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.

Objective:To compare the clinical characteristics of patients with drug-induced liver injury (DILI) caused by Polygonum multiflorum and other drug-induced liver injuries (DILI).Methods:A retrospective cohort study was conducted. Clinical data of seventy-three cases confirmedly diagnosed with DILI caused by Polygonum multiflorum, 168 cases diagnosed with DILI caused by other traditional Chinese medicines, and 225 cases diagnosed with DILI caused by modern medicines admitted to Peking University First Hospital, the Fipth People's Hospital of Wuxi, Yantai Qishan Hospital, and Qinhuangdao Third Hospital from January 1995 to August 2019 were selected and collected as the research subjects. The Mann-Whitney U test was used for comparison of skewed distribution of continuous data between two groups. The Kruskal-Wallis rank-sum test was used for comparison between three groups. The χ2 test was used for comparing count data between groups. Results:Among the 73 cases with DILI caused by Polygonum multiflorum, 11 (15.1%) took a single herb of Polygonum multiflorum (including its powder and boiled water), 37 (50.7%) took traditional Chinese patent medicines containing Polygonum multiflorum, and 25 (34.2%) took a traditional Chinese medicine formula containing Polygonum multiflorum. The age of the DILI group caused by Polygonum multiflorum was 48 years old, which was lower than the other two groups (the DILI group caused by other traditional Chinese medicines: 55 years old, the DILI group caused by modern medicines: 52 years old; P<0.01). The levels of alanine aminotransferase (ALT), aspartate aminotransferase, and alkaline phosphatase were all higher than the other two groups ( P<0.05). The proportion of patients with antinuclear antibody positivity rate and severity of liver damage grade 3 was higher in the DILI group induced by Polygonum multiflorum than those in the modern drug-induced DILI group ( P<0.05). The liver cell injury type accounted for 96.6% (57/59) in the DILI group caused by Polygonum multiflorum, which was higher than that in the modern drug-induced DILI group (69.3%, 156/225) ( P<0.001). There was no statistically significant difference ( P>0.05) in gender, age, medication duration, and various biochemical indicators between patients with DILI caused by Polygonum multiflorum monotherapy and compound preparations in terms of compatibility. The ALT level in the DILI group caused by raw Polygonum multiflorum was higher than that in the DILI group caused by processed Polygonum multiflorum [the DILI group caused by raw Polygonum multiflorum: 1 289.0(921.8, 1 851.8)U/L, the DILI group caused by processed Polygonum multiflorum: 890.0(304.0,1 320.0)U/L; P<0.05] according to the comparison of processing methods. Conclusion:The degree of DILI caused by Polygonum multiflorum is more obvious than that caused by other drugs. There was no difference in the degree of DILI caused by the single and the compound formulation. However, the liver damage caused by raw Polygonum multiflorum was more severe than that caused by processed Polygonum multiflorum.

Intrahepatic cholangiocarcinoma (ICC) is the second most common primary malignant tumor of the liver, characterized by high lethality and poor prognosis. Among the three subtypes of ICC, the intrahepatic mass-forming cholangiocarcinoma (IMCC) is the most prevalent. In recent years, the incidence of IMCC has been continuously rising, and its differential diagnosis and prognostic prediction have received widespread attention. Multimodal functional magnetic resonance imaging (MRI) integrates the advantages of various imaging modalities, capable of monitoring tumor hemodynamic changes, cellular metabolism, and other factors. Radiomics, with MRI as its basis, utilizes high-throughput extraction of imaging features to non-invasively acquire information on intra-tumor heterogeneity, subsequently assisting in the diagnosis of liver tumors. This article mainly summarizes the advancements in the application of multimodal functional MRI and MRI-based radiomics in the differential diagnosis and prognostic prediction of IMCC.

