Objective:To fine-tune the mT5 (massively multilingual pre-trained text-to-text transformer) large language model, automatically generate report conclusions for teaching purposes from chest CT image descriptions, and assess the quality of automatically generated conclusions.Methods:The training set included 3 000 high-quality physical examination chest CT reports from one hospital, and the external validation set consisted of 600 physical examination chest CT reports from two other hospitals. Experienced radiology teaching physicians assessed the consistency between the generated conclusions and the original physician-written conclusions in the external validation set using a 5-point Likert scale across five linguistic indicators (correctness of examination information, correctness of lesion detection, standardization of terminology, applicability of the conclusions, and simplicity of conclusions). Using the original report conclusions as the reference, the accuracy of the conclusions generated based on the external validation set in describing four major thoracic conditions (pulmonary nodules, pneumonia, emphysema, pleural effusion) was evaluated. Perform chi square test using SPSS 25.0.Results:In the external validation set, the mean consistency score between the generated conclusions and the original conclusions given by the radiology teaching physicians was >4 points, indicating agreement with the original conclusions. In the generated conclusions, the description of the four major thoracic conditions demonstrated 0.95-1.00 (95% CI=0.91-1.00) accuracy, 0.76-1.00 (95% CI=0.59-1.00) sensitivity, and 0.97-1.00 (95% CI=0.91-1.00) specificity. Conclusions:The chest CT report conclusion generation system based on the mT5 large language model demonstrated high accuracy and is expected to provide immediate and efficient automated guidance for standardized residency training.

Objective To observe the value of Swin2SR network based on Transformer architecture for reconstructing chest super-resolution CT images.Methods Chest CT data of 218 patients were retrospectively collected.Swin2SR model based on Transformer architecture was adopted to enhance standard 512 matrix(512 × 512)CT images(standard-512 group)into 1 024(SR-1 024 group)and 2 048(SR-2 048 group)matrix SR CT images,respectively.Subjective and objective evaluation of image quality were performed,and the results were compared among groups.Results The subjective scores of overall imaging quality and lesion clarity in SR-1 024 and SR-2 048 groups were both higher than those in standard-512 group(all P＜0.05),while no significant difference was found between the former two(P＞0.05).Meanwhile,no significant difference of objective indexes of imaging quality was observed among 3 groups(all P＞0.05).Conclusion Swin2SR model could reconstruct chest SR CT images without increasing noise and improve imaging quality.

Objective To explore the application effect of the dual-track nursing intervention model in the treatment process of children with lobar pneumonia.Methods A total of 186 children with lobar pneumonia were selected and randomly divided into control group and intervention group u-sing a double-blind method,with 93 cases in each group.The control group received conventional nursing intervention,while the intervention group implemented the dual-track nursing intervention model on the basis of conventional nursing.This model included the establishment and training of nurs-ing teams,personalized nursing plans,health education,and psychological support.Outside the hos-pital,it emphasized family support,regular follow-up guidance,and community-based collaborative ed-ucation.Both groups received a 3-week intervention.The improvement times of clinical symptoms,hos-pital stay,pulmonary function indicators before and after nursing,treatment compliance,and family members' satisfaction with nursing were compared and analyzed between the two groups.Results The fever resolution time[(3.89±0.96)d],cough relief time[(6.21±1.34)d],disappearance time of pulmonary rales[(7.89±1.56)d],and hospital stay duration[(9.45±1.89)d]in the intervention group were all shorter than those in the control group[(5.23±1.14),(7.45±1.67),(9.32±2.01),and(11.28±2.35)d,respectively],with statistically significant differences(P＜0.05).After nursing,the forced expiratory volume in one second(FEV1)[(1.51±0.22)L],forced vital capacity(FVC)[(1.75±0.25)L],and FEV1/FVC[(94.12±5.65)％]in the intervention group were all higher than those in the control group[(1.42±0.15)L,(1.66±0.22)L,and(85.73±8.41)％,respectively],with statistically significant differences(P＜0.05).The scores for exami-nation cooperation[(23.91±3.82)points],nursing cooperation[(24.19±4.03)points],standardized medication use[(24.26±3.94)points],and rational diet[(23.77±3.62)points]in the intervention group were higher than those in the control group[(20.16±3.53),(19.64±3.46),(23.05±3.68),and(18.85±3.41)points,respectively],with statistically significant differences(P＜0.05).The satisfaction rate of family members with nursing work in the intervention group was higher than that in the control group,with a statistically significant difference(98.92％versus 89.25％,P＜0.05).Conclusion The dual-track nursing intervention model has a signifi-cant application effect in children with lobar pneumonia.It can accelerate their recovery process,improve treatment compliance,promote pulmonary function improvement,and enhance family mem-bers' satisfaction.

