BACKGROUND:In recent years,deep learning technologies have been increasingly applied in the field of oral medicine,enhancing the efficiency and accuracy of oral imaging analysis and promoting the rapid development of intelligent oral medicine. OBJECTIVE:To elaborate the current research status,advantages,and limitations of deep learning based on oral imaging in the diagnosis and treatment decision-making of oral diseases,as well as future prospects,exploring new directions for the transformation of oral medicine under the backdrop of deep learning technology. METHODS:PubMed was searched for literature related to deep learning in oral medical imaging published from January 2017 to January 2024 with the search terms"deep learning,artificial intelligence,stomatology,oral medical imaging."According to the inclusion criteria,80 papers were finally included for review. RESULTS AND CONCLUSION:(1)Classic deep learning models include artificial neural networks,convolutional neural networks,recurrent neural networks,and generative adversarial networks.Scholars have used these models in competitive or cooperative forms to achieve more efficient interpretation of oral medical images.(2)In the field of oral medicine,the diagnosis of diseases and the formulation of treatment plans largely depend on the interpretation of medical imaging data.Deep learning technology,with its strong image processing capabilities,aids in the diagnosis of diseases such as dental caries,periapical periodontitis,vertical root fractures,periodontal disease,and jaw cysts,as well as preoperative assessments for procedures such as third molar extraction and cervical lymph node dissection,helping clinicians improve the accuracy and efficiency of decision-making.(3)Although deep learning is promising as an important auxiliary tool for the diagnosis and treatment of oral diseases,it still has certain limitations in model technology,safety ethics,and legal regulation.Future research should focus on demonstrating the scalability,robustness,and clinical practicality of deep learning,and finding the best way to integrate automated deep learning decision support systems into routine clinical workflows.

ObjectiveTo elucidate the critical role of rehabilitation medical records (including electronic records) in rehabilitation medicine's clinical practice and management, comprehensively analyzed the structure, core content and data standards of rehabilitation medical records, to develop a standardized medical record data architecture and core dataset suitable for rehabilitation medicine and to explore the application of rehabilitation data in performance evaluation and payment. MethodsBased on the regulatory documents Basic Specifications for Medical Record Writing and Basic Specifications for Electronic Medical Records (Trial) issued by National Health Commission of China, and referencing the World Health Organization (WHO) Family of International Classifications (WHO-FICs) classifications, International Classification of Diseases (ICD-10/ICD-11), International Classification of Functioning, Disability and Health (ICF), and International Classification of Health Interventions (ICHI Beta-3), this study constructed the data architecture, core content and data standards for rehabilitation medical records. Furthermore, it explored the application of rehabilitation record summary sheets (home page) data in rehabilitation medical statistics and payment methods, including Diagnosis-related Groups (DRG), Diagnosis-Intervention Packet (DIP) and Case Mix Index. ResultsThis study proposed a systematic standard framework for rehabilitation medical records, covering key components such as patient demographics, rehabilitation diagnosis, functional assessment, rehabilitation treatment prescriptions, progress evaluations and discharge summaries. The research analyzed the systematic application methods and data standards of ICD-10/ICD-11, ICF and ICHI Beta-3 in the fields of medical record terminology, coding and assessment. Constructing a standardized data structure and data standards for rehabilitation medical records can significantly improve the quality of data reporting based on the medical record summary sheet, thereby enhancing the quality control of rehabilitation services, effectively supporting the optimization of rehabilitation medical insurance payment mechanisms, and contributing to the establishment of rehabilitation medical performance evaluation and payment based on DRG and DIP. ConclusionStructured rehabilitation records and data standardization are crucial tools for quality control in rehabilitation. Systematically applying the three reference classifications of the WHO-FICs, and aligning with national medical record and electronic health record specifications, facilitate the development of a standardized rehabilitation record architecture and core dataset. Standardizing rehabilitation care pathways based on the ICF methodology, and developing ICF- and ICD-11-based rehabilitation assessment tools, auxiliary diagnostic and therapeutic systems, and supporting terminology and coding systems, can effectively enhance the quality of rehabilitation records and enable interoperability and sharing of rehabilitation data with other medical data, ultimately improving the quality and safety of rehabilitation services.

