Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective: To investigate the knowledge of hepatitis C prevention and treatment and related factors among two groups of female sex workers (FSW) and men who have sex with men (MSM) in the Xizang Autonomous Region (Xizang) to provide a basis for the subsequent development of Hepatitis C publicity and education strategies. Methods: From August to September 2021, a special survey was conducted among 1 244 FSW and 234 MSM in 5 districts (counties) of 4 regions in Xizang. A one-on-one face-to-face questionnaire survey was adopted, and the χ² test and logistic regression were used to analyze the related factors of awareness of hepatitis C prevention and treatment among FSW and MSM. Results: The awareness rates of hepatitis C prevention and treatment knowledge among FSW and MSM were 35.0% (436/1 244) and 11.1% (26/234), respectively. Multivariate logistic regression analysis revealed that the positive related factors of FSW' awareness of hepatitis C prevention and treatment knowledge among those who had high school or technical secondary school education (aOR=4.72, 95%CI: 3.30-6.74) and college education or above (aOR=2.24, 95%CI: 1.58-3.18), those who experienced self-perceived risk of HCV infection (aOR=1.87, 95%CI: 1.43-2.45), negative related factors included married or cohabiting (aOR=0.58, 95%CI: 0.35-0.95), divorce or windowless (aOR=0.44, 95%CI: 0.27-0.72), no condom was used in the most recent commercial sexual activity (aOR=0.54, 95%CI: 0.43-0.69). The positive related factors of MSM's awareness of hepatitis C prevention and treatment knowledge were over 40 years old (aOR=8.65, 95%CI: 3.19-23.42) and having a self-perceived risk of HCV infection (aOR=6.25, 95%CI: 2.50-15.61). Conclusions: The awareness rate of hepatitis C prevention and treatment among FSW and MSM was relatively low in Xizang in 2021 and urgently needs to be improved. It is necessary to formulate targeted publicity strategies based on the characteristics of these two groups of people, increase publicity efforts, and expand the coverage of knowledge publicity to popularize key points about the clinical manifestations, treatment options, and transmission routes of hepatitis C, and carry out necessary warnings and education.
Humans ; Male ; Hepatitis C/therapy* ; Health Knowledge, Attitudes, Practice ; Surveys and Questionnaires ; Sex Workers/psychology* ; Homosexuality, Male ; Female ; Adult ; China ; Young Adult ; Middle Aged ; Logistic Models

The research and development of new traditional Chinese medicine (TCM) drugs have progressively established a novel system founded on the integration of TCM theory, human experience, and clinical trials (termed the "Three Combinations"). However, considering TCM's distinctive features of "syndrome differentiation and treatment" and "multicomponent formulations and complex mechanisms", current TCM drug development faces challenges such as insufficient understanding of the material basis and the overall mechanism of action and an incomplete evidence chain system. Moreover, significant obstacles persist in gathering human experience data, evaluating clinical efficacy, and controlling the quality of active ingredients, which impede the innovation process in TCM drug development. Network pharmacology, centered on the "network targets" theory, transcends the limitations of the conventional "single target" reductionist research model. It emphasizes the comprehensive effects of disease or syndrome biological networks as targets to elucidate the overall regulatory mechanism of TCM prescriptions. This approach aligns with the holistic perspective of TCM, offering a novel method consistent with TCM's holistic view for investigating the complex mechanisms of TCM and developing new TCM drugs. It is internationally recognized as a "next-generation drug research model". To advance the research of new tools, methods, and standards for TCM evaluation and to overcome fundamental, critical, and cutting-edge technical challenges in TCM regulation, this consensus aims to explore the characteristics, progress, challenges, applicable pathways, and specific applications of network pharmacology as a new theory, method, and tool in TCM drug development. The goal is to enhance the quality of TCM drug research and development and accelerate the efficiency of developing new TCM products.
Humans ; Consensus ; Drug Development/standards* ; Drugs, Chinese Herbal/chemistry* ; Medicine, Chinese Traditional ; Network Pharmacology/standards* ; Guidelines as Topic

