Early warning of atrial fibrillation using deep learning.

Atrial fibrillation (AF), the most prevalent cardiac rhythm disorder, significantly increases hospitalization and health risks. Reverting from AF to sinus rhythm (SR) often requires intensive interventions. This study presents a deep-learning model capable of predicting the transition from SR to AF on average 30.8 min before the onset appears, with an accuracy of 83% and an F1 score of 85% on the test data. This performance was obtained from R-to-R interval signals, which can be accessible from wearable technology. Our model, entitled Warning of Atrial Fibrillation (WARN), consists of a deep convolutional neural network trained and validated on 24-h Holter electrocardiogram data from 280 patients, with 70 additional patients used for testing and further evaluation on 33 patients from two external centers. The low computational cost of WARN makes it ideal for integration into wearable technology, allowing for continuous heart monitoring and early AF detection, which can potentially reduce emergency interventions and improve patient outcomes.

Mechanisms of imbalanced testicular homeostasis in infancy due to aberrant histone acetylation in undifferentiated spermatogonia under different concentrations of Di(2-ethylhexyl) phthalate (DEHP) exposure.

Di (2-ethylhexyl) phthalate (DEHP), identified as an endocrine-disrupting chemical, is associated with reproductive toxicity. This association is particularly noteworthy in newborns with incompletely developed metabolic functions, as exposure to DEHP can induce enduring damage to the reproductive system, potentially influencing adult reproductive health. In this study, we continuously administered 40 µg/kg and 80 µg/kg DEHP to postnatal day 5 (PD5) mice for ten days to simulate low and high doses of DEHP exposure during infancy. Utilizing single-cell RNA sequencing (scRNA-seq), our analysis revealed that varying concentrations of DEHP exposure during infancy induced distinct DNA damage response characteristics in testicular Undifferentiated spermatogonia (Undiff SPG). Specifically, DNA damage triggered mitochondrial dysfunction, leading to acetyl-CoA content alterations. Subsequently, this disruption caused aberrations in histone acetylation patterns, ultimately resulting in apoptosis of Undiff SPG in the 40 µg/kg DEHP group and autophagy in the 80 µg/kg DEHP group. Furthermore, we found that DEHP exposure impacts the development and functionality of Sertoli and Leydig cells through the focal adhesion and PPAR signaling pathways, respectively. We also revealed that Leydig cells regulate the metabolic environment of Undiff SPG via Ptn-Sdc4 and Mdk-Sdc4 after DEHP exposure. Finally, our study provided pioneering evidence that disruptions in testicular homeostasis induced by DEHP exposure during infancy endure into adulthood. In summary, this study elucidates the molecular mechanisms through which DEHP exposure during infancy influences the development of testicular cell populations.

Chestnut polysaccharide rescues the damaged spermatogenesis process of asthenozoospermia-model mice by upregulating the level of palmitic acid.

Introduction: In recent years, the quality of male semen has been decreasing, and the number of male infertilities caused by asthenozoospermia is increasing year by year, and the diagnosis and treatment of patients with asthenozoospermia are gradually receiving the attention of the whole society. Due to the unknown etiology and complex pathogenesis, there is no specific treatment for asthenozoospermia. Our previous study found that the administration of chestnut polysaccharide could alter the intestinal microbiota and thus improve the testicular microenvironment, and rescue the impaired spermatogenesis process by enhancing the expression of reproduction-related genes, but its exact metabolome-related repairment mechanism of chestnut polysaccharide is still unclear. Methods and results: In this study, we studied the blood metabolomic changes of busulfan-induced asthenozoospermia-model mice before and after oral administration of chestnut polysaccharide with the help of metabolome, and screened two key differential metabolites (hydrogen carbonate and palmitic acid) from the set of metabolomic changes; we then analyzed the correlation between several metabolites and between different metabolites and intestinal flora by correlation analysis, and found that palmitic acid in the blood serum of mice after oral administration of chestnut polysaccharide had different degrees of correlation with various metabolites, and palmitic acid level had a significant positive correlation with the abundance of Verrucomicrobia; finally, we verified the role of palmitic acid in rescuing the damaged spermatogenesis process by using asthenozoospermia-model mice, and screened the key target gene for palmitic acid to play the rescuing effect by integrating the analysis of multiple databases. Discussion: In conclusion, this study found that chestnut polysaccharide rescued the damaged spermatogenesis in asthenozoospermia-model mice by upregulating palmitic acid level, which will provide theoretical basis and technical support for the use of chestnut polysaccharide in the treatment of asthenozoospermia.