ObjectiveTo explore the data standard system of electronic medical records in the field of rehabilitation, focusing on the terminology and coding standards, data structure, and key content categories of rehabilitation electronic medical records. MethodsBased on the Administrative Norms for the Application of Electronic Medical Records issued by the National Health Commission of China, the electronic medical record standard architecture issued by the International Organization for Standardization and Health Level Seven (HL7), the framework of the World Health Organization Family of International Classifications (WHO-FICs), Basic Architecture and Data Standards of Electronic Medical Records, Basic Data Set of Electronic Medical Records, and Specifications for Sharing Documents of Electronic Medical Records, the study constructed and organized the data structure, content, and data standards of rehabilitation electronic medical records. ResultsThe data structure of rehabilitation electronic medical records should strictly follow the structure of electronic medical records, including four levels (clinical document, document section, data set and data element) and four major content areas (basic information, diagnostic information, intervention information and cost information). Rehabilitation electronic medical records further integrated information related to rehabilitation needs and characteristics, emphasizing rehabilitation treatment, into clinical information. By fully applying the WHO-FICs reference classifications, rehabilitation electronic medical records could establish a standardized framework, diagnostic criteria, functional description tools, coding tools and terminology index tools for the coding, indexing, functional description, and analysis and interpretation of diseases and health problems. The study elaborated on the data structure and content categories of rehabilitation electronic medical records in four major categories, refined the granularity of reporting rehabilitation content in electronic medical records, and provided detailed data reporting guidance for rehabilitation electronic medical records. ConclusionThe standardization of rehabilitation electronic medical records is significant for improving the quality of rehabilitation medical services and promoting the rehabilitation process of patients. The development of rehabilitation electronic medical records must be based on the national and international standards. Under the general electronic medical records data structure and standards, a rehabilitation electronic medical records data system should be constructed which incorporates core data such as disease diagnosis, functional description and assessment, and rehabilitation interventions. The standardized rehabilitation electronic medical records scheme constructed in this study can support the improvement of standardization of rehabilitation electronic medical records data information.

ObjectiveTo analyze the data structure and standards of rehabilitation outpatient medical records, to provide data support for improving the quality of rehabilitation outpatient care and developing medical insurance payment policies. MethodsBased on the normative documents issued by the National Health Commission, Basic Standards for Medical Record Writing and Standards for Electronic Medical Record Sharing Documents, in accordance with the Quality Management Regulations for Outpatient (Emergency) Diagnosis and Treatment Information Pages (Trial), reference to the framework of the World Health Organization Family of International Classifications (WHO-FICs), the data framework and content of rehabilitation outpatient medical records were determined, and the data standards were discussed. ResultsThis study constructed a data framework for rehabilitation outpatient medical records, including four main components: patient basic information, visit process information, diagnosis and treatment information, and cost information. Three major reference classifications of WHO-FICs, International Classification of Diseases, International Classification of Functioning, Disability and Health, and International Classification of Health Interventions,were used to establish diagnostic standards and standardized terminology, as well as coding disease diagnosis, functional description, functional assessment, and rehabilitation interventions, to improve the quality of data reporting, and level of quality control in rehabilitation. ConclusionThe structuring and standardization of rehabilitation outpatient medical records are the foundation for sharing of rehabilitation data. The using of the three major classifications of WHO-FICs is valuable for the terminology and coding of disease diagnosis, functional description and assessment, and intervention in rehabilitation outpatient medical records, which is significant for sharing and interconnectivity of rehabilitation outpatient data, as well as for optimizing the quality and safety of rehabilitation medical services.