Drug development remains a critical issue in the field of biomedicine.With the rapid advancement of information technologies such as artificial intelligence(AI)and the advent of the big data era,AI-assisted drug development has become a new trend,particularly in predicting drug-target associations.To address the challenge of drug-target prediction,AI-driven models have emerged as powerful tools,of-fering innovative solutions by effectively extracting features from complex biological data,accurately modeling molecular interactions,and precisely predicting potential drug-target outcomes.Traditional machine learning(ML),network-based,and advanced deep learning architectures such as convolutional neural networks(CNNs),graph convolutional networks(GCNs),and transformers play a pivotal role.This review systematically compiles and evaluates AI algorithms for drug-and drug combination-target predictions,highlighting their theoretical frameworks,strengths,and limitations.CNNs effectively identify spatial patterns and molecular features critical for drug-target interactions.GCNs provide deep insights into molecular interactions via relational data,whereas transformers increase prediction accu-racy by capturing complex dependencies within biological sequences.Network-based models offer a systematic perspective by integrating diverse data sources,and traditional ML efficiently handles large datasets to improve overall predictive accuracy.Collectively,these AI-driven methods are transforming drug-target predictions and advancing the development of personalized therapy.This review summa-rizes the application of AI in drug development,particularly in drug-target prediction,and offers rec-ommendations on models and algorithms for researchers engaged in biomedical research.It also provides typical cases to better illustrate how AI can further accelerate development in the fields of biomedicine and drug discovery.

Objective:To investigate the effects of pulsed electric field (PEF) combined with gemcitabine (GEM) on the viability and stemness of HCCC-9810 cholangiocarcinoma stem cells.Methods:HCCC-9810 cholangiocarcinoma stem cells were established in serum-free, cytokine-rich medium and divided into four groups: the control group, GEM group, PEF group, and the pulsed electric field combined with gemcitabine (PEF+ GEM) group. Cell proliferation was detected using the Cell Counting Kit-8 (CCK8) assay. Cell viability and apoptosis rate were measured by flow cytometry. Cell invasion ability was assessed using the Transwell assay. The expression of stemness marker proteins CD133 and Octamer-binding transcription factor 4 (OCT4), as well as the expression of β-catenin, was detected by Western blotting.Results:Regarding cell viability, the GEM, PEF, and PEF+ GEM groups showed significantly lower cell viability and higher apoptosis rate than the control group at 24 h, 48 h, and 72 h (all P<0.05). At 48 h and 72 h, the PEF+ GEM group showed significantly lower cell viability (7.2%±0.3% and 5.9%±0.8%, respectively) than the GEM group (50.7%±0.6% and 31.0%±1.2%, respectively) and the PEF group (12.2%±0.2% and 12.8%±0.2%, respectively) (all P<0.05). Regarding stemness inhibition, the PEF+ GEM groups showed significantly lower expression levels of CD133 and OCT4 at 24 h, 48 h, and 72 h compared with the control group (all P<0.05). Notably, at 48 h, the PEF+ GEM group showed a significantly lower expression level of the OCT4 (0.61±0.02) than the GEM group (0.87±0.08) and the PEF group (1.00±0.10) ( P<0.01). Furthermore, at 24 h and 48 h, the GEM, PEF, and PEF+ GEM groups showed significantly lower expression levels of β-catenin compared with the control group (all P<0.05). Conclusion:Pulsed electric field combined with gemcitabine therapy demonstrated more effective anti-proliferation and cancer stemness inhibition effects on HCCC-9810 cholangiocarcinoma stem cells compared with either monotherapy.

Traditional Chinese medicine (TCM) is characterized by complex, multicomponent herbal formulations that challenge the conventional“one drug, one target” paradigm. Network pharmacology, through the construction of multilayered drug-target-disease networks, provides a systematic framework for unraveling TCM’s multitarget and multipathway mechanisms. Recent advancements in artificial intelligence, particularly large language models (LLMs), further enhance data integration, target identification, and clinical decision-making. This review synthesizes current progress in the application of network pharmacology and LLMs in TCM, highlighting their potential to deepen mechanistic insights and optimize drug discovery. By bridging traditional medical wisdom with modern computational tools, this integrative approach aims to advance the scientific validation of TCM and foster innovative healthcare solutions.

Biomolecular condensates are formed through phase separation of biomacromolecules such as proteins and RNAs. These condensates exhibit liquid-like properties that can futher transition into more stable material states. They form complex internal structures via multivalent weak interactions, enabling precise spatiotemporal regulations. However, the use of inconsistent and non-standardized terminology has become increasingly problematic, hindering academic exchange and the dissemination of scientific knowledge. Therefore, it is necessary to discuss the terminology related to biomolecular condensates in order to clarify concepts, promote interdisciplinary cooperation, enhance research efficiency, and support the healthy development of this field.