The development and validation of clinical prediction models based on artificial intelligence (AI) and machine learning methods have become increasingly widespread. However, the prediction model bias risk and applicability evaluation tool developed in 2019 (i.e., PROBAST-2019) has shown significant limitations. Therefore, an expanded and updated version of the PROBAST-2019 tool was released in 2025, known as the PROBAST+AI tool. The tool is divided into two parts including model development and model evaluation. It aims to comprehensively and systematically evaluate potential methodological quality issues in model development, bias risks in model evaluation, and the applicability of models, regardless of the modeling method used. This paper provides a systematic interpretation of the PROBAST+AI tool's items and case analyses, with the aim of guiding and assisting researchers engaged in related studies and promoting the high-quality development of clinical predictive model research.

Objective To explore the supportive care needs of heart transplant patients at different stages.Methods Purposive sampling method was used to select 15 heart transplant patients who were hospitalized in a tertiary A hospital in Guangdong Province from July 2023 to February 2024 as research subjects.According to the"Timing It Right"theory,5 semi-structured interviews were conducted with patients.Interpretive phenomenology was used to sort out and analyze the data.Results A total of 5 themes and 18 subthemes were extracted,including urgent desire for transplant information and psychological support during diagnosis,strong physiological and emotional needs during hospitalization,significant demand for health education in the preparation period for discharge,expectation of family support during the adjustment period,increasing demand for social support during the adaptation period.Conclusion The supportive care needs of heart transplant patients at different stages are dynamic.Medical staff should adopt the concept of dynamic and continuous care,and provide personalized care in stages,plans and continuance,in order to improve the quality of life of heart transplant patients.

This consensus was developed by the Orthodontic Society of the Chinese Stomatological Association to provide a systematic, scientific, and practical guideline for informed consent in orthodontic care. Orthodontic treatment is typically lengthy, highly individualized, and involves multiple factors such as growth and development, occlusal function, and facial esthetics. Rapid technological advances and diverse risk profiles make the traditional reliance on orthodontist experience or institutional templates insufficient to ensure patients′ full understanding and autonomous decision-making. To address this, the expert panel conducted extensive reviews of domestic and international guidelines, analyzed representative dispute cases, and performed multicenter patient-clinician surveys. Using a multi-round Delphi method, the group established a standardized informed consent framework covering the initial consultation, treatment, and retention phases. The consensus emphasizes that informed consent is not only a fundamental legal and ethical requirement but also a key step in building trust, improving patient compliance, and enhancing treatment satisfaction. Orthodontists should clearly and comprehensively explain treatment plans, potential risks, uncertainties, and associated costs, while respecting the autonomy of patients or guardians, and maintain continuous communication and dynamic evaluation throughout the treatment process. The release of this consensus provides unified and authoritative guidance for clinical orthodontics, helping to standardize informed consent, enhance its transparency, safeguard patient rights, reduce medical risks, and promote high-quality, sustainable development of orthodontic practice.

