Objective To validate the diagnostic performance and risk stratification ability of an AI-based recognition system(PE-AI)for pulmonary embolism(PE)using computed tomography pulmonary angiography(CTPA)so as to analyze its diagnostic value in clinical practice.Methods A total of 416 patients with suspected PE who underwent CTPA from January 1,2023 to December 10,2023 at our hospital were included in this study.Two junior radiologists and PE-AI separately detected and diagnosed emboli in the collected cases by double-blind method,and recorded the diagnosis time respectively.Three senior radiologists reviewing with clinical follow-up results were used as the gold standard in this study.Diagnostic performance was evaluated by using the receiver operating characteristic(ROC)curve analysis and Delong-t test.For positive cases,the pulmonary artery obstruction index(PAOI)calculated by AI and manually were collected respectively and consistency analysis was performed.Results The area under the curve(AUC)of PE-AI,manual and combined diagnosis was 85.6％,90.8％and 95.1％,respectively,which differed significantly(P＜0.05).The reading time of PE-AI[(0.16±0.07)min]was significantly lower than the time of manual[(4.42±1.85)min,P＜0.001]and combined diagnosis[(4.58±1.84)min,P＜0.001].The PAOI measured by PE-AI and manually had high consistency(intraclass correlation efficient,ICC=0.80)in the subgroup analysis of confirmed cases.Conclusion AI can quickly identify pulmonary artery emboli in a short time and assist radiologists to improve diagnostic efficiency.At the same time,through the intelligent detection of PAOI,it is helpful for the risk stratification of patients with PE and optimizing the diagnosis and treatment pathway for pulmonary embolism.

Gastric carcinoma(GC),a highly prevalent malignant tumor globally,often progresses to advanced stages by the time of diagnosis due to its insidious clinical presentation,thereby significantly reducing therapeutic effectiveness and patient quality of life.Accurate screening and histopathological characterization of early gastric cancer(EGC)are essential for developing individualized treatment approaches.Although endoscopic techniques remain the gold standard for early GC detection,their diagnostic accuracy is largely dependent on the operator's skill,a challenge that current artificial intelligence(AI)-assisted innovations aim to address by stan-dardizing diagnostic procedures.Deep learning(DL)-based computer vision systems have demonstrated remarkable performance in identifying subtle EGC features,not only improving lesion detection sensitivity but also enabling automated assessment of key pathological indicators.These technological advances offer objective,visualized diag-nostic support for clinical decision-making.This review provides a systematic overview of recent developments in DL applications for endoscopic image analysis of EGC and evaluates their potential for clinical integration.

Objective This study aims to establish a hidden curriculum-based medical humanities teaching pathway within surgical internship education and evaluate its effectiveness in enhancing students' humanistic care competence.Methods A single-group pre-test and post-test design was adopted.A total of 76 interns from a tertiary teaching hospital in 2024 were in-cluded.A five-dimensional hidden curriculum framework—material,spiritual,behavioral,faculty,and institutional—was con-structed.Humanistic competence was assessed before and after the intervention using the Humanistic Professional Awareness Scale for Healthcare Students and Providers(HPAS-HSP).Results Post-intervention scores significantly improved compared to pre-intervention across the total scale in the three dimensions:personal integrity and responsibility,sensitivity to others,and pro-fessional competence(P＜0.05),with the greatest improvement observed in sensitivity to others.Conclusion The structured hidden curriculum is effective in enhancing medical students' humanistic qualities,especially in fostering emotional resonance and professional identity.Future work should focus on verifying behavioral transformation and developing multi-source evaluation sys-tems to improve effectiveness and applicability.

