Background: Gestational diabetes mellitus (GDM) is a metabolic disorder posing significant risks to maternal and infant health, with a lack of effective early screening markers. Therefore, identifying early screening biomarkers for GDM with higher sensitivity and specificity is urgently needed. Methods: High-throughput sequencing was employed to screen for key circular RNAs (circRNAs), which were then evaluated using reverse transcription quantitative polymerase chain reaction. Logistic regression analysis was conducted to examine the relationship between clinical characteristics, circRNA expression, and adverse pregnancy outcomes. The diagnostic accuracy of circRNAs for early and mid-pregnancy GDM was assessed using receiver operating characteristic curves. Pearson correlation analysis was utilized to explore the relationship between circRNA levels and oral glucose tolerance test results. A predictive model for early GDM was established using logistic regression. Results: Significant alterations in circRNA expression profiles were detected in GDM patients, with hsa_circ_0031560 and hsa_ circ_0000793 notably upregulated during the first and second trimesters. These circRNAs were associated with adverse pregnancy outcomes and effectively differentiated GDM patients, with second trimester cohorts achieving an area under the curve (AUC) of 0.836. In first trimester cohorts, these circRNAs identified potential GDM patients with AUCs of 0.832 and 0.765, respectively. The early GDM prediction model achieved an AUC of 0.904, validated in two independent cohorts. Conclusion Hsa_circ_0031560, hsa_circ_0000793, and the developed model serve as biomarkers for early prediction or midterm diagnosis of GDM, offering clinical tools for early GDM screening.

Background: Gestational diabetes mellitus (GDM) is a metabolic disorder posing significant risks to maternal and infant health, with a lack of effective early screening markers. Therefore, identifying early screening biomarkers for GDM with higher sensitivity and specificity is urgently needed. Methods: High-throughput sequencing was employed to screen for key circular RNAs (circRNAs), which were then evaluated using reverse transcription quantitative polymerase chain reaction. Logistic regression analysis was conducted to examine the relationship between clinical characteristics, circRNA expression, and adverse pregnancy outcomes. The diagnostic accuracy of circRNAs for early and mid-pregnancy GDM was assessed using receiver operating characteristic curves. Pearson correlation analysis was utilized to explore the relationship between circRNA levels and oral glucose tolerance test results. A predictive model for early GDM was established using logistic regression. Results: Significant alterations in circRNA expression profiles were detected in GDM patients, with hsa_circ_0031560 and hsa_ circ_0000793 notably upregulated during the first and second trimesters. These circRNAs were associated with adverse pregnancy outcomes and effectively differentiated GDM patients, with second trimester cohorts achieving an area under the curve (AUC) of 0.836. In first trimester cohorts, these circRNAs identified potential GDM patients with AUCs of 0.832 and 0.765, respectively. The early GDM prediction model achieved an AUC of 0.904, validated in two independent cohorts. Conclusion Hsa_circ_0031560, hsa_circ_0000793, and the developed model serve as biomarkers for early prediction or midterm diagnosis of GDM, offering clinical tools for early GDM screening.

With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

In recent years, China has been facing the dual challenges of declining fertility rates and births, with male reproductive health issues, especially the decline in semen quality, identified as a pivotal contributor to this phenomenon. Meanwhile, accumulating evidence indicates that air pollutants, an increasingly severe environmental problem, can damage semen quality not only directly through their biological toxicity but also indirectly by disrupting the composition of microbial communities in the gut and semen, thereby dysregulating immune function, endocrine homeostasis, and oxidative stress responses. The gut microbiota and semen microbiota, as important components of the human microecosystem, play crucial roles in maintaining reproductive health. This article comprehensively reviewed the research progress on the potential effects of air pollutants (particulate matter and gaseous pollutants), gut microbiota, and semen microbiota on semen quality. Specifically, it elucidated the mechanisms of interaction between these factors and explored how they affect male fertility.