OBJECTIVE: To evaluate the effect of biodegradable magnesium alloy materials in promoting tendon-bone healing during rotator cuff tear repair and to investigate their potential underlying biological mechanisms. METHODS: Forty-eight 8-week-old Sprague Dawley rats were taken and randomly divided into groups A, B, and C. Rotator cuff tear models were created and repaired using magnesium alloy sutures in group A and Vicryl Plus 4-0 absorbable sutures in group B, while only subcutaneous incisions and sutures were performed in group C. Organ samples of groups A and B were taken for HE staining at 1 and 2 weeks after operation to evaluate the safety of magnesium alloy, and specimens from the supraspinatus tendon and proximal humerus were harvested at 2, 4, 8, and 12 weeks after operation. The specimens were observed macroscopically at 4 and 12 weeks after operation. Biomechanical tests were performed at 4, 8, and 12 weeks to test the ultimate load and stiffness of the healing sites in groups A and B. At 2, 4, and 12 weeks, the specimens were subjected to the following tests: Micro-CT to evaluate the formation of bone tunnels in groups A and B, HE staining and Masson staining to observe the regeneration of fibrocartilage at the tendon-bone interface after decalcification and sectioning, and Goldner trichrome staining to evaluate the calcification. Immunohistochemical staining was performed to detect the expressions of angiogenic factors, including vascular endothelial growth factor (VEGF) and bone morphogenetic protein 2 (BMP-2), as well as osteogenic factors at the tendon-bone interface. Additionally, immunofluorescence staining was used to examine the expressions of Arginase 1 and Integrin beta-2 to assess M1 and M2 macrophage polarization at the tendon-bone interface. The role of the phosphatidylinositol 3-kinase (PI3K)/protein kinase B (AKT) signaling pathway in tendon-bone healing was further analyzed using real-time fluorescence quantitative PCR. RESULTS: Analysis of visceral sections revealed that magnesium ions released during the degradation of magnesium alloys did not cause significant toxic effects on organs such as the heart, liver, spleen, lungs, and kidneys, indicating good biosafety. Histological analysis further demonstrated that fibrocartilage regeneration at the tendon-bone interface in group A occurred earlier, and the amount of fibrocartilage was significantly greater compared to group B, suggesting a positive effect of magnesium alloy material on tendon-bone interface repair. Additionally, Micro-CT analysis results revealed that bone tunnel formation occurred more rapidly in group A compared to group B, further supporting the beneficial effect of magnesium alloy on bone healing. Biomechanical testing showed that the ultimate load in group A was consistently higher than in group B, and the stiffness of group A was also greater than that of group B at 4 weeks, indicating stronger tissue-carrying capacity following tendon-bone interface repair and highlighting the potential of magnesium alloy in enhancing tendon-bone healing. Immunohistochemical staining results indicated that the expressions of VEGF and BMP-2 were significantly upregulated during the early stages of healing, suggesting that magnesium alloy effectively promoted angiogenesis and bone formation, thereby accelerating the tendon-bone healing process. Immunofluorescence staining further revealed that magnesium ions exerted significant anti-inflammatory effects by regulating macrophage polarization, promoting their shift toward the M2 phenotype. Real-time fluorescence quantitative PCR results demonstrated that magnesium ions could facilitate tendon-bone healing by modulating the PI3K/AKT signaling pathway. CONCLUSION Biodegradable magnesium alloy material accelerated fibrocartilage regeneration and calcification at the tendon-bone interface in rat rotator cuff tear repair by regulating the PI3K/AKT signaling pathway, thereby significantly enhancing tendon-bone healing.
Animals ; Rotator Cuff Injuries/metabolism* ; Rats, Sprague-Dawley ; Signal Transduction ; Wound Healing/drug effects* ; Alloys/pharmacology* ; Rats ; Proto-Oncogene Proteins c-akt/metabolism* ; Rotator Cuff/metabolism* ; Macrophages/metabolism* ; Magnesium/pharmacology* ; Phosphatidylinositol 3-Kinases/metabolism* ; Vascular Endothelial Growth Factor A/metabolism* ; Male ; Biocompatible Materials ; Bone Morphogenetic Protein 2/metabolism*

As a chronic progressive lung disease with poor prognosis,the pathogenesis of idiopathic pulmonary fibrosis(IPF)has not yet been clarified,and its treatment is still being explored.Animal models are important tools for studying the pathogenesis and therapeutic effects of diseases.Based on the similarity between animal models and human of IPF in terms of disease phenotype,this paper will review the research progress of IPF animal models in terms of the fibrosis mechanism induced by drugs and environmental factors,histopathological alterations,fibrosis stage,modelling time,etc.,and describe the advantages and disadvantages of different animal models,their characteristics and application profiles.