Objective:To analyze the awareness of and factors influencing the adjusted national immunization schedule for the diphtheria-tetanus-acellular pertussis (DTaP) vaccine among grassroots immunization service personnel in China.Methods:Based on the snowball sampling method from January to February 2025, immunization service personnel from all provinces of China were selected from the "Tingting Experts Talk" WeChat platform, with concurrent dissemination through the "National Vaccine-Preventable Diseases Communication Group" WeChat group. The questionnaire included basic demographic characteristics and knowledge of the DTaP vaccine immunization policy (13 questions in total). Respondents who answered ≥10 questions correctly were defined as being aware of the policy adjustment. The multivariable logistic regression analysis was performed to identify factors influencing awareness.Results:A total of 8 030 valid questionnaires were collected from 29 provinces, with a valid response rate of 92.91%. The overall awareness accuracy rates among the Centers for Disease Control and Prevention (CDC) personnel and the point of vaccination (POV) staff were 74.1% and 62.5%, respectively. The awareness rate of the core points of policy adjustment among the research subjects exceeded 90%. Among the questions regarding the operational details of policy implementation, the correct rate of answering questions related to the catch-up vaccination principles was relatively low (37.1%-74.0%). The multivariate logistic regression analysis showed that, compared with those with primary titles, CDC personnel with senior titles had higher mastery of the policy adjustment, with an OR (95% CI) value of 2.238 (1.343-3.730). Compared with those engaged in disease surveillance and immunization strategy research, CDC personnel with other work types had lower awareness of the policy adjustment, with an OR (95% CI) value of 0.404 (0.195-0.833). Compared with those in western regions, with primary titles, and without relevant training, POV staff in central regions, eastern regions, with intermediate titles, with senior titles, with one relevant training session, and with ≥2 relevant training sessions had better awareness of the program adjustment, with OR (95% CI) values of 1.214 (1.085-1.358), 1.412 (1.246-1.600), 1.606 (1.446-1.784), 1.737 (1.443-2.091), 2.254 (1.509-3.366), and 2.674 (1.769-3.981), respectively. Compared with those engaged in information registration/recipient notification, POV staff with vaccination services and other work types had lower awareness of the program adjustment, with OR (95% CI) values of 0.713 (0.633-0.803) and 0.508 (0.427-0.604), respectively. Conclusion:Although grassroots immunization service personnel show an insufficient mastery of certain catch-up vaccination knowledge, they demonstrate a good understanding of overall principles and routine immunization schedules shortly after the policy adjustment, which can effectively ensure an orderly transition between old and new immunization strategies.

Objective:To explore the distribution of Traditional Chinese Medicine constitution among patients with impaired awareness of hypoglycemia (IAH) and identify risk factors for IAH in patients with diabetes mellitus, to develop a risk prediction model. The aim is to validate the models′ predictive accuracy to facilitate early prevention and treatment of IAH.Methods:A case control study employing convenience sampling model was conducted on 1351 hospitalized patients with diabetes mellitus in the endocrinology departments of Changshu Hospital Affiliated to Nanjing University of Chinese Medicine and Affiliated Hospital of Jiangsu University, between August 2021 and December 2023. Traditional Chinese medicine constitution types were determined using the Traditional Chinese Medicine Constitution Classification and Judgment (ZYYXH/T157-2009). Data were divided into training and test sets at a ratio of 7∶3. Two prediction models were developed: Model 1, a conventional IAH prediction model for patients with diabetes mellitus, and Model 2, an IAH prediction model for patients with diabetes mellitus incorporating traditional Chinese medicine constitution. Nomograms were drawn for both models. The Hosmer-Lemeshow goodness-of-fit test, calibration curve, receiver operating characteristic (ROC) curve, and area under the curve (AUC) were calculated to evaluate the effectiveness of models 1 and 2. The improvement in prediction performance between Models 1 and 2 was assessed using Delong test, AUC, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA).Results:The study included 1 283 patients with diabetes mellitus, including 578 males and 705 females, aged (59.61 ± 14.09) years. The incidence of IAH among patients with diabetes mellitus was 20.50% (263/1283), with yang deficiency constitution being the most prevalent traditional Chinese medicine constitution type, at 47.53% (125/263). Multivariate analysis revealed that age, body mass index, course of diabetes, neurological hypoglycemia symptoms, hypoglycemia symptoms and severe hypoglycemia history were the influencing factors of Model 1 (all P<0.05); age, body mass index, neurological hypoglycemic symptoms, hypoglycemic symptoms, history of severe hypoglycemia, and traditional Chinese medicine constitution were the influencing factors of Model 2 (all P<0.05). The Hosmer-Lemeshow goodness-of-fit test showed a good fit of Model 2 [training set ( χ2=8.48, P>0.05), test set ( χ2=3.92, P>0.05)]. The Delong test results showed that the AUC for Model 2 was 0.96 for both the training and test sets, significantly higher than the AUCs of the 0.90 and 0.91 for Model 1 ( Z=-7.27, -3.70, both P<0.01). Furthermore, NRI was 0.66 ( 95%CI 0.53-0.79, P<0.01) and IDI was 0.02 (95% CI 0.01-0.03, P<0.05) for Model 2. Comparative analysis of clinical utility demonstrated that the net benefit of Model 2 for predicting IAH in patients with diabetes mellitus surpassed that of Model 1 across threshold probabilities ranging from 5% to 100%. Conclusions:The study constructed a nomogram prediction model included traditional Chinese medicine constitution with good predictive performance for IAH in patients with diabetes mellitus, and is of significant clinical value for identifying high-risk IAH populations.IAH patients mainly have a biased constitution, indicating that medical staff can reduce the incidence of IAH by improving the patients′ constitution.

