Objective:To establish three machine learning prediction models based on CT imaging characteristics of papillary thyroid carcinoma (PTC) , and use SHAP (shapley additive explanations) analysis to investigate the contribution of each CT image features in the best model.Methods:CT imaging features in 426 cases of 440 PTCs confirmed pathologically from Jan. 2016 to Jan. 2021 at the affiliated Hangzhou First People’s Hospital of Westlake University Medical School were retrospectively analyzed. compared with 467 cases of 528 nodular goiter (NG) , evaluating the distribution of four CT characteristics: cookie bite sign, enhanced range of narrowing/blur (ERNB) , microcalcifications, and irregular shape. We split the data into 8∶2 ratio for training and testing sets, then constructed three machine learning models using XGBoost, RF, and SVM. Based on AUC, accuracy, F1 score, and other metrics, we selected the best model. Lastly, we used SHAP values to assess each CT feature’s contribution and positive/negative effects on the model.Results:Among 440 PTC and 528 NG nodules, CT features like cookie bite sign, ERNB, microcalcifications, and irregular shape occurred in 326 and 30 ( χ 2=483.05, P<0.001) , 363 and 106 ( χ 2=374.45, P<0.001) , 158 and 53 ( χ 2=94.24, P<0.001) , and 354 and 52 ( χ 2=491.34, P<0.001) nodules, respectively. The machine learning models built using XGBoost, RF, and SVM had AUC, accuracy, and F1 scores ranging from 0.884~0.925, 0.867~0.873, and 0.844~0.854 respectively on the training set. On the test set, the scores ranged from 0.869~0.923, 0.845~0.871, and 0.803~0.845. Among them, the XGBoost model demonstrated the highest diagnostic performance on the test set. Among the four CT features, irregular shape had the highest absolute SHAP value, positively contributing to PTC diagnosis. Conclusion:XGBoost model showed the highest PTC diagnostic performance. Irregular shape had the greatest positive impact on PTC diagnosis.

Objective:Papillary thyroid carcinoma with a maximum tumor diameter of ≤1 cm was defined as papillary thyroid carcinoma (PTC). To explore the clinical risk factors of central lymph node metastasis (CLNM) in PTC at different locations.Methods:The clinical and pathological data of 1383 cases with solitary PTC in Hangzhou First People’s Hospital were retrospectively analyzed, and they were divided into isthmus group (175 cases), near-isthmus group (95 cases) and lateral lobe group (1113 cases) according to their tumor location. Univariate and multivariate analyses were used to analyze the relationship between gender, age, tumor maximum diameter, Hashimoto’s thyroiditis (HT) and CLNM, and the threshold for the occurrence of CLNM in each group of age and tumor maximum diameter was determined by the area under the receiver operating characteristic (ROC) .Results:The proportion of CLNM in the isthmus group, near-isthmus group and the lateral lobe group were 39.4% (69/175), 35.8% (34/95) and 29.6% (329/1113), respectively ( χ2=7.84, P=0.020). The intra-group comparison showed that there were statistical differences between the isthmus group and the lateral lobe group ( χ2=6.90, P=0.011), and there were no statistical differences between the isthmus group and near-isthmus group ( χ2=0.35, P=0.601), and near-isthmus group and the lateral leaf group ( χ2=1.62, P=0.313). Univariate and multivariate analysis showed that male ( OR: 3.697) and age < 38.5 years ( OR: 4.727) were independent risk factors for CLNM in PTC in the Isthmus Group, while male ( OR: 2.193), without HT ( OR: 1.702), tumor maximum diameter > 6.5 mm ( OR: 2.535) and age < 45.5 years ( OR: 3.030) were independent risk factors for CLNM in PTC in the lateral lobe group. Conclusions:Male sex and age are independent risk factors for CLNM in isthmus and lateral lobe PTC, and uncomplicated HT and tumor maximum diameter are also independent risk factors for CLNM in lateral lobe PTC. The incidence of CLNM in PTC in the isthmus, near-isthmus and lateral lobes decreased sequentially, and PTC in the near isthmus can not be simply regarded as the isthmus or lateral lobe PTC, and the lymph nodes in the central area should be fully evaluated before surgery to provide individualized treatment.