Background: Gestational diabetes mellitus (GDM) is a metabolic disorder posing significant risks to maternal and infant health, with a lack of effective early screening markers. Therefore, identifying early screening biomarkers for GDM with higher sensitivity and specificity is urgently needed. Methods: High-throughput sequencing was employed to screen for key circular RNAs (circRNAs), which were then evaluated using reverse transcription quantitative polymerase chain reaction. Logistic regression analysis was conducted to examine the relationship between clinical characteristics, circRNA expression, and adverse pregnancy outcomes. The diagnostic accuracy of circRNAs for early and mid-pregnancy GDM was assessed using receiver operating characteristic curves. Pearson correlation analysis was utilized to explore the relationship between circRNA levels and oral glucose tolerance test results. A predictive model for early GDM was established using logistic regression. Results: Significant alterations in circRNA expression profiles were detected in GDM patients, with hsa_circ_0031560 and hsa_ circ_0000793 notably upregulated during the first and second trimesters. These circRNAs were associated with adverse pregnancy outcomes and effectively differentiated GDM patients, with second trimester cohorts achieving an area under the curve (AUC) of 0.836. In first trimester cohorts, these circRNAs identified potential GDM patients with AUCs of 0.832 and 0.765, respectively. The early GDM prediction model achieved an AUC of 0.904, validated in two independent cohorts. Conclusion Hsa_circ_0031560, hsa_circ_0000793, and the developed model serve as biomarkers for early prediction or midterm diagnosis of GDM, offering clinical tools for early GDM screening.

Background: Gestational diabetes mellitus (GDM) is a metabolic disorder posing significant risks to maternal and infant health, with a lack of effective early screening markers. Therefore, identifying early screening biomarkers for GDM with higher sensitivity and specificity is urgently needed. Methods: High-throughput sequencing was employed to screen for key circular RNAs (circRNAs), which were then evaluated using reverse transcription quantitative polymerase chain reaction. Logistic regression analysis was conducted to examine the relationship between clinical characteristics, circRNA expression, and adverse pregnancy outcomes. The diagnostic accuracy of circRNAs for early and mid-pregnancy GDM was assessed using receiver operating characteristic curves. Pearson correlation analysis was utilized to explore the relationship between circRNA levels and oral glucose tolerance test results. A predictive model for early GDM was established using logistic regression. Results: Significant alterations in circRNA expression profiles were detected in GDM patients, with hsa_circ_0031560 and hsa_ circ_0000793 notably upregulated during the first and second trimesters. These circRNAs were associated with adverse pregnancy outcomes and effectively differentiated GDM patients, with second trimester cohorts achieving an area under the curve (AUC) of 0.836. In first trimester cohorts, these circRNAs identified potential GDM patients with AUCs of 0.832 and 0.765, respectively. The early GDM prediction model achieved an AUC of 0.904, validated in two independent cohorts. Conclusion Hsa_circ_0031560, hsa_circ_0000793, and the developed model serve as biomarkers for early prediction or midterm diagnosis of GDM, offering clinical tools for early GDM screening.

Objective Focusing on gynecological surgery,we constructed a prediction model for surgical duration by extracting features from unstructured surgical planning texts and integrating multimodal data via artificial intelligence technology.Methods The clinical data of 34 614 patients who underwent gynecologic surgeries at West China Second University Hospital,Sichuan University between January 2022 and October 2024 were collected.An embedding-transformer model was constructed to convert surgical planning texts into a one-dimensional numerical feature,referred to as the step feature.The predictive value of the step feature was assessed by comparing the performance improvements of linear regression,random forest,eXtreme Gradient Boosting(XGBoost),support vector regression,K-nearest neighbor regression,and artificial neural network algorithms in two scenarios—with and without the step feature as an input.The out-of-sample prediction accuracy of the models was assessed using mean absolute error(MAE),root mean squared error(RMSE),and R-squared(R2).Furthermore,the model interpretability was examined using SHapley Additive exPlanations(SHAP)values.Results SHAP results showed that the step feature had the highest predictive contribution.Temporal factors in surgical scheduling also influenced gynecological surgery duration.The XGBoost model demonstrated optimal performance on the test set,significantly improving prediction accuracy with a 40.43%increase in R2,while reducing MAE and RMSE by 21.27%and 20.13%,respectively,compared to the baseline model without the step feature.Conclusion The embedding-transformer model developed in this study effectively extracts features from surgical planning texts and enhances the predictive performance of machine learning models.The XGBoost prediction model can assist hospital administrators in implementing more refined management of gynecological surgeries and improving the utilization efficiency of surgical resources.