Gastric carcinoma(GC),a highly prevalent malignant tumor globally,often progresses to advanced stages by the time of diagnosis due to its insidious clinical presentation,thereby significantly reducing therapeutic effectiveness and patient quality of life.Accurate screening and histopathological characterization of early gastric cancer(EGC)are essential for developing individualized treatment approaches.Although endoscopic techniques remain the gold standard for early GC detection,their diagnostic accuracy is largely dependent on the operator's skill,a challenge that current artificial intelligence(AI)-assisted innovations aim to address by stan-dardizing diagnostic procedures.Deep learning(DL)-based computer vision systems have demonstrated remarkable performance in identifying subtle EGC features,not only improving lesion detection sensitivity but also enabling automated assessment of key pathological indicators.These technological advances offer objective,visualized diag-nostic support for clinical decision-making.This review provides a systematic overview of recent developments in DL applications for endoscopic image analysis of EGC and evaluates their potential for clinical integration.

Objective:To analyze the awareness of and factors influencing the adjusted national immunization schedule for the diphtheria-tetanus-acellular pertussis (DTaP) vaccine among grassroots immunization service personnel in China.Methods:Based on the snowball sampling method from January to February 2025, immunization service personnel from all provinces of China were selected from the "Tingting Experts Talk" WeChat platform, with concurrent dissemination through the "National Vaccine-Preventable Diseases Communication Group" WeChat group. The questionnaire included basic demographic characteristics and knowledge of the DTaP vaccine immunization policy (13 questions in total). Respondents who answered ≥10 questions correctly were defined as being aware of the policy adjustment. The multivariable logistic regression analysis was performed to identify factors influencing awareness.Results:A total of 8 030 valid questionnaires were collected from 29 provinces, with a valid response rate of 92.91%. The overall awareness accuracy rates among the Centers for Disease Control and Prevention (CDC) personnel and the point of vaccination (POV) staff were 74.1% and 62.5%, respectively. The awareness rate of the core points of policy adjustment among the research subjects exceeded 90%. Among the questions regarding the operational details of policy implementation, the correct rate of answering questions related to the catch-up vaccination principles was relatively low (37.1%-74.0%). The multivariate logistic regression analysis showed that, compared with those with primary titles, CDC personnel with senior titles had higher mastery of the policy adjustment, with an OR (95% CI) value of 2.238 (1.343-3.730). Compared with those engaged in disease surveillance and immunization strategy research, CDC personnel with other work types had lower awareness of the policy adjustment, with an OR (95% CI) value of 0.404 (0.195-0.833). Compared with those in western regions, with primary titles, and without relevant training, POV staff in central regions, eastern regions, with intermediate titles, with senior titles, with one relevant training session, and with ≥2 relevant training sessions had better awareness of the program adjustment, with OR (95% CI) values of 1.214 (1.085-1.358), 1.412 (1.246-1.600), 1.606 (1.446-1.784), 1.737 (1.443-2.091), 2.254 (1.509-3.366), and 2.674 (1.769-3.981), respectively. Compared with those engaged in information registration/recipient notification, POV staff with vaccination services and other work types had lower awareness of the program adjustment, with OR (95% CI) values of 0.713 (0.633-0.803) and 0.508 (0.427-0.604), respectively. Conclusion:Although grassroots immunization service personnel show an insufficient mastery of certain catch-up vaccination knowledge, they demonstrate a good understanding of overall principles and routine immunization schedules shortly after the policy adjustment, which can effectively ensure an orderly transition between old and new immunization strategies.

Objective To validate the diagnostic performance and risk stratification ability of an AI-based recognition system(PE-AI)for pulmonary embolism(PE)using computed tomography pulmonary angiography(CTPA)so as to analyze its diagnostic value in clinical practice.Methods A total of 416 patients with suspected PE who underwent CTPA from January 1,2023 to December 10,2023 at our hospital were included in this study.Two junior radiologists and PE-AI separately detected and diagnosed emboli in the collected cases by double-blind method,and recorded the diagnosis time respectively.Three senior radiologists reviewing with clinical follow-up results were used as the gold standard in this study.Diagnostic performance was evaluated by using the receiver operating characteristic(ROC)curve analysis and Delong-t test.For positive cases,the pulmonary artery obstruction index(PAOI)calculated by AI and manually were collected respectively and consistency analysis was performed.Results The area under the curve(AUC)of PE-AI,manual and combined diagnosis was 85.6％,90.8％and 95.1％,respectively,which differed significantly(P＜0.05).The reading time of PE-AI[(0.16±0.07)min]was significantly lower than the time of manual[(4.42±1.85)min,P＜0.001]and combined diagnosis[(4.58±1.84)min,P＜0.001].The PAOI measured by PE-AI and manually had high consistency(intraclass correlation efficient,ICC=0.80)in the subgroup analysis of confirmed cases.Conclusion AI can quickly identify pulmonary artery emboli in a short time and assist radiologists to improve diagnostic efficiency.At the same time,through the intelligent detection of PAOI,it is helpful for the risk stratification of patients with PE and optimizing the diagnosis and treatment pathway for pulmonary embolism.