ObjectiveTo explore the standardization of inpatient rehabilitation medical record summary sheet, encompassing its structure, content and data standards, to enhance the standardization level of inpatient rehabilitation medical record summary sheet, improve data reporting quality, and provide accurate data support for medical insurance payment, hospital performance evaluation, and rehabilitation discipline evaluation. MethodsBased on the relevant specifications of the National Health Commission's Basic Norms for Medical Record Writing, Specifications for Sharing Documents of Electronic Medical Records, and Quality Management and Control Indicators for Inpatient Medical Record Summary Sheet (2016 Edition), this study analyzed the structure and content of the inpatient rehabilitation medical record summary sheet. The study systematically applied the three major reference classifications of the World Health Organization Family of International Classifications, International Classification of Diseases (ICD-10/ICD-11, ICD-9-CM-3), International Classification of Functioning, Disability and Health (ICF), and International Classification of Health Interventions (ICHI Beta-3), for disease diagnosis, functional description and assessment, and rehabilitation intervention, forming a standardized terminology system and coding methods. ResultsThe inpatient rehabilitation medical record summary sheet covered four major sections: inpatient information, hospitalization information, diagnosis and treatment information, and cost information. ICD-10/ICD-11 were the standards and coding tools for admission and discharge diagnoses in the inpatient rehabilitation medical record summary sheet. The three functional assessment tools recommended by ICD-11, the 36-item version of World Health Organization Disability Assessment Schedule 2.0, Brief Model Disability Survey and Generic Functioning domains, as well as ICF, were used for rehabilitation functioning assessment and the coding of outcomes. ICHI Beta-3 and ICD-9-CM-3 were used for coding surgical procedures and operations in the medical record summary sheet, and also for coding rehabilitation intervention items. ConclusionThe inpatient rehabilitation medical record summary sheet is a summary of the relevant content of the rehabilitation medical record and a tool for reporting inpatient rehabilitation data. It needs to be refined and optimized according to the characteristics of rehabilitation, with necessary data supplemented. The application of ICD-11/ICD-10, ICF and ICHI Beta-3/ICD-9-CM-3 classification standards would comprehensively promote the accuracy of inpatient diagnosis of diseases and functions. Based on ICD-11 and ICF, relevant functional assessment result data would be added, and ICHI Beta-3/ICD-9-CM-3 should be used to code rehabilitation interventions. Improving the quality of rehabilitation medical records and inpatient rehabilitation medical record summary sheet is an important part of rehabilitation quality control, and also lays an evidence-based data foundation for the analysis and application of inpatient rehabilitation medical record summary sheet.

Objective To analyze the current status of occupational stress among primary and secondary school teachers, and explore the dose-response relationship between weekly work hours and occupational stress. Methods A total of 1 252 teachers from 13 primary and secondary schools in three prefecture-level cities of a central province of China were selected as the research subjects by the convenience sampling method. The Core Occupational Stress Scale was used to assess occupational stress levels of the teachers. Multivariate logistic regression analysis combined with restricted cubic spline models was applied to study the dose-response relationship between weekly work hours and occupational stress. Results The average weekly work hours were (55.3±15.9) hours, with 78.6% of teachers working more than 40.0 hours per week. The total score of occupational stress was (40.3±8.2) points, and the detection rate of occupational stress was 29.8%. Multivariate logistic regression analysis combined with restricted cubic spline models revealed a linear dose-response relationship in weekly work hours and occupational stress among teachers (P for overall trend <0.05, P for nonlinearity was 0.22). Result of age-stratified analysis showed that weekly work hours had a linear dose-response relationship with occupational stress risk in teachers aged 21-<31 and 31-<46 years (P for overall trend <0.05, P for nonlinearity was 0.71 and 0.27, respectively). However, no association was found between weekly work hours and occupational stress risk among teachers aged ≥46 years (P for overall trend =0.08, P for nonlinearity was 0.09). Conclusion There is a linear dose-response relationship between weekly work hours and occupational stress among primary and secondary school teachers in the province, with younger teachers being more susceptible to suffer occupational stress due to long working hours.