Periodontitis is a clear risk factor for peri-implant diseases,so implant therapy for patients with periodontitis is special and difficult.It is important to control periodontal infection before implant placement.Besides,we should choose the appropriate surgical procedures and protocols according to the anatomical characteristics of different regions.After implant surgery,we should provide perio-dontal care to maintain the health and long-term stability of the natural teeth and the implants.This article summarizes and reviews the pathogenic characteristics of periodontitis and the characteristics of hard and soft tissues after infection.It systematically describes how implant treatment should be considered and maintained in the therapeutic process,which provides reference for clinical treatment.

Objective:Constructing a risk prediction model to assess the impact of various factors on the need for auxiliary bone grafting with implant placement following alveolar ridge preservation (ARP) in posterior teeth.Methods:According to the sample size calculation formula, the sample size was calculated using the pmsampsize package of R 4.1.3 software, based on inclusion and exclusion criteria, a total of 110 posterior teeth in 98 patients who underwent ARP at the Department of Periodontology, School and Hospital of Stomatology, China Medical University, from January 2018 to May 2024 were conducted. Teeth were randomly divided into modeling group and validation group with 7∶3 ratio according to the random number table. The modeling group was divided into direct implantation group and auxiliary bone grafting group on the basis of whether auxiliary bone grafting was performed 6 months after ARP. Univariate and multivariate analyses were conducted to identify factors influencing auxiliary bone grafting with implant placement following ARP. Nomogram was constructed using R software. Receiver operator characteristic (ROC) curve and calibration curve were drawn to evaluate model differentiation and consistency. The decision curve analysis (DCA) was used to assess the clinical application value of the model.Results:Age ( OR=1.06, P=0.001), maximum attachment loss (AL) ( OR=1.75, P<0.001), reason of tooth extraction ( OR=12.73, P<0.001), smoking [<10 cigarettes/d ( OR=7.59, P<0.001);≥10 cigarettes/d ( OR=28.12, P<0.001)] and stage of periodontitis [stage Ⅱ ( OR=2.57, P=0.430); stage Ⅲ ( OR=21.00, P=0.007); stage Ⅳ ( OR=76.50, P<0.001)] influenced the necessity for auxiliary bone grafting with implant placement after ARP. After multivariate analysis of the above influencing factors, it was found that smoking [<10 cigarettes/d ( OR=7.02, P=0.009);≥10 cigarettes/d ( OR=10.27, P=0.026)] was an independent risk factor for the need of auxiliary bone grafting with implant placement after ARP. The area under the ROC curve for internal verification was 0.90 (95 %CI: 0.84-0.97), and the H-L goodness of fit test results were χ 2=4.79, P=0.780, indicating a good agreement. The area under the externally verified ROC curve was 0.97 (95 %CI: 0.92-1.00), suggesting that the fitting effect was slightly lower than that of the modeling group, and the predicted value of the model was slightly lower than the true value, which might underestimate the risk of additional surgery in patients. Results:of H-L goodness of fit test were χ 2=5.03, P=0.754. The DCA curve showed that when the probability of high-risk threshold was between 0.06 and 0.93, the clinical application value of the prediction model was higher. Conclusions:Age, smoking, reason of tooth extraction, stage of periodontitis, and maximum AL of the affected teeth were related to the necessity for auxiliary bone grafting with implant placement 6 months after ARP. Smoking was an independent risk factor for auxiliary bone grafting surgery. The constructed nomogram model had good discrimination and consistency.

The European Federation of Periodontology (EFP) and the Association for Dental Education in Europe (ADEE) jointly held the second European Consensus Workshop on Education in Periodontology in February, 2023. Building on the first consensus workshop in 2009, expert working groups from European Workshop Committee updated four educational levels: undergraduate, specialist, continuing professional development (CPD), as well as teaching methods, culminating in the updated consensus report in March, 2024. This article introduces and interprets the contents of the 2024 consensus report. Specific to China′s national conditions, we also propose future perspectives and considerations on different levels of periodontal education in China based on this consensus.

Objective:To fine-tune the mT5 (massively multilingual pre-trained text-to-text transformer) large language model, automatically generate report conclusions for teaching purposes from chest CT image descriptions, and assess the quality of automatically generated conclusions.Methods:The training set included 3 000 high-quality physical examination chest CT reports from one hospital, and the external validation set consisted of 600 physical examination chest CT reports from two other hospitals. Experienced radiology teaching physicians assessed the consistency between the generated conclusions and the original physician-written conclusions in the external validation set using a 5-point Likert scale across five linguistic indicators (correctness of examination information, correctness of lesion detection, standardization of terminology, applicability of the conclusions, and simplicity of conclusions). Using the original report conclusions as the reference, the accuracy of the conclusions generated based on the external validation set in describing four major thoracic conditions (pulmonary nodules, pneumonia, emphysema, pleural effusion) was evaluated. Perform chi square test using SPSS 25.0.Results:In the external validation set, the mean consistency score between the generated conclusions and the original conclusions given by the radiology teaching physicians was >4 points, indicating agreement with the original conclusions. In the generated conclusions, the description of the four major thoracic conditions demonstrated 0.95-1.00 (95% CI=0.91-1.00) accuracy, 0.76-1.00 (95% CI=0.59-1.00) sensitivity, and 0.97-1.00 (95% CI=0.91-1.00) specificity. Conclusions:The chest CT report conclusion generation system based on the mT5 large language model demonstrated high accuracy and is expected to provide immediate and efficient automated guidance for standardized residency training.