Objective This study aims to establish a hidden curriculum-based medical humanities teaching pathway within surgical internship education and evaluate its effectiveness in enhancing students' humanistic care competence.Methods A single-group pre-test and post-test design was adopted.A total of 76 interns from a tertiary teaching hospital in 2024 were in-cluded.A five-dimensional hidden curriculum framework—material,spiritual,behavioral,faculty,and institutional—was con-structed.Humanistic competence was assessed before and after the intervention using the Humanistic Professional Awareness Scale for Healthcare Students and Providers(HPAS-HSP).Results Post-intervention scores significantly improved compared to pre-intervention across the total scale in the three dimensions:personal integrity and responsibility,sensitivity to others,and pro-fessional competence(P＜0.05),with the greatest improvement observed in sensitivity to others.Conclusion The structured hidden curriculum is effective in enhancing medical students' humanistic qualities,especially in fostering emotional resonance and professional identity.Future work should focus on verifying behavioral transformation and developing multi-source evaluation sys-tems to improve effectiveness and applicability.

Objective:To explore the distribution of Traditional Chinese Medicine constitution among patients with impaired awareness of hypoglycemia (IAH) and identify risk factors for IAH in patients with diabetes mellitus, to develop a risk prediction model. The aim is to validate the models′ predictive accuracy to facilitate early prevention and treatment of IAH.Methods:A case control study employing convenience sampling model was conducted on 1351 hospitalized patients with diabetes mellitus in the endocrinology departments of Changshu Hospital Affiliated to Nanjing University of Chinese Medicine and Affiliated Hospital of Jiangsu University, between August 2021 and December 2023. Traditional Chinese medicine constitution types were determined using the Traditional Chinese Medicine Constitution Classification and Judgment (ZYYXH/T157-2009). Data were divided into training and test sets at a ratio of 7∶3. Two prediction models were developed: Model 1, a conventional IAH prediction model for patients with diabetes mellitus, and Model 2, an IAH prediction model for patients with diabetes mellitus incorporating traditional Chinese medicine constitution. Nomograms were drawn for both models. The Hosmer-Lemeshow goodness-of-fit test, calibration curve, receiver operating characteristic (ROC) curve, and area under the curve (AUC) were calculated to evaluate the effectiveness of models 1 and 2. The improvement in prediction performance between Models 1 and 2 was assessed using Delong test, AUC, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA).Results:The study included 1 283 patients with diabetes mellitus, including 578 males and 705 females, aged (59.61 ± 14.09) years. The incidence of IAH among patients with diabetes mellitus was 20.50% (263/1283), with yang deficiency constitution being the most prevalent traditional Chinese medicine constitution type, at 47.53% (125/263). Multivariate analysis revealed that age, body mass index, course of diabetes, neurological hypoglycemia symptoms, hypoglycemia symptoms and severe hypoglycemia history were the influencing factors of Model 1 (all P<0.05); age, body mass index, neurological hypoglycemic symptoms, hypoglycemic symptoms, history of severe hypoglycemia, and traditional Chinese medicine constitution were the influencing factors of Model 2 (all P<0.05). The Hosmer-Lemeshow goodness-of-fit test showed a good fit of Model 2 [training set ( χ2=8.48, P>0.05), test set ( χ2=3.92, P>0.05)]. The Delong test results showed that the AUC for Model 2 was 0.96 for both the training and test sets, significantly higher than the AUCs of the 0.90 and 0.91 for Model 1 ( Z=-7.27, -3.70, both P<0.01). Furthermore, NRI was 0.66 ( 95%CI 0.53-0.79, P<0.01) and IDI was 0.02 (95% CI 0.01-0.03, P<0.05) for Model 2. Comparative analysis of clinical utility demonstrated that the net benefit of Model 2 for predicting IAH in patients with diabetes mellitus surpassed that of Model 1 across threshold probabilities ranging from 5% to 100%. Conclusions:The study constructed a nomogram prediction model included traditional Chinese medicine constitution with good predictive performance for IAH in patients with diabetes mellitus, and is of significant clinical value for identifying high-risk IAH populations.IAH patients mainly have a biased constitution, indicating that medical staff can reduce the incidence of IAH by improving the patients′ constitution.