Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Objective:To apply artificial intelligence（AI）in classifying ovarian tumors on ultrasound images，and compare the diagnostic results of several sonographers with varying seniority levels.Methods:A total of 645 patients diagnosed with adnexal masses via gynecological ultrasound examination at Qilu Hospital of Shandong University from January 2021 to December 2024 were enrolled. Three deep learning architectures，i.e.，Alexnet，Densenet121，and Resnet50 were developed and used to internally test the classification effectiveness of ovarian tumors，while the optimal model was selected for external testing. Two junior sonographers and two senior sonographers were recruited to independently diagnose ovarian tumors in the external test dataset. Subsequently，the benign and malignant results of the model's predictions were disclosed to each sonographer，and their revised diagnoses on the same external test data in combination with the best AI model were recorded.Results:The optimal model achieved an accuracy of 0.941，sensitivity of 0.936，and specificity of 0.944 on the internal test dataset，and maintained robust performance on the external test dataset with accuracy of 0.891，sensitivity of 0.880，and specificity of 0.907. Compared to junior sonographers，the optimal model demonstrated significantly higher sensitivity in discriminating benign from malignant ovarian tumors（0.880 vs. 0.723，0.602；all P<0.05）. No statistically significant difference was observed in diagnostic accuracy between the optimal model and senior sonographer 1（ P=0.05）. With assistance from the optimal model，junior sonographers achieved significant improvements in both sensitivity and specificity（sensitivity：0.723 vs. 0.843，0.602 vs. 0.819；specificity：0.778 vs. 0.833，0.685 vs. 0.741；all P<0.05）. Conclusions:The optimal model achieves comparable performance to that of senior sonographers in ovarian tumor classification. With model assistance，the diagnostic performance of junior sonographers is significantly improved.

Objective : To investigate the association between c. 1311C > T and c. 1004C > A of glucose⁃6 ⁃phosphate dehydrogenase (G6PD) gene single nucleotide polymorphism ( SNP) with the risk of G6PD deficiency in Guangxi population. Methods : 417 patients with G6PD deficiency were randomly selected as case group , and 295 healthy patients were selected as control group. The c. 1311C > T and c. 1004C > A were genotyped using the SNPscanTM multiple SNP method , and the haplotype frequency of two sites were analyzed by SHEsis. Results : In the case and control group , there were statistically significant differences in the distribution frequency of genotype TT , CC + CT and allele T at c. 1311C > T locus [TT vs CC :(P = 0. 001 , OR = 0. 373 , 95% CI = 0. 204 - 0. 683) ; TT vs CC + CT :(P = 0. 001 , OR = 0. 371 , 95% CI = 0. 203 - 0. 678) ; T vs C :(P = 0. 002 , OR = 0. 601 , 95% CI = 0. 435 - 0. 829)] ;however, there was no significant difference in genotype and allele distribution frequency at c. 1004C > A locus (P > 0. 05) . The results of the rate method showed that compared with genotype CC , the genotype CT at c. 1311C > T increased the expression level of G6PD enzyme , while the genotype TT decreased the expression level of G6PD enzyme(P < 0. 05) , the haplotype analysis showed that C ⁃C and T ⁃C were associated with G6PD risk (P < 0. 05) . Conclusion In Guangxi population , c. 1311C > T locus genotypes TT , CC + CT and allele T were related to the decreased risk of G6PD deficiency.

Objective : To investigate the association between c. 1311C > T and c. 1004C > A of glucose⁃6 ⁃phosphate dehydrogenase (G6PD) gene single nucleotide polymorphism ( SNP) with the risk of G6PD deficiency in Guangxi population. Methods : 417 patients with G6PD deficiency were randomly selected as case group , and 295 healthy patients were selected as control group. The c. 1311C > T and c. 1004C > A were genotyped using the SNPscanTM multiple SNP method , and the haplotype frequency of two sites were analyzed by SHEsis. Results : In the case and control group , there were statistically significant differences in the distribution frequency of genotype TT , CC + CT and allele T at c. 1311C > T locus [TT vs CC :(P = 0. 001 , OR = 0. 373 , 95% CI = 0. 204 - 0. 683) ; TT vs CC + CT :(P = 0. 001 , OR = 0. 371 , 95% CI = 0. 203 - 0. 678) ; T vs C :(P = 0. 002 , OR = 0. 601 , 95% CI = 0. 435 - 0. 829)] ;however, there was no significant difference in genotype and allele distribution frequency at c. 1004C > A locus (P > 0. 05) . The results of the rate method showed that compared with genotype CC , the genotype CT at c. 1311C > T increased the expression level of G6PD enzyme , while the genotype TT decreased the expression level of G6PD enzyme(P < 0. 05) , the haplotype analysis showed that C ⁃C and T ⁃C were associated with G6PD risk (P < 0. 05) . Conclusion In Guangxi population , c. 1311C > T locus genotypes TT , CC + CT and allele T were related to the decreased risk of G6PD deficiency.

Objective To observe the efficacy and safety of levofloxacin for the theatment of com-munity acquired pneumonia(CAP) in the elderly patients. Methods Thirty-six elderly inpatients with CAP between May 2005 and May 2007 were treated with levofloxacin at a dosage intravenously of 500 mg once a day for 5 to 14 days treatment. Results Streptococcus pneumoniae of multiple drugs-resistant were found in sputum of 22 patients,pseudomonas aeruginosa in 8 patients and haemophilus influenzae in 6 patients de-pending on the results of the sputum culture. The total clinical efficacy rate of levofloxacin was 75.0% and bacteria elimination rate was 82.1%,and 16.7% patients showed related side effect of diarrhea,skin-rash and kidney injury. Conclusions Levofloxacin is an effective with little side effect in treatment of CAP in the elderly.