Objective To observe the value of Swin2SR network based on Transformer architecture for reconstructing chest super-resolution CT images.Methods Chest CT data of 218 patients were retrospectively collected.Swin2SR model based on Transformer architecture was adopted to enhance standard 512 matrix(512 × 512)CT images(standard-512 group)into 1 024(SR-1 024 group)and 2 048(SR-2 048 group)matrix SR CT images,respectively.Subjective and objective evaluation of image quality were performed,and the results were compared among groups.Results The subjective scores of overall imaging quality and lesion clarity in SR-1 024 and SR-2 048 groups were both higher than those in standard-512 group(all P＜0.05),while no significant difference was found between the former two(P＞0.05).Meanwhile,no significant difference of objective indexes of imaging quality was observed among 3 groups(all P＞0.05).Conclusion Swin2SR model could reconstruct chest SR CT images without increasing noise and improve imaging quality.

Objective:Constructing a risk prediction model to assess the impact of various factors on the need for auxiliary bone grafting with implant placement following alveolar ridge preservation (ARP) in posterior teeth.Methods:According to the sample size calculation formula, the sample size was calculated using the pmsampsize package of R 4.1.3 software, based on inclusion and exclusion criteria, a total of 110 posterior teeth in 98 patients who underwent ARP at the Department of Periodontology, School and Hospital of Stomatology, China Medical University, from January 2018 to May 2024 were conducted. Teeth were randomly divided into modeling group and validation group with 7∶3 ratio according to the random number table. The modeling group was divided into direct implantation group and auxiliary bone grafting group on the basis of whether auxiliary bone grafting was performed 6 months after ARP. Univariate and multivariate analyses were conducted to identify factors influencing auxiliary bone grafting with implant placement following ARP. Nomogram was constructed using R software. Receiver operator characteristic (ROC) curve and calibration curve were drawn to evaluate model differentiation and consistency. The decision curve analysis (DCA) was used to assess the clinical application value of the model.Results:Age ( OR=1.06, P=0.001), maximum attachment loss (AL) ( OR=1.75, P<0.001), reason of tooth extraction ( OR=12.73, P<0.001), smoking [<10 cigarettes/d ( OR=7.59, P<0.001);≥10 cigarettes/d ( OR=28.12, P<0.001)] and stage of periodontitis [stage Ⅱ ( OR=2.57, P=0.430); stage Ⅲ ( OR=21.00, P=0.007); stage Ⅳ ( OR=76.50, P<0.001)] influenced the necessity for auxiliary bone grafting with implant placement after ARP. After multivariate analysis of the above influencing factors, it was found that smoking [<10 cigarettes/d ( OR=7.02, P=0.009);≥10 cigarettes/d ( OR=10.27, P=0.026)] was an independent risk factor for the need of auxiliary bone grafting with implant placement after ARP. The area under the ROC curve for internal verification was 0.90 (95 %CI: 0.84-0.97), and the H-L goodness of fit test results were χ 2=4.79, P=0.780, indicating a good agreement. The area under the externally verified ROC curve was 0.97 (95 %CI: 0.92-1.00), suggesting that the fitting effect was slightly lower than that of the modeling group, and the predicted value of the model was slightly lower than the true value, which might underestimate the risk of additional surgery in patients. Results:of H-L goodness of fit test were χ 2=5.03, P=0.754. The DCA curve showed that when the probability of high-risk threshold was between 0.06 and 0.93, the clinical application value of the prediction model was higher. Conclusions:Age, smoking, reason of tooth extraction, stage of periodontitis, and maximum AL of the affected teeth were related to the necessity for auxiliary bone grafting with implant placement 6 months after ARP. Smoking was an independent risk factor for auxiliary bone grafting surgery. The constructed nomogram model had good discrimination and consistency.

The European Federation of Periodontology (EFP) and the Association for Dental Education in Europe (ADEE) jointly held the second European Consensus Workshop on Education in Periodontology in February, 2023. Building on the first consensus workshop in 2009, expert working groups from European Workshop Committee updated four educational levels: undergraduate, specialist, continuing professional development (CPD), as well as teaching methods, culminating in the updated consensus report in March, 2024. This article introduces and interprets the contents of the 2024 consensus report. Specific to China′s national conditions, we also propose future perspectives and considerations on different levels of periodontal education in China based on this consensus.