Objective:To investigate the expression changes of branched-chain amino acid transaminase 1(BCAT1)in the process of atherosclerosis(AS)in the elderly and its regulatory effect on macrophage foam cell formation,thereby revealing the potential pathogenesis of AS in the elderly.Methods:AS mouse models were established by feeding a high-fat diet in vivo.The expression and co-localization of BCAT1 and CD68 in aortic tissues of mice were detected by immunofluorescence double staining.Hematoxylin-eosin staining and Oil Red O staining were used to observe the pathological damage and lipid deposition in the aortic root tissues of mice.The expression of TNF-α,IL-6 and IL-1β in aortic tissues was determined by qPCR.In vitro,RAW264.7 mouse macrophage cells were stimulated with ox-LDL.The expression of BCAT1 in cells was detected by Western blot.Oil Red O staining was used to detect lipid accumulation and foam cell formation in cells.The contents of TNF-α,IL-6 and IL-1β in the cell supernatant were detected by ELISA.Results:Compared with the control group,the expression of BCAT1 in aortic tissues of AS mice was upregulated,and this protein was mainly localized in infiltrating macrophages(CD68+cells).The lipid content in atherosclerotic plaques of AS mice was significantly increased,the arterial wall was significantly thickened,and the infiltration of inflammatory cells was aggravated.Overexpression of BCAT1 further exacerbated AS lesions in aortic tissues of mice.The mRNA expression levels of TNF-α,IL-6 and IL-1β in the aorta of AS mice were significantly higher than those in the control group,and overexpression of BCAT1 further upregulated the mRNA expression levels of pro-inflammatory cytokines.In vitro,ox-LDL treatment significantly upregulated the protein expression of BCAT1 in RAW264.7 cells,increased intracellular lipid accumulation and foam cell formation,and promoted the release of pro-inflammatory cytokines.Overexpression of BCAT1 promoted lipid accumulation,foam cell formation and the release of pro-inflammatory cytokines in cells,while knockdown of BCAT1 showed the opposite trend.Conclusion:BCAT1 is involved in the development process of AS and increases the secretion of pro-inflammatory cytokines,promotes macrophage foam cell formation and inflammatory response,suggesting that BCAT1 plays a key role in the development of AS in the elderly.

Objective:To investigate the practicality and clinical significance of quantitative indicators related to wide QRS complex in the diagnosis of atrial fibrillation (AF) with wide QRS complex.Methods:A retrospective study was conducted to analyze the dynamic electrocardiogram data of 93 patients who visited Ankang People's Hospital from January 2021 to December 2023. Based on the type of arrhythmia, the patients were divided into two groups: AF with premature ventricular contraction (PVC) group ( n = 65) and AF with intraventricular conduction abnormality group ( n = 28). The traditional diagnostic indicators and newly introduced quantitative indicators were compared between the two groups to analyze the clinical significance of the new quantitative indicators in identifying AF with wide QRS complex. Results:There were statistically significant differences in the occurrence of cannon waves, QRS duration > 140 ms, QRS morphology in lead V1, the R wave or qR pattern, or the deepest point of R being greater than r or rS in lead V1 being > 60 ms, R/S ratio in lead V6 < 1 or displaying QS pattern, the presence of a notching, a slow decline, or a prominent R wave in the QRS beginning in lead aVR, Vi/Vt in lead aVR ≤ 1, and the data regarding the electrical axis in the no man's land between the two groups ( χ2 = 11.83, 37.59, 26.05, 27.33, 5.30, 49.46, 34.95, 4.90, all P < 0.05). The premature interval/coupling interval in the AF with PVC group was (1.38 ± 0.32), which was significantly lower than (1.84 ± 0.43) in the AF with intraventricular condection abnormality group ( t = -5.71, P < 0.001). The quasi-compensatory pause/coupling interval and quasi-compensatory pause/premature interval in the AF with PVC group were (1.71 ± 0.36) and (1.28 ± 0.25), respectively, which were significantly higher than those in the AF with intraventricular conduction abnormality group ( t = 5.48, 5.06, both P < 0.001). The areas under the curve for the premature interval/coupling interval, quasi-compensatory pause /coupling interval, and quasi-compensatory pause/premature interval, and the combined three indicators (using logistic regression) in distinguishing AF with wide QRS complex were 0.810, 0.788, 0.818, and 0.953, respectively. The area under the curve for the combined three indicators was significantly greater than that for each individual indicator ( Z = -3.10, -3.92, -3.09, all P < 0.05). Conclusions:Premature interval/coupling interval, quasi-compensatory pause/coupling interval, and quasi-compensatory pause/premature interval show good value in the diagnosis of AF with wide QRS complex, and the combined use of the three can significantly improve the diagnostic accuracy.