Objective To explore the effectiveness of multimodal comprehensive diabetes management teaching in the standardized training of endocrinology residents.Methods Fifty-nine resident physicians rotating through the endocrinology department from March to October 2024 were selected.They underwent a multimodal comprehensive diabetes management teaching model that integrated standardized theoretical instruction,case dis-cussions,teaching ward rounds,practical operations,and interdisciplinary pharmaceutical education.The effec-tiveness of this teaching model was evaluated through multiple dimensions using a comprehensive diabetes man-agement evaluation form,Mini-Clinical Evaluation Exercise(Mini-CEX)scale,and satisfaction surveys.Results After two months of multimodal standardized training,the results showed:1)The resident physicians demonstra-ted significant improvements in all aspects of comprehensive diabetes management(P＜0.05).2)The Mini-CEX scores of the resident physicians generally reached excellent levels(P＜0.05).3)Both the resident physicians and teaching faculty showed significantly higher satisfaction with the comprehensive diabetes management program after the training(P＜0.05).Conclusions Multimodal comprehensive diabetes management teaching is effective in enhancing the standardized diagnosis and treatment abilities of resident physicians in the endocrinology depart-ment regarding diabetes.

Crigler-Najjar syndrome(CNS)is an autosomal recessive genetic disorder caused by mutations in the UGT1A1 gene.This author retrospectively analyzes the clinical data of one patient presenting with postnatal hyperbilirubinemia,who was genetically diagnosed with CNS.Her clinical course,genetic characteristics,diagnostic and therapeutic approaches are discussed to enhance clinicians'understanding of this condition.The patient exhibited recurrent jaundice due to elevated unconjugated bilirubin(UCB)levels since birth.During this period,the gallstones were identified and surgically removed,yet her bilirubin levels did not improve.In March 2024,the patient presented to our hospital and underwent genetic testing via a third-party facility.The results revealed two risk variants in the UGT1A1 gene.After one week of oral phenobarbital administration,her UCB levels decreased by approximately 47%,confirming a diagnosis of CNS type Ⅱ.The patient is currently under active follow-up with regular monitoring of bilirubin levels.For the infants and children presenting with persistent,fluctuating,non-hemolytic,and non-hepatitic hyperbilirubinemia since birth,early genetic testing should be prioritized to establish the definitive diagnosis.

Objective To investigate the feasibility and accuracy of an ultrasound-based transfer learning artificial intelligence model in predicting the malignancy probability of partially cystic thyroid nodules(PCTN).Methods A retrospective analysis was conducted on 246 patients with PCTN who had definitive pathological results and were admitted to Weihai Municipal Hospital,Cheeloo College of Medicine,Shandong University from January 2021 to December 2023.Patients were randomly divided into training and test cohorts at a ratio of 7:3.Ultrasonic image features of PCTN were evaluated,and independent risk factors were identified using multivariate logistic regression analysis,with the area under the curve(AUC)subsequently calculated.Additionally,five different pre-trained models-Inception_v3,EfficientNet,VGG19,ResNet50,and DenseNet121-were selected for transfer learning after data preprocessing using the PyTorch framework in Python.The AUC values of these models were calculated and compared.Results Solid portion greater than 50%,eccentric acute angle,ill-defined margin,spiculated or microlobulated margin,rim calcification,and microcalcification exhibited statistically significant differences(P<0.05)in distinguishing between benign and malignant PCTN.The AUC value derived from these independent risk factors was 0.843.Furthermore,among the five transfer learning models evaluated,the ResNet50 model demonstrated the highest diagnostic efficiency,achieving an AUC value of 0.903 2.Conclusion The ultrasound-based transfer learning artificial intelligence model demonstrated superior performance compared to traditional ultrasound image evaluation methods,enabling accurate prediction of the nature of PCTN and thereby reducing unnecessary ultrasound-guided fine needle biopsies.

