Periodontitis is a globally prevalent inflammatory oral disease, affecting approximately 50% of the population worldwide and imposing a substantial burden on patients′ health and quality of life. Early and accurate diagnosis is critical for preventing disease progression; however, conventional diagnostic approaches often rely on subjective clinical assessments, which only primarily evaluate the cumulative state of the disease, thus limiting their ability to achieve precise early detection. In recent years, the rapid advancement of artificial intelligence (AI) in medical diagnostics has demonstrated significant promise, particularly through the integration of multimodal data to enable more comprehensive information capture and analysis. Multimodal data fusion, which combines diverse inputs such as imaging, clinical parameters, and biomarkers, offers transformative potential for AI-powered periodontitis diagnostics. This innovative approach aims to overcome the limitations of traditional methods, significantly enhancing diagnostic accuracy and predictive capabilities. This manuscript reviews the primary diagnostic techniques for periodontitis, explores recent advances in AI applications within this domain, and emphasizes the potential of multimodal data in facilitating precision diagnosis. Furthermore, it provides new insights and supports for personalized treatment strategies.

Viral myocarditis is a myocardial disease resulting from various viral infections.Due to the com-plexity of its pathogenesis,effective prevention and treatment options are currently lacking.Establishing appropriate ex-perimental models is crucial for studying the pathogenic mechanisms,disease progression,early diagnosis,and the devel-opment of new drugs and therapies for viral myocarditis.This article reviews the construction methods,research advance-ments,and applications of common experimental models of viral myocarditis,which range from cell models to small ani-mal models,including mice,hamsters,and rabbits,as well as larger animals such as pigs and non-human primates.Ad-ditionally,we summarize and discuss future research directions,providing a theoretical foundation and technological guid-ance for the prevention and treatment of viral myocarditis in clinical settings.

Objective To investigate the association between baseline depression and the risk of type 2 diabetes mellitus(T2DM)in middle-aged and elderly people in Chengguan District of Lanzhou.Methods A total of 4471 residents who were followed up in Chengguan District,Lanzhou City from August 2014 to July 2016 in the 2011 REACTION study were selected as the research subjects.According to the 9-item patient health questionnaire(PHQ-9),they were divided into the non-depression group with a score of 0～4 points(ND,n=3827),the mild depression group with a score of 5～10 points(MD,n=546)and the moderate to severe depression group with a score of≥10 points(MSD,n=98).The general data and biochemical indicators of the three groups were compared.The correlation between depression status and glycolipid metabolism indicators was analyzed.The follow-up results of the three groups with different baseline glucose metabolism status populations were compared.Logistic regression was used to analyze the influencing factors of progression in different glucose metabolism populations.Results The married rate in the ND,MD and MSD groups decreased sequentially(P<0.05),while the rate of living alone and the PHQ-9 score increased(P<0.05).The female population,family history of DM,coronary heart disease,LDL-C and TC in the MD group were higher than those in the ND group(P<0.05),while the age,BMI,WHR,FPG and 2 hPG in the MD group were lower than those in the ND group(P<0.05).The family history of DM in the MSD group was higher than those in the ND group(P<0.05),drinking and LDL-C in the MSD group were higher than those in the MD group(P<0.05),the BMI was lower than that in the ND group(P<0.05).Spearman correlation analysis showed that the baseline PHQ-9 score was negatively correlated with FPG level(r=-0.039,P<0.05),and positively correlated with HDL-C and TC(r=0.049,0.031,P<0.05).There was no significant difference in the incidence of pre-DM and T2DM at the end of follow-up among the three groups with different baseline glucose metabolism(P>0.05).Logistic regression analysis showed that after adjusting for confounding factors,the risk of pre-DM and T2DM in normal glucose tolerance people with different depression status and the risk of T2DM in pre-DM patients were not increased.Conclusions Depressive state may not be the main factor affecting the occurrence of T2DM in middle-aged and elderly people in Chengguan District of Lanzhou.

Viral myocarditis is a myocardial disease resulting from various viral infections.Due to the com-plexity of its pathogenesis,effective prevention and treatment options are currently lacking.Establishing appropriate ex-perimental models is crucial for studying the pathogenic mechanisms,disease progression,early diagnosis,and the devel-opment of new drugs and therapies for viral myocarditis.This article reviews the construction methods,research advance-ments,and applications of common experimental models of viral myocarditis,which range from cell models to small ani-mal models,including mice,hamsters,and rabbits,as well as larger animals such as pigs and non-human primates.Ad-ditionally,we summarize and discuss future research directions,providing a theoretical foundation and technological guid-ance for the prevention and treatment of viral myocarditis in clinical settings.

Clinical pharmacist teacher training is an important mean to improve the quality of clinical pharmacy talent cultivation and ensure the service ability and level of the clinical pharmacist team.The Pharmacy Administration and Pharmacy Practice in Healthcare Institutions-Part 4-8-2:Pharmacy Administration-Pharmacy Training Management-Clinical Pharmacist Teacher Training was based on the newly revised management document for clinical pharmacist teacher training of the Chinese Hospital Association.After sorting out relevant materials,such as standards,policies and regulations,technical specifications,liter-ature,documents of the Chinese Hospital Association,expert opinions,and the current situation of clinical pharmacist teacher training in China,the standard was formulated.In the standard,12 key elements,which can be divided into 3 parts of base manage-ment,training process and assessment,quality management and evaluation improvement,were standardized.This article aimed to introduce the construction method and content of the standard,to facilitate the understanding of the standard content for medical institutions which joined or willing to join the clinical pharmacist teacher training base,and to provide a reference for other medi-cal institutions to carry out related work.