Objective:To compare the clinical efficacy and safety of bronchial artery chemoembolization (BACE) combined with anlotinib (BACE+A) versus BACE alone in patients with stage III-IV non-small cell lung cancer (NSCLC).Methods:A total of 94 patients with advanced NSCLC treated at six interventional centers between November 2020 and November 2021 were retrospectively enrolled. Patients were divided into the BACE+A group ( n=46) and the BACE alone group ( n=48) based on treatment regimen. Baseline and perioperative clinical data were collected and compared between the two groups. Treatment response was evaluated using the modified Response Evaluation Criteria in Solid Tumors (mRECIST) at 1, 6, and 12 months after the first BACE procedure. Objective response rate (ORR), disease control rate (DCR), progression-free survival (PFS), overall survival (OS), and treatment-related adverse events (AEs) were recorded. Kaplan-Meier survival curves were plotted to compare median OS and PFS between groups. Cox proportional hazards regression analysis was used to identify factors influencing OS and PFS. Results:The Kaplan-Meier analysis showed that the median OS was significantly longer in the BACE+A group (18.8 months, 95% CI 16.3-21.3) than in the BACE group (13.4 months, 95% CI 11.6-15.2) ( P=0.001). The median PFS was also significantly longer in the BACE+A group (9.0 months, 95% CI 7.3-10.7) compared to the BACE group (6.1 months, 95% CI 4.9-7.3) ( P=0.001). At 6 and 12 months post-first BACE, the ORR (43.5%, 40.0%) and DCR (89.1%, 83.3%) were significantly higher in the BACE+A group than in the BACE group (ORR: 20.8%, 14.8%; DCR: 66.7%, 59.3%) (all P<0.05). Multivariate Cox regression identified treatment with BACE+A ( HR=0.42, 95% CI 0.27-0.72, P=0.002), tumor stage ( HR=1.80, 95% CI 1.05-3.07, P=0.031), presence of pre-existing complications requiring intervention ( HR=2.72, 95% CI 1.65-4.50, P<0.001), and >2 BACE procedures ( HR=0.32, 95% CI 0.15-0.68, P=0.003) as independent factors influencing OS. Treatment with BACE+A ( HR=0.49, 95% CI 0.32-0.76, P=0.001), tumor stage ( HR=1.72, 95% CI 1.07-2.77, P=0.025), multi-arterial tumor blood supply ( HR=2.76, 95% CI 1.76-4.31, P<0.001), and>2 BACE procedures ( HR=0.40, 95% CI 0.22-0.71, P=0.002) were independent factors influencing PFS. There was no significant difference in BACE-related adverse events between the two groups (all P>0.05). Hypertension, fatigue, hand-foot syndrome, and anorexia were common anlotinib-specific adverse reactions in the combination group, but no grade 4 or higher adverse reactions were observed. Conclusions:BACE combined with anlotinib demonstrates superior efficacy compared to BACE alone in treating advanced NSCLC, significantly prolonging OS and PFS. The safety profile is manageable, with adverse events remaining within tolerable limits.

Objective To evaluate the rehabilitative effect of targeted sonic vibration load brushing method in stroke patients with oral phase swallowing disorders.Methods A total of 60 stroke patients with swallowing disor-ders,who hospitalized in the rehabilitation department of a Grade Ⅲ Class A hospital in Nanjing City from October 2023 to May 2024,were randomly assigned to an experimental group and a control group,with 30 patients in each group.Both groups received the conventional swallowing function training.The experimental group received targeted sonic vibration load brushing therapy,while the control group received routine oral care with manual toothbrushes.After 30 days of intervention,the swallowing function(Gugging Swallowing Screen,GUSS),modified Beck oral score,incidence of swallowing disorder-related complications,Swallowing Quality of Life(SWAL-QOL)scores,and oral care satisfaction were assessed in both groups.Results No sample detachment.After the intervention,the GUSS score for the experimental group was significantly higher than that of the control group,with a statistical difference(Z=-4.239,P＜0.001).Additionally,the modified Beck oral score and the overall complications rate related to swallowing disor-ders in the experimental group were significantly lower than those in the control group(both P＜0.05).Furthermore,the SWAL-QOL score and the oral care satisfaction score were both higher in the experimental group compared to those in the control group,with statistically significant differences(both P＜0.001).Conclusion Targeted sonic vibration load brushing method significantly improves swallowing function,enhances oral cleanliness,reduces the occurrence of swallowing disorder-related complications,and effectively improves patients' quality of life and nursing satisfaction.