Objective To investigate the feasibility and accuracy of an ultrasound-based transfer learning artificial intelligence model in predicting the malignancy probability of partially cystic thyroid nodules(PCTN).Methods A retrospective analysis was conducted on 246 patients with PCTN who had definitive pathological results and were admitted to Weihai Municipal Hospital,Cheeloo College of Medicine,Shandong University from January 2021 to December 2023.Patients were randomly divided into training and test cohorts at a ratio of 7:3.Ultrasonic image features of PCTN were evaluated,and independent risk factors were identified using multivariate logistic regression analysis,with the area under the curve(AUC)subsequently calculated.Additionally,five different pre-trained models-Inception_v3,EfficientNet,VGG19,ResNet50,and DenseNet121-were selected for transfer learning after data preprocessing using the PyTorch framework in Python.The AUC values of these models were calculated and compared.Results Solid portion greater than 50%,eccentric acute angle,ill-defined margin,spiculated or microlobulated margin,rim calcification,and microcalcification exhibited statistically significant differences(P<0.05)in distinguishing between benign and malignant PCTN.The AUC value derived from these independent risk factors was 0.843.Furthermore,among the five transfer learning models evaluated,the ResNet50 model demonstrated the highest diagnostic efficiency,achieving an AUC value of 0.903 2.Conclusion The ultrasound-based transfer learning artificial intelligence model demonstrated superior performance compared to traditional ultrasound image evaluation methods,enabling accurate prediction of the nature of PCTN and thereby reducing unnecessary ultrasound-guided fine needle biopsies.

Objcetive: To explore the treatment of long segment defect of tibia by using tensor fascia lata combined with iliac flap or deep circumflex iliac pedicle iliac flap. Methods: From February 2012 to August 2017, The People′s Hospital of Zun Yi City Bo Zhou District treated 16 patients who had long segment defect of tibia.There were 11 males and 5 females, age from 22 to 58 years old, the average age was 42 years old. Iliac flap grafting with tensor fascia lata combined with iliac flap or deep circumflex iliac pedicle was used to treat the defect of long segment of tibia. There were 4 cases with simple tibial defect and 12 cases with skin defect. The longest tibial defect was 5-8 cm. Results: In this study, four patients used iliac flaps with deep circumflex iliac pedicle, the area of flaps ranged from 2.5 cm×5.0 cm to 5.0 cm×10.0 cm, while the area of iliac flaps ranged from 5.0 cm×2.5 cm to 8.0 cm×4.0 cm. Twelve patients used grafting with tensor fascia lata combined with iliac flap, the area of flaps ranged from 5.0 cm×12.0 cm to 12.0 cm×23.0 cm, while the area of iliac flaps ranged from 7.0 cm×2.0 cm to 8.0 cm×4.0 cm. All 16 cases of bone flap were survived, fracture healing, without surgical complications. The average follow-up period was 1.5 years, the flaps had good appearance in 10 cases and was slightly bloated in 6 cases; the ankle had normal motion in 14 cases and had poor dorsal extension in 2 cases. X-ray films showed that the bone flap repaired the bone defects and reached bone healing. Conclusions Vascularized tensor fascia lata combined with iliac flap or deep circumflex iliac pedicle iliac flap grafts increase local blood supply and accelerate the process of fracture healing.

Objective:To explore the diagnostic value of mammography and ultrasonography(US)in diagnosis of breast disease with microcalcifications.Methods:Seventy-eight cases with breast microcalcifications were detected by mammography.The detection rate of breast microcalcification at US was analyzed.And the sensitivity,specificity and the accuracy of US in diagnosis breast disease with microcalcifications was compared with these of mammography.Results:The detection rate of breast microcalcification was 66.7%,And US depicted more malignant(87.5%)than benign microcalcification(33.3%).The sensitivity specificity and accuracy of US was 68.7%、83.3%、 74.3%respectively,and the sensitivity specificity and accuracy of mammography was 72.9%、 73.3%、75.6%respectively,there were no significant difference between the two methods.The sensitivity,specificity and accuracy of the combined the two methods was 89.6%,90.0%,92.3% respectively.Conclusion:US can effectively detect and identify the breast microcalicications.The combination can improve the assessment of breast disease with microcalicications,and has a significant clinical practical value in diagnosis of early breast cancer.

Objective To study the diagnostic value of mammography and high-frequency ultrasound in diagnosis of early breast carcinoma.Methods Sixty-five female patients with breast carcinoma were all confirmed by surgery and pathological examinations. All the patients were examined by the high-frequency ultrasound as well as mammography.Results The positive diagnostic rate,the display of tumor shadow and malignant microcalcification with high-frequency ultrasound and mammography were as follows :64.6%(42/65)and 46%(30/ 65),62%(40/65)and 20%(13/65),40%(26/65)and 20%(13/65)respectively. The difference was considered statistically significant(P