Adhesive Carbon Paste Electrode for Convenient and Long-term Electrocardiogram Monitoring: A Pilot Study.

Long-term electrocardiogram (ECG) monitoring is an important and widely-used technique in the clinic that helps with the diagnosis of possible diseases that cannot be detected in a short time monitoring. However, the clinically used electrode needs conductive gel to reduce the impedance between the skin and the electrodes, which easily causes the possibility of allergy. Moreover, as the conductive gel becomes dry, the signal's quality will decrease accordingly. In this paper, we proposed a novel adhesive Carbon Paste Electrode (CPE) to achieve convenient and long-term ECG monitoring. By comparing the time-domain waveforms, the R-R peak intervals difference, and the Signal-to-Noise Ratio (SNR) of ECG with the traditional conductive gel-based electrode (Gel) in fixed and unfixed conditions, the performance of the proposed CPE was investigated. The results showed that the CPE could achieve similar ECG monitoring both in fixed and unfixed conditions. When on Day 2, the quality acquired by Gel began to decrease while CPE was still stable, which was obvious especially in unfixed condition. The R-R peak intervals showed that on Day 2, the Gel was unreliable with some abnormal points occurring. Besides, the results of SNR and average heart rate (AHR) also confirmed that the CPE could achieve similar results as Gel on Day 1 and outperformed Gel on Day 2. It is believed that the proposed CPE opens a window of high-quality long-term ECG monitoring with more convenience.

Classification of attention deficit/hyperactivity disorder based on EEG signals using a EEG-Transformer model∗.

Objective. Attention-deficit/hyperactivity disorder (ADHD) is the most common neurodevelopmental disorder in adolescents that can seriously impair a person's attention function, cognitive processes, and learning ability. Currently, clinicians primarily diagnose patients based on the subjective assessments of the Diagnostic and Statistical Manual of Mental Disorders-5, which can lead to delayed diagnosis of ADHD and even misdiagnosis due to low diagnostic efficiency and lack of well-trained diagnostic experts. Deep learning of electroencephalogram (EEG) signals recorded from ADHD patients could provide an objective and accurate method to assist physicians in clinical diagnosis.Approach. This paper proposes the EEG-Transformer deep learning model, which is based on the attention mechanism in the traditional Transformer model, and can perform feature extraction and signal classification processing for the characteristics of EEG signals. A comprehensive comparison was made between the proposed transformer model and three existing convolutional neural network models.Main results. The results showed that the proposed EEG-Transformer model achieved an average accuracy of 95.85% and an average AUC value of 0.9926 with the fastest convergence speed, outperforming the other three models. The function and relationship of each module of the model are studied by ablation experiments. The model with optimal performance was identified by the optimization experiment.Significance. The EEG-Transformer model proposed in this paper can be used as an auxiliary tool for clinical diagnosis of ADHD, and at the same time provides a basic model for transferable learning in the field of EEG signal classification.

[A neonatal intelligent regulation system based on the combination of mild hypothermia mattress and hyperbaric oxygen chamber: introduction to a patent]. / 基于亚低温床垫与高压氧舱结合的新生儿智能调控系统.

Neonatal hypoxic-ischemic encephalopathy (HIE) is a common disease that affects brain function in neonates. At present, mild hypothermia and hyperbaric oxygen therapy are the main methods for the treatment of neonatal HIE; however, they are independent of each other and cannot be combined for synchronous treatment, without monitoring of brain function-related physiological information. In addition, parameter setting of hyperbaric oxygen chamber and mild hypothermia mattress relies on the experience of the medical practitioner, and the parameters remain unchanged throughout the medical process. This article proposes a new device for the treatment of neonatal HIE, which has the modules of hyperbaric oxygen chamber and mild hypothermic mattress, so that neonates can receive the treatment of hyperbaric oxygen chamber and/or mild hypothermic mattress based on their conditions. Meanwhile, it can realize the real-time monitoring of various physiological information, including amplitude-integrated electroencephalogram, electrocardiogram, and near-infrared spectrum, which can monitor brain function, heart rate, rhythm, myocardial blood supply, hemoglobin concentration in brain tissue, and blood oxygen saturation. In combination with an intelligent control algorithm, the device can intelligently regulate parameters according to the physiological information of neonates and give recommendations for subsequent treatment.

A Deep-Learning-Based Artificial Intelligence System for the Pathology Diagnosis of Uterine Smooth Muscle Tumor.

We aimed to develop an artificial intelligence (AI) diagnosis system for uterine smooth muscle tumors (UMTs) by using deep learning. We analyzed the morphological features of UMTs on whole-slide images (233, 108, and 30 digital slides of leiomyosarcomas, leiomyomas, and smooth muscle tumors of uncertain malignant potential stained with hematoxylin and eosin, respectively). Aperio ImageScope software randomly selected ≥10 areas of the total field of view. Pathologists randomly selected a marked region in each section that was no smaller than the total area of 10 high-power fields in which necrotic, vascular, collagenous, and mitotic areas were labeled. We constructed an automatic identification algorithm for cytological atypia and necrosis by using ResNet and constructed an automatic detection algorithm for mitosis by using YOLOv5. A logical evaluation algorithm was then designed to obtain an automatic UMT diagnostic aid that can "study and synthesize" a pathologist's experience. The precision, recall, and F1 index reached more than 0.920. The detection network could accurately detect the mitoses (0.913 precision, 0.893 recall). For the prediction ability, the AI system had a precision of 0.90. An AI-assisted system for diagnosing UMTs in routine practice scenarios is feasible and can improve the accuracy and efficiency of diagnosis.

Study of Anti-Inflammatory and Analgesic Activity of Scorpion Toxins DKK-SP1/2 from Scorpion Buthus martensii Karsch (BmK).

Buthus martensii Karsch (BmK), is a kind of traditional Chinese medicine, which has been used for a long history for the treatment of many diseases, such as inflammation, pain and cancer. In this study, DKK-SP1/2/3 genes were screened and extracted from the cDNA library of BmK. The DKK-SP1/2/3 were expressed by using plasmid pSYPU-1b in E. coli BL21, and recombinant proteins were obtained by column chromatography. In the xylene-induced mouse ear swelling and carrageenan-induced rat paw swelling model, DKK-SP1 exerted a significant anti-inflammatory effect by inhibiting the expression of Nav1.8 channel. Meanwhile, the release of pro-inflammatory cytokines (COX-2, IL-6) was decreased significantly and the release of anti-inflammatory cytokines (IL-10) were elevated significantly. Moreover, DKK-SP1 could significantly decrease the Nav1.8 current in acutely isolated rat DRG neurons. In the acetic acid-writhing and ION-CCI model, DKK-SP2 displayed significant analgesic activity by inhibiting the expression of the Nav1.7 channel. Moreover, DKK-SP2 could significantly inhibit the Nav1.7 current in the hNav1.7-CHO cells.