Objective:This study aims to systematically review the current evaluation paradigms of conversational AI in healthcare and provide insights to facilitate the development of a comprehensive evaluation framework and methodological advancements in this field.Methods:A systematic review was conducted by searching the PubMed and Web of Science databases to analyze the existing evaluation paradigms of healthcare conversational AI,including evaluation subjects,assessment metrics,and evaluation methodologies.Results:A total of 60 studies were included in this review.The findings indicate that most evaluation subjects focus on general-purpose large language models.The assessment metrics cover five key dimensions:technical performance,information quality,clinical effectiveness,user experience,and ethics and safety.However,there were significant differences in the evaluation criteria used in existing studies.There were also issues such as a low degree of alignment between the evaluation questions and the application scenarios,as well as a lack of diversity in the roles of the evaluators.Conclusions:The current evaluation framework for healthcare conversational AI remains underdeveloped.Future improvements should focus on broadening model coverage,enhancing the comprehensiveness of evaluation indicators,standardizing evaluation methods,improving the operationalizability of test content,and expanding the scalability of evaluation languages.

Objective:This study aims to systematically review the current evaluation paradigms of conversational AI in healthcare and provide insights to facilitate the development of a comprehensive evaluation framework and methodological advancements in this field.Methods:A systematic review was conducted by searching the PubMed and Web of Science databases to analyze the existing evaluation paradigms of healthcare conversational AI,including evaluation subjects,assessment metrics,and evaluation methodologies.Results:A total of 60 studies were included in this review.The findings indicate that most evaluation subjects focus on general-purpose large language models.The assessment metrics cover five key dimensions:technical performance,information quality,clinical effectiveness,user experience,and ethics and safety.However,there were significant differences in the evaluation criteria used in existing studies.There were also issues such as a low degree of alignment between the evaluation questions and the application scenarios,as well as a lack of diversity in the roles of the evaluators.Conclusions:The current evaluation framework for healthcare conversational AI remains underdeveloped.Future improvements should focus on broadening model coverage,enhancing the comprehensiveness of evaluation indicators,standardizing evaluation methods,improving the operationalizability of test content,and expanding the scalability of evaluation languages.

This study developed a core outcome set(COS) for traditional Chinese medicine(TCM) interventions in diabetic peripheral neuropathy(DPN), standardizing evaluation metrics for TCM efficacy and providing a new framework for DPN treatment and management. A systematic search was conducted across databases, including CNKI, Wanfang, and PubMed, targeting clinical trial literature published between January 1, 2013, and January 1, 2023. The search focused on extracting outcome indicators and measurement tools used in TCM treatments for DPN. Retrospective data collection was performed from January 2018 to June 2023, involving 200 DPN patients hospitalized at the Department of Endocrinology of the First Affiliated Hospital of Anhui University of Chinese Medicine. Additionally, semi-structured interviews were conducted with inpatients, outpatients, their families, and nursing staff to further refine and enhance the list of outcome indicators. After two rounds of Delphi questionnaire survey and consensus meeting, a consensus was reached. The study initially retrieved 3 421 publications, of which 170 met the inclusion criteria after review. These publications, combined with retrospective analysis and semi-structured interviews, supplemented the list of indicators. After two rounds of Delphi surveys, experts agreed on 24 indicators and 6 measurement tools. The final COS determined by expert consensus meeting included 5 domains and 13 outcome indicators: neurological function signs, quality of life, TCM syndrome score, nerve conduction velocity, current perception threshold test, fasting blood glucose, 2 h postprandial blood glucose, glycated hemoglobin, complete blood count, urinalysis, liver function test, kidney function test, and electrocardiogram.
Humans ; Diabetic Neuropathies/drug therapy* ; Medicine, Chinese Traditional/methods* ; Drugs, Chinese Herbal/therapeutic use* ; Retrospective Studies ; Treatment Outcome ; Male ; Female

Periodontitis is a globally prevalent inflammatory oral disease, affecting approximately 50% of the population worldwide and imposing a substantial burden on patients′ health and quality of life. Early and accurate diagnosis is critical for preventing disease progression; however, conventional diagnostic approaches often rely on subjective clinical assessments, which only primarily evaluate the cumulative state of the disease, thus limiting their ability to achieve precise early detection. In recent years, the rapid advancement of artificial intelligence (AI) in medical diagnostics has demonstrated significant promise, particularly through the integration of multimodal data to enable more comprehensive information capture and analysis. Multimodal data fusion, which combines diverse inputs such as imaging, clinical parameters, and biomarkers, offers transformative potential for AI-powered periodontitis diagnostics. This innovative approach aims to overcome the limitations of traditional methods, significantly enhancing diagnostic accuracy and predictive capabilities. This manuscript reviews the primary diagnostic techniques for periodontitis, explores recent advances in AI applications within this domain, and emphasizes the potential of multimodal data in facilitating precision diagnosis. Furthermore, it provides new insights and supports for personalized treatment strategies.

AIM To establish the quantitative models for gallic acid,mononucleoside,loganin,resveratrol,and rhein in Yishen Xiezhuo Mixture.METHODS HPLC was adopted in the content determination of various effective components,after which the near-infrared spectroscopy(NIRS)data were collected in 128 batches of samples and pretreatment was conducted,competitive adaptive reweighting sampling(CARS)algorithm was used for screening wavelength,partial least square method(PLS)regression analysis was performed.RESULTS There were no significant differences between the predicted values obtained by PLS models and measured values obtained by HPLC for various effective components(P＞0.05).CONCLUSION The quantitative models established by NIRS combined with chemometrics display good predictive performance,which can be used for the rapid determination of effective components in Yishen Xiezhuo Mixture,and provide a reference for the rapid monitoring of other traditional Chinese medicine preparations in production processes.