised Learning for Low-Cost Personalized Obstructive Sleep Apnea Detection Using Unsupervised Deep Learning and Single-Lead Electrocardiogram.

OBJECTIVE: Obstructive sleep apnea (OSA) is a common sleep-related breathing disorder that can lead to a wide range of health issues if left untreated. This study aims to address the lack of research on personalized models for single-lead electrocardiogram (ECG)-based OSA detection, by proposing an automatic semi-supervised algorithm for automated low-cost personalization fine-tuning. METHODS: We utilize a convolutional neural network (CNN)-based auto-encoder (AE) with a modified training objective to detect anomalous region of OSA. An indicator based on model outputs is utilized as a benchmark measure to assign pseudo-labels with confidence to each sample. Finally, we perform validation of the semi-supervised algorithm on the same database and cross-database scenarios. RESULTS: By introducing semi-supervised personalization, the accuracy, AUC, and mean absolute error (MAE) of the general model (GM) of 35 subjects from the same database are improved from 86.3%, 0.915, and 5.178 to 90.3%, 0.948, and 2.593. Simultaneously, in the validation of 25 subjects from a cross-database, the accuracy, AUC, and MAE of the GM are enhanced from 75.6%, 0.800, and 9.149 to 84.3%, 0.881, and 3.509. CONCLUSION: The improved version of AE demonstrates excellent adaptability in identifying abnormal features in OSA, employing a data-driven approach to assign pseudo-labels for unknown data automatically. Additionally, leveraging the pseudo-labels through a semi-supervised fine-tuning strategy provides a solution to overcome the limitation of clinical annotations, facilitating low-cost implementation of personalized models. SIGNIFICANCE: The semi-supervised approach proposed in this article provides a high-performance and annotation-free solution for personalized adjustment of automatic OSA detection.

Exploring the Applicability of Transfer Learning and Feature Engineering in Epilepsy Prediction Using Hybrid Transformer Model.

OBJECTIVE: Epilepsy prediction algorithms offer patients with drug-resistant epilepsy a way to reduce unintended harm from sudden seizures. The purpose of this study is to investigate the applicability of transfer learning (TL) technique and model inputs for different deep learning (DL) model structures, which may provide a reference for researchers to design algorithms. Moreover, we also attempt to provide a novel and precise Transformer-based algorithm. METHODS: Two classical feature engineering methods and the proposed method which consists of various EEG rhythms are explored, then a hybrid Transformer model is designed to evaluate the advantages over pure convolutional neural networks (CNN)-based models. Finally, the performances of two model structures are analyzed utilizing patient-independent approach and two TL strategies. RESULTS: We tested our method on the CHB-MIT scalp EEG database, the results showed that our feature engineering method gains a significant improvement in model performance and is more suitable for Transformer-based model. In addition, the performance improvement of Transformer-based model utilizing fine-tuning strategies is more robust than that of pure CNN-based model, and our model achieved an optimal sensitivity of 91.7% with false positive rate (FPR) of 0.00/h. CONCLUSION: Our epilepsy prediction method achieves excellent performance and demonstrates its advantage over pure CNN-based structure in TL. Moreover, we find that the information contained in the gamma ( γ ) rhythm is helpful for epilepsy prediction. SIGNIFICANCE: We propose a precise hybrid Transformer model for epilepsy prediction. The applicability of TL and model inputs is also explored for customizing personalized models in clinical application scenarios.

[Clinical efficacy of microvascular decompression plus intraoperative monitoring of abnormal muscle response in the treatment of hemifacial spasm].

OBJECTIVE: To explore the clinical efficacy of microvascular decompression plus intraoperative monitoring of abnormal muscle response in the treatment of hemifacial spasm. METHODS: Between 2009 and 2010, a total of 47 patients underwent microvascular decompression for hemifacial spasm. There were 15 males and 32 females with an age range 23 - 70 years old. During operations, intermittent electrical pulses were applied to stimulate the zygomatic branch of facial nerve at the spasm side. And evoked potentials were monitored in orbicularis oris. All patients were followed up for 5 - 22 months. RESULTS: The abnormal muscle responses were recorded pre-operatively in all 47 patients at the spasm side. In 42 patients, the abnormal muscle responses disappeared at the different stages of operations (4 while opening dura, 9 while dissecting arachnoid membrane and 29 while separating responsible vessels). All 42 patients were cured during the follow-up period. In the remaining 5 patients, the abnormal muscle response were still recorded even at the end of operations. Two of 5 patients were free from spasm during the follow-up period while the symptoms of other 3 patients became obviously relieved. CONCLUSION: The combined approaches of microvascular decompression and intraoperative monitoring of abnormal muscle response may assist the identification of responsible vessels and improve the outcomes of hemifacial spasm.

In vivo detection of reduced scattering coefficient of C6 glioma in rat brain tissue by near-infrared spectroscopy.

The purpose of this study is to investigate the reduced scattering coefficient of C6 glioma by the near-infrared (NIR) technique. Light scattering properties of C6 glioma in brain tissue is measured by NIR spectroscopy within the wavelength range from 700 to 850 nm. C6 gliomas were implanted in rats' right brains. The scattering properties of the left and right target corresponding to the position of normal and tumor tissue were measured by a bifurcated needle probe on postoperative days 3, 10, and 17. The results show that there was no significant difference in reduced scattering coefficient between left and right brain tissue at postoperative day 3, but significant decreases were found between left and right brains at postoperative days 10 and 17. This study proved our initial hypothesis that the NIR technique may have a potential for clinical application in brain muglioma diagnosis.