Objective:To establish three machine learning prediction models based on CT imaging characteristics of papillary thyroid carcinoma (PTC) , and use SHAP (shapley additive explanations) analysis to investigate the contribution of each CT image features in the best model.Methods:CT imaging features in 426 cases of 440 PTCs confirmed pathologically from Jan. 2016 to Jan. 2021 at the affiliated Hangzhou First People’s Hospital of Westlake University Medical School were retrospectively analyzed. compared with 467 cases of 528 nodular goiter (NG) , evaluating the distribution of four CT characteristics: cookie bite sign, enhanced range of narrowing/blur (ERNB) , microcalcifications, and irregular shape. We split the data into 8∶2 ratio for training and testing sets, then constructed three machine learning models using XGBoost, RF, and SVM. Based on AUC, accuracy, F1 score, and other metrics, we selected the best model. Lastly, we used SHAP values to assess each CT feature’s contribution and positive/negative effects on the model.Results:Among 440 PTC and 528 NG nodules, CT features like cookie bite sign, ERNB, microcalcifications, and irregular shape occurred in 326 and 30 ( χ 2=483.05, P<0.001) , 363 and 106 ( χ 2=374.45, P<0.001) , 158 and 53 ( χ 2=94.24, P<0.001) , and 354 and 52 ( χ 2=491.34, P<0.001) nodules, respectively. The machine learning models built using XGBoost, RF, and SVM had AUC, accuracy, and F1 scores ranging from 0.884~0.925, 0.867~0.873, and 0.844~0.854 respectively on the training set. On the test set, the scores ranged from 0.869~0.923, 0.845~0.871, and 0.803~0.845. Among them, the XGBoost model demonstrated the highest diagnostic performance on the test set. Among the four CT features, irregular shape had the highest absolute SHAP value, positively contributing to PTC diagnosis. Conclusion:XGBoost model showed the highest PTC diagnostic performance. Irregular shape had the greatest positive impact on PTC diagnosis.

Objective:Papillary thyroid carcinoma with a maximum tumor diameter of ≤1 cm was defined as papillary thyroid carcinoma (PTC). To explore the clinical risk factors of central lymph node metastasis (CLNM) in PTC at different locations.Methods:The clinical and pathological data of 1383 cases with solitary PTC in Hangzhou First People’s Hospital were retrospectively analyzed, and they were divided into isthmus group (175 cases), near-isthmus group (95 cases) and lateral lobe group (1113 cases) according to their tumor location. Univariate and multivariate analyses were used to analyze the relationship between gender, age, tumor maximum diameter, Hashimoto’s thyroiditis (HT) and CLNM, and the threshold for the occurrence of CLNM in each group of age and tumor maximum diameter was determined by the area under the receiver operating characteristic (ROC) .Results:The proportion of CLNM in the isthmus group, near-isthmus group and the lateral lobe group were 39.4% (69/175), 35.8% (34/95) and 29.6% (329/1113), respectively ( χ2=7.84, P=0.020). The intra-group comparison showed that there were statistical differences between the isthmus group and the lateral lobe group ( χ2=6.90, P=0.011), and there were no statistical differences between the isthmus group and near-isthmus group ( χ2=0.35, P=0.601), and near-isthmus group and the lateral leaf group ( χ2=1.62, P=0.313). Univariate and multivariate analysis showed that male ( OR: 3.697) and age < 38.5 years ( OR: 4.727) were independent risk factors for CLNM in PTC in the Isthmus Group, while male ( OR: 2.193), without HT ( OR: 1.702), tumor maximum diameter > 6.5 mm ( OR: 2.535) and age < 45.5 years ( OR: 3.030) were independent risk factors for CLNM in PTC in the lateral lobe group. Conclusions:Male sex and age are independent risk factors for CLNM in isthmus and lateral lobe PTC, and uncomplicated HT and tumor maximum diameter are also independent risk factors for CLNM in lateral lobe PTC. The incidence of CLNM in PTC in the isthmus, near-isthmus and lateral lobes decreased sequentially, and PTC in the near isthmus can not be simply regarded as the isthmus or lateral lobe PTC, and the lymph nodes in the central area should be fully evaluated before surgery to provide individualized treatment.

