Analysis of brain signals is essential to the study of mental states and various neurological conditions. The two most prevalent noninvasive signals for measuring brain activities are electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS). EEG, characterized by its higher sampling frequency, captures more temporal features, while fNIRS, with a greater number of channels, provides richer spatial information. Although a few previous studies have explored the use of multimodal deep-learning models to analyze brain activity for both EEG and fNIRS, subject-independent training–testing split analysis remains underexplored. The results of the subject-independent setting directly show the model’s ability on unseen subjects, which is crucial for real-world applications. In this paper, we introduce EF-Net, a new CNN-based multimodal deep-learning model. We evaluate EF-Net on an EEG-fNIRS word generation (WG) dataset on the mental state recognition task, primarily focusing on the subject-independent setting. For completeness, we report results in the subject-dependent and subject-semidependent settings as well. We compare our model with five baseline approaches, including three traditional machine learning methods and two deep learning methods. EF-Net demonstrates superior performance in both accuracy and F1 score, surpassing these baselines. Our model achieves F1 scores of 99.36%, 98.31%, and 65.05% in the subject-dependent, subject-semidependent, and subject-independent settings, respectively, surpassing the best baseline F1 scores by 1.83%, 4.34%, and 2.13% These results highlight EF-Net’s capability to effectively learn and interpret mental states and brain activity across different and unseen subjects.

Precision-cut liver tissue slice (PCLS) contains all major cell types of the liver parenchyma and preserves the original cell-cell and cell-matrix contacts. It represents a promising ex vivo model to study liver fibrosis and test the anti-fibrotic effect of experimental compounds in a physiologic environment. In this study using RNAquencing we demonstrated that various pathways functionally related to fibrotic mechanisms were dysregulated in PCLSs derived from rats subjected to bile duct ligation. The Alk5 inhibitor SB525334, nintedanib and sorafenib each reversed a subset of genes dysregulated in fibrotic PCLSs and of those genes we identified 608 genes whose expression was reversed by all three compounds. These genes define a molecular signature characterizing many aspects of liver fibrosis pathology and its attenuation in the model. A panel of 12 genes and 4 secreted biomarkers including procollagen I, HA, IGFBP5 and WISP1, were further validated as efficacy endpoints for the evaluation of anti-fibrotic activity of experimental compounds. Finally, we showed that blockade of αV integrins with a small molecule inhibitor attenuated the fibrotic phenotype in the model. Overall, our results suggest that the rat fibrotic PCLS model may represent a valuable system for target validation and to determine the efficacy of experimental compounds.

The ongoing outbreak of the severe acute respiratory syndrome‐coronavirus 2 (SARS‐CoV‐2) has spread globally and poses a threat to public health and National economic development. Rapid and high‐throughput SARS‐CoV‐2 RNA detection without the need of RNA extraction and amplification remain a key challenge. In this study, a new SARS‐CoV‐2 RNA detection strategy using a microfluidic biochip for the rapid and ultrasensitive detection of SARS‐CoV‐2 without RNA extraction and amplification was developed. This new strategy takes advantage of the specific SARS‐CoV‐2 RNA and probe DNA reaction in the microfluidic channel, fluorescence signal regulation by nanomaterials, and accurate sample control by the microfluidic chip. It presents an ultralow limit of detection of 600 copies mL⁻¹ in a large linear detection regime from 1 aM to 100 fM. Fifteen samples were simultaneously detected in 40 min without the need for RNA purification and amplification. The detection accuracy of the strategy was validated through quantitative reverse transcription polymerase chain reaction (qRT‐PCR), with a recovery of 99–113 %. Therefore, the SARS‐CoV‐2 RNA detection strategy proposed in this study can potentially be used for the quantitative diagnosis of viral infectious diseases.

Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning methods primarily focus on one single data level, which fails to fully exploit the intricate nature of medical time series. To address this issue, we present COMET, an innovative hierarchical framework that leverages data consistencies at all inherent levels in medical time series. Our meticulously designed model systematically captures data consistency from four potential levels: observation, sample, trial, and patient levels. By developing contrastive loss at multiple levels, we can learn effective representations that preserve comprehensive data consistency, maximizing information utilization in a self-supervised manner. We conduct experiments in the challenging patient-independent setting. We compare COMET against six baselines using three diverse datasets, which include ECG signals for myocardial infarction and EEG signals for Alzheimer's and Parkinson's diseases. The results demonstrate that COMET consistently outperforms all baselines, particularly in setup with 10% and 1% labeled data fractions across all datasets. These results underscore the significant impact of our framework in advancing contrastive representation learning techniques for medical time series. The source code is available at https://github.com/DL4mHealth/COMET.