The research on the cardiovascular toxicity of air pollutants is in urgent need of collaborative innovation across multiple models. This paper systematically reviewed the advantages and limitations of four principal research models of cardiotoxicity, including epidemiological model, mammalian model, zebrafish model, and in vitro model. Epidemiological models have been used to demonstrate a significant correlation between exposure to PM_2.5 and both the incidence and mortality of cardiovascular diseases within populations; however, these models face challenges in establishing causal inferences and interpreting individual mechanisms. Mammalian models have been applied to elucidate the pathogenic mechanisms of PM_2.5 at both the systemic and organ-specific levels, yet they encounter difficulties related to interspecies differences and throughput constraints. Zebrafish models, with their transparent embryos and observable development, offer a distinctive opportunity for high-throughput screening and mechanistic investigation of PM_2.5-induced cardiac developmental toxicity. Nonetheless, their cardiac physiological structure diverges from that of mammals, limiting their capacity to accurately model chronic conditions such as coronary heart disease. In vitro models, particularly human heart organoids and chip technologies, have provided profound insights into the direct toxic mechanisms of PM_2.5, including disruptions in calcium homeostasis, cellular senescence, and electrophysiological irregularities at the cellular and molecular levels. Despite these advancements, the complexity and developmental maturity of these models present challenges to their broader application. This paper proposed that the key to overcoming the bottlenecks of single models lies in the construction of an integrated evaluation system that combines “epidemiological studies, mammalian models, zebrafish models, and in vitro models”. By focusing on three aspects, namely model integration, technological convergence, and policy support, it is intended to collaboratively address issues such as standardization of multi-model data, simulation of complex exposure scenarios and susceptible life stages, and transformation pathways. This will provide innovative methodological support for the analysis of the cardiotoxic mechanisms of air pollutants, the assessment of environmental health impacts, and the formulation of precise prevention and control strategies.

Pulmonary hypertension(PH)is a fatal disease characterized by pulmonary vascular remodeling,ultimately leading to right heart failure and death.Current treatments for PH are suboptimal,with no substantial improvement in overall survival among patients with advanced PH.Despite some progress in understanding the pathogenesis of PH,further studies at the molecular level are needed to develop more effective treatments for PH.Recent research has shown that long non-coding RNAs(lncRNAs)have an important regulatory function in the pathophysiological process of PH,and may thus be potential disease biomarkers and therapeutic targets.In this paper,we review recent progress in our understanding of the molecular mechanisms of lncRNAs in PH.

Objective:To explore how the teaching of ideological and political courses in colleges and universities can effectively guide online public opinion under the background of melted media,so as to cope with the challenges posed by diversified information transmission channels and complex and changeable online public opinion,thereby promoting the formation of correct values and ideological cognition among students.Methods:A total of 1 353 students who volunteered to participate in this survey in a university that offers courses related to online public opinion guidance were selected as the survey subjects.Multiple linear regression analysis was used to analyze how universities should teach students to deal with online hot topics through relevant ideological and political courses.Results:Results of multiple linear regression analysis indicated that the teaching of ideological and political courses in colleges and universities under the background of melted media significantly enhanced students'awareness of online public opinion,and the courses played a positive role in the guidance.The improvement of media literacy facilitated the formation of students'correct values and ideological cognition,effectively responding to the challenges of diversified information dissemination.Variables including the infringement of personal privacy by online public opinion,the enhancement of civic consciousness,the impact on learning,and the distortion of reality understanding all had an impact on students'perception of the teaching effect of ideological and political courses.Conclusions:The teaching of ideological and political courses in colleges and universities plays a significant role in guiding online public opinion under the background of melted media.By enhancing students'media literacy,discernment,and emotional management ability,it effectively promotes the formation of students'correct values and ideological ideological,and provides strong support for the healthy growth of students in the complex network environment.The important role of ideological and political teaching in cultivating students'comprehensive abilities and guiding them to correctly deal with online public opinion is emphasized.