Objective To observe the value of non-contrast CT radiomics extreme gradient boosting(XGBoost)model based on SHAP method for predicting acute necrotic collection(ANC)around acute pancreatitis(AP).Methods A total of 307 patients with initially clinically diagnosed AP were retrospectively enrolled.The optimal radiomics features of peripheral pancreatic tissue volume of interest(VOI)were extracted and screened based on automatic segmentation on the first non-contrast CT,and the evaluation results of modified CT severity index(MCTSI)score of AP severity based on first enhanced CT were recorded.The patients were divided into peripancreatic ANC group(ANC group)and acute peripancreatic fluid collection(APFC)group according to follow-up abdominal CT.XGBoost method was used to construct radiomics model,MCTSI model and combined model for predicting AP ANC based on the optimal radiomics features,MCTSI and their combination,respectively.The diagnostic efficacy of each model was evaluated using 5-fold cross-validation method,and the contribution of each variable to combined model was analyzed with SHAP method.Results Among 307 cases,there were 134 cases in ANC group and 173 in APFC group.Totally 6 optimal radiomics features were screened based on the first non-contrast CT.The area under the receiver operating characteristic curve(AUC)of radiomics model,MCTSI model and combined model was 0.936,0.693 and 0.917,respectively.The AUC of MCTSI model was lower than that of radiomics model and combined model(Z=-3.485,-2.824,both P＜0.01),while no significant difference of AUC was found between radiomics model and combined model(Z=-0.817,P=0.415).The contribution of optimal radiomics features to combined model were all higher than that of MCTSI score.Conclusion Non-contrast CT radiomics XGBoost model could effectively predict AP ANC.

Objective To observe the value of non-contrast CT radiomics extreme gradient boosting(XGBoost)model based on SHAP method for predicting acute necrotic collection(ANC)around acute pancreatitis(AP).Methods A total of 307 patients with initially clinically diagnosed AP were retrospectively enrolled.The optimal radiomics features of peripheral pancreatic tissue volume of interest(VOI)were extracted and screened based on automatic segmentation on the first non-contrast CT,and the evaluation results of modified CT severity index(MCTSI)score of AP severity based on first enhanced CT were recorded.The patients were divided into peripancreatic ANC group(ANC group)and acute peripancreatic fluid collection(APFC)group according to follow-up abdominal CT.XGBoost method was used to construct radiomics model,MCTSI model and combined model for predicting AP ANC based on the optimal radiomics features,MCTSI and their combination,respectively.The diagnostic efficacy of each model was evaluated using 5-fold cross-validation method,and the contribution of each variable to combined model was analyzed with SHAP method.Results Among 307 cases,there were 134 cases in ANC group and 173 in APFC group.Totally 6 optimal radiomics features were screened based on the first non-contrast CT.The area under the receiver operating characteristic curve(AUC)of radiomics model,MCTSI model and combined model was 0.936,0.693 and 0.917,respectively.The AUC of MCTSI model was lower than that of radiomics model and combined model(Z=-3.485,-2.824,both P＜0.01),while no significant difference of AUC was found between radiomics model and combined model(Z=-0.817,P=0.415).The contribution of optimal radiomics features to combined model were all higher than that of MCTSI score.Conclusion Non-contrast CT radiomics XGBoost model could effectively predict AP ANC.

Objective:To explore the diagnostic efficacy of enhanced CT value in central lymph node metastasis (CLNM) of papillary thyroid carcinoma (PTC) with Hashimoto’s thyroiditis (HT) .Methods:The 209 central lymph nodes of 209 patients with PTC confirmed by surgery and pathology were retrospectively analyzed, and they were divided into HT group and non-HT group, including 77 lymph nodes (52 negative and 25 positive) in the HT-PTC group and 132 lymph nodes (74 negative and 58 positive) in the non-HT group. The CT values of lymph nodes were measured on enhanced CT images, and the optimal thresholds and corresponding sensitivity and specificity of enhanced CT values in the two groups were analyzed by the receiver operating characteristic curve.Results:The enhanced CT values of metastatic lymph nodes in the two groups were (103.2±21.1) Hu and (101.9±25.4) Hu, respectively ( t=0.23, P>0.05), and the enhanced CT values of benign lymph nodes were (72.0±15.8) Hu and (68.5±10.9) Hu, respectively ( t=-1.38, P>0.05). The area under the curve of enhanced CT values in the HT group and non-HT group were 0.882 and 0.918, respectively, and the optimal thresholds were 78.8 Hu and 74.7 Hu, respectively, with corresponding sensitivity of 92.0% and 91.4%, and specificity of 67.3% and 77.0%, respectively, for the diagnosis of CLNM in the two groups. Conclusion:The enhanced CT value has high and similar diagnostic efficiency for CLNM in HT group and non-HT group, providing a theoretical basis for the early clinical development of individualized treatment plans.