Japanese encephalitis virus(JEV)usually evades the inhibitory effect of the innate immunity factor type Ⅰ interferon(Ⅰ-IFN)when it infects human cells and tissues.The virus then causes a series of serious symptoms,such as spasticity,neurodegenerative lesions,neuroinflammation,and even death.Generally,JEV escapes innate immunity by inhibiting IFN-α/β production and the interferon Janus kinase-signal transducer and activator of transcription signaling pathway.Because of this special immune escape mechanism,various mouse infection models have been constructed for the study of the pathogenesis of and therapeutic regimens for JEV infections.In this review,based on an exposition of the IFN immune escape mechanism of JEV,we systematically introduce the concept of JEV-infected mouse models and analyze the characteristics of these models and the degree to which they simulate human symptoms.The intention is to develop various new JEV-infected mouse models based on potential new research targets and provide novel ideas for animal models for JEV research.

Objective:To observe the changes of small airway parameters in patients with coal workers' pneumoconiosis in different disease stages by high resolution computed tomography (HRCT) , and analyze the correlation between them and the severity of the disease.Methods:From June 2016 to June 2023, 25 healthy volunteers and 71 untreated patients with coal worker's pneumoconiosis in the Fifth People's Hospital of Ningxia were selected as the research objects. The clinical and imaging data of the patients were collected, and the disease stages were performed according to the dust exposure history and high-kilovolt chest X-ray. The patients were divided into 4 groups: control group (25 cases) , coal workers' pneumoconiosis stage Ⅰ group (17 cases) , coal workers' pneumoconiosis stage Ⅱ group (32 cases) and coal workers' pneumoconiosis stage Ⅲ group (22 cases) . Quantitative chest HRCT parameters of each group were collected, including the square root of wall area at 10 mm inner perimeter (AWT-Pi10, Pi10) , airway wall thickness, airway wall volume, airway wall area percentage of the whole lung and the 5th, 6th, 7th and 8th level airways, and low attenuation area percentage (LAA%) of the whole lung. Pulmonary function indicators were collected, including forced expiratory volume in 1 second (FEV 1) and the percentage of its projected value [FEV 1 (%pred) ], the ratio of FEV 1 to forced vital capacity (FEV 1/FVC) and the percentage of its projected value[FEV 1/FVC (%pred) ]. One-way ANOVA or Kruskal-Wallis H test and Spearman rank correlation were used to analyze the difference and correlation. Results:Compared with control group, FEV 1, FEV 1 (%pred) , FEV 1/FVC and FEV 1/FVC (%pred) in stage Ⅱ and Ⅲ coal workers' pneumoconiosis groups were lower ( P<0.05) . In addition, the FEV 1 and FEV 1 (%pred) of the stage Ⅲgroup were lower than those of the stageⅡ group ( P<0.05) , and the FEV 1/FVC and FEV 1/FVC (%pred) of the stage Ⅲgroup were lower than those of the stage Ⅰgroup ( P<0.05) . Compared with stage Ⅰ group, Pi10 in stage Ⅲ group were increased ( P < 0.05) at the 6th and 8th level airways, and airway wall thickness and airway wall volume in the 6th, 7th and 8th level airways of stage Ⅲgroup increased ( P<0.05) . Correlation analysis showed that all pulmonary function indexes were negatively correlated with Pi10 of whole lung and the 6th, 7th and 8th level airways ( P<0.05) , all pulmonary function indexes were negatively correlated with airway wall thickness of the 7th and 8th level airways ( P<0.05) , and FEV 1/FVC (%pred) was negatively correlated with airway wall volume of the 7th and 8th level airways ( P<0.05) . FEV 1, FEV 1 (%pred) , FEV 1/FVC (%pred) were negatively correlated with percentage of airway wall area of whole lung and the 6th, 7th and 8th level airways ( P<0.05) . Conclusion:The quantitative airway parameters of coal workers' pneumoconiosis based on HRCT are correlated with pulmonary function indexes, which can reflect the severity of coal workers' pneumoconiosis.