A semi-supervised learning approach for COVID-19 detection from chest CT scans.

COVID-19 has spread rapidly all over the world and has infected more than 200 countries and regions. Early screening of suspected infected patients is essential for preventing and combating COVID-19. Computed Tomography (CT) is a fast and efficient tool which can quickly provide chest scan results. To reduce the burden on doctors of reading CTs, in this article, a high precision diagnosis algorithm of COVID-19 from chest CTs is designed for intelligent diagnosis. A semi-supervised learning approach is developed to solve the problem when only small amount of labelled data is available. While following the MixMatch rules to conduct sophisticated data augmentation, we introduce a model training technique to reduce the risk of model over-fitting. At the same time, a new data enhancement method is proposed to modify the regularization term in MixMatch. To further enhance the generalization of the model, a convolutional neural network based on an attention mechanism is then developed that enables to extract multi-scale features on CT scans. The proposed algorithm is evaluated on an independent CT dataset of the chest from COVID-19 and achieves the area under the receiver operating characteristic curve (AUC) value of 0.932, accuracy of 90.1%, sensitivity of 91.4%, specificity of 88.9%, and F1-score of 89.9%. The results show that the proposed algorithm can accurately diagnose whether a chest CT belongs to a positive or negative indication of COVID-19, and can help doctors to diagnose rapidly in the early stages of a COVID-19 outbreak.

A Noncanonical Hedgehog Signaling Exerts a Tumor-Promoting Effect on Pancreatic Cancer Cells Via Induction of Osteopontin Expression.

Objective: Sonic Hedgehog (Shh)-Gli1 signaling and osteopontin (OPN) play vital roles in pancreatic cancer. However, the precise mechanisms of both signals have not been fully clarified, and whether there is a correlation between them in pancreatic ductal adenocarcinoma (PDAC) is unknown. This study aims to confirm the effect of OPN on human PDAC and assess whether Hh signaling affects pancreatic cancer cells through upregulation of OPN. Materials and Methods: OPN expression in human PDAC tissues and cell lines was investigated. Proliferation, apoptosis, migration, and invasion of OPN-knockdown BxPC-3 cells were observed. We analyzed the correlation between Shh or Gli1 and OPN expression in human PDAC. Hh signaling inhibitors and shRNA against Gli1 were used to confirm if OPN expression in BxPC-3 cells was regulated by Hh canonical or noncanonical pathway. We also evaluated the proliferation, apoptosis, migration, and invasion of Gli1-knockdown BxPC-3 cells. Results: OPN is highly expressed in human PDAC tissues and cell lines. The proliferation, migration, and invasion of BxPC-3 cell lines were decreased, whereas apoptosis was increased when OPN was knocked down. Correlation analysis showed that Gli1, but not Shh, was associated with OPN expression in human PDAC, and Gli1 regulated OPN production in BxPC-3 cells through a noncanonical pathway because Gli but not Smo inhibitor reduced OPN expression. Similar to above, the proliferation, migration, and invasion of BxPC-3 cells were decreased, whereas the apoptosis was increased when Gli1 was knocked down. Supplement of exogenous OPN protein could partially reverse the effect of both OPN knockdown and Gli1 knockdown on the bio-behavior of BxPC-3 cells. Conclusion: Hh signaling promotes proliferation, migration, and invasion but inhibits apoptosis of pancreatic cancer cells through upregulation of OPN in a noncanonical pathway.