Objective:To determine the clinical factors affecting Central lymph node metastases (CLNM) of single Papillary thyroid carcinoma (PTC). To predict the value of age for CLNM under different genders and the status of Hashimoto’s thyroiditis (HT) .Methods:The clinical data of 4 115 patients with PTMC (≤10.0 mm) and 664 patients with PTC (> 10.0 mm) in Hangzhou First People’s Hospital affiliated to Westlake University Medical School from Jan. 2010 to Aug. 2023 were retrospectively analyzed, and the independent risk factors of PTMC and PTC CLNM were identified by univariate and multivariate logistic regression analysis. According to different gender and HT status, the patients were divided into male group, female group, HT group and non-HT group. The optimal age threshold and diagnostic efficacy of CLNM in each subgroup were determined by Receiver operating characteristic area under the curve (AUC) .Results:The proportion of CLNM in 3451 PTMCs and 664 PTCs was 27.2% (937/3451) and 58.9% (391/664) ( χ2=256.565, P<0.050), respectively. Univariate and multivariate regression analysis showed that larger tumor ( OR 1.230), male ( OR 2.085), older age ( OR 0.960) and HT ( OR 0.697) were independent predictors of the occurrence of CLNM in PTMC. Only male ( OR 1.460) and older ( OR 0.963) PTC were independently associated with CLNM. Subgroup analysis showed that the age-predicted AUC of CLNM in male, HT and non-HT patients in PTC were higher than that of PTMC, which were 0.642-0.689 and 0.635-0.659, respectively. The age thresholds of female, HT and non-HT subgroups in PTC were lower than those in PTMC, which were 38.5 to 39.5 years old and 41.5 to 42.5 years old, respectively. Conclusions:Larger tumor, male, older patients and HT can independently predict the risk of CLNM in PTMC, while only male and older people can independently predict the risk of CLNM in PTC. There are certain differences in the age of CLNM occurrence between PTMC and PTC patients with different genders and HT combination status. It is of great significance to correctly understand these differences for providing personalized clinical treatment.

Objective To explore the application effect of the anchored and paired classroom combined case teaching mode in the teaching of pediatric Surgery.Methods The five-year undergraduate students of pediatrics in Guangzhou Medical U-niversity from September 2022 to June 2024 were selected as the research objects.Traditional teaching mode was used as the con-trol group,and the anchored and paired classroom combined case teaching mode was used as the research group.According to the"Teaching Evaluation Form",the learning process,learning effect,classroom atmosphere and teaching strategies were evaluated,and the test results of the two groups of medical students were compared,so as to evaluate the degree of students'mastery of bas-ic knowledge and clinical thinking ability.Results The study group scored higher than the control group,and the difference was statistically significant(P＜0.05).Conclusion The anchored and paired classroom combined case teaching mode can improve the teaching quality of Pediatric Surgery,improve the classroom atmosphere,and enhance the learning interest and autonomy of medical students.

Objective To explore the application effect of the anchored and paired classroom combined case teaching mode in the teaching of pediatric Surgery.Methods The five-year undergraduate students of pediatrics in Guangzhou Medical U-niversity from September 2022 to June 2024 were selected as the research objects.Traditional teaching mode was used as the con-trol group,and the anchored and paired classroom combined case teaching mode was used as the research group.According to the"Teaching Evaluation Form",the learning process,learning effect,classroom atmosphere and teaching strategies were evaluated,and the test results of the two groups of medical students were compared,so as to evaluate the degree of students'mastery of bas-ic knowledge and clinical thinking ability.Results The study group scored higher than the control group,and the difference was statistically significant(P＜0.05).Conclusion The anchored and paired classroom combined case teaching mode can improve the teaching quality of Pediatric Surgery,improve the classroom atmosphere,and enhance the learning interest and autonomy of medical students.