Objective To evaluate the performance of the artificial intelligence (AI)-enabled snail identification system for recognition of Oncomelania hupensis robertsoni and Tricula in schistosomiasis-endemic areas of Yunnan Province. Methods Fifty O. hupensis robertsoni and 50 Tricula samples were collected from Yongbei Township, Yongsheng County, Lijiang City, a schistosomiasis-endemic area in Yunnan Province in May 2024. A total of 100 snail sample images were captured with smartphones, including front-view images of 25 O. hupensis robertsoni and 25 Tricula samples (upward shell opening) and back-view images of 25 O. hupensis robertsoni and 25 Tricula samples (downward shell opening). Snail samples were identified as O. hupensis robertsoni or Tricula by schistosomiasis control experts with a deputy senior professional title and above according to image quality and morphological characteristics. A standard dataset for snail image classification was created, and served as a gold standard for recognition of snail samples. A total of 100 snail sample images were recognized with the AI-enabled intelligent snail identification system based on a WeChat mini program in smartphones. Schistosomiasis control professionals were randomly sampled from stations of schistosomisis prevention and control and centers for disease control and prevention in 18 schistosomiasis-endemic counties (districts, cities) of Yunnan Province, for artificial identification of 100 snail sample images. All professionals are assigned to two groups according the median years of snail survey experiences, and the effect of years of snail survey experiences on O. hupensis robertsoni sample image recognition was evaluated. A receiver operating characteristic (ROC) curve was plotted, and the sensitivity, specificity, accuracy, Youden’s index and the area under the curve (AUC) of the AI-enabled intelligent snail identification system and artificial identification were calculated for recognition of snail sample images. The snail sample image recognition results of AI-enabled intelligent snail identification system and artificial identification were compared with the gold standard, and the internal consistency of artificial identification results was evaluated with the Cronbach’s coefficient alpha. Results A total of 54 schistosomiasis control professionals were sampled for artificial identification of snail sample image recognition, with a response rate of 100% (54/54), and the accuracy, sensitivity, specificity, Youden’s index, and AUC of artificial identification were 90%, 86%, 94%, 0.80 and 0.90 for recognition of snail sample images, respectively. The overall Cronbach’s coefficient alpha of artificial identification was 0.768 for recognition of snail sample images, and the Cronbach’s coefficient alpha was 0.916 for recognition of O. hupensis robertsoni snail sample images and 0.925 for recognition of Tricula snail sample images. The overall accuracy of artificial identification was 90% for recognition of snail sample images, and there was no significant difference in the accuracy of artificial identification for recognition of O. hupensis robertsoni (86%) and Tricula snail sample images (94%) (χ² = 1.778, P > 0.05). There was no significant difference in the accuracy of artificial identification for recognition of snail sample images with upward (88%) and downward shell openings (92%) (χ² = 0.444, P > 0.05), and there was a significant difference in the accuracy of artificial identification for recognition of snail sample images between schistosomiasis control professionals with snail survey experiences of 6 years and less (75%) and more than 6 years (90%) (χ² = 7.792, P < 0.05). The accuracy, sensitivity, specificity and AUC of the AI-enabled intelligent snail identification system were 88%, 100%, 76% and 0.88 for recognition of O. hupensis robertsoni snail sample images, and there was no significant difference in the accuracy of recognition of O. hupensis robertsoni snail sample images between the AI-enabled intelligent snail identification system and artificial identification (χ² = 0.204, P > 0.05). In addition, there was no significant difference in the accuracy of artificial identification for recognition of snail sample images with upward (90%) and downward shell openings (86%) (χ² = 0.379, P > 0.05), and there was a significant difference in the accuracy of artificial identification for recognition of snail sample images between schistosomiasis control professionals with snail survey experiences of 6 years and less and more than 6 years (χ² = 5.604, P_adjusted < 0.025). Conclusions The accuracy of recognition of snail sample images is comparable between the AI-enabled intelligent snail identification system and artificial identification by schistosomiasis control professionals, and the AI-enabled intelligent snail identification system is feasible for recognition of O. hupensis robertsoni and Tricula in Yunnan Province.

Objective To evaluate cardiac involvement in patients with anti-neutrophil cytoplasmic antibody-associated vasculitis (AAV) using echocardiography combined with electrocardiography. Methods A retrospective analysis was performed on the detailed medical records of AAV patients treated in Jining First People’s Hospital between January 2020 and December 2024. Eighty patients were enrolled in the AAV group, and the risk of heart disease was compared between the AAV group and a control group with 80 subjects matched for age, sex, and cardiovascular disease risk factors. Results Electrocardiographic abnormalities were observed in 78.75% of patients in the AAV group, while significant electrocardiographic abnormalities only occurred in symptomatic patients in the control group. There were no differences in left atrial enlargement or interventricular septal thickening between the AAV group and the control group. The overall left ventricular systolic function in the AAV group was lower than that in the control group (8.75% vs. 0). The incidence of reduced diastolic function in the AAV group was significantly higher than that in the control group (37.5% vs. 15%). The incidence rates of tricuspid regurgitation, mitral regurgitation, aortic regurgitation, and pericardial effusion in the AAV group were significantly higher than those in the control group. Pericardial thickening, aortic stenosis, pulmonary hypertension, and rare periaortic granulomas were found in the AAV group, but not in the control group. Conclusion Echocardiography and electrocardiography are important examination methods for evaluating cardiac involvement in AAV. These methods have key roles in disease screening, diagnosis and treatment, follow-up, and prognosis judgment.

Objective To investigate the relationship between between the levels of serum malondialdehyde(MDA)and superoxide dismutase(SOD),the balance of oxidative/antioxidant stress,and the prognostic nu-tritional index(PNI)and the risk of early neurological deterioration in patients with acute ischemic stroke(AIS).Methods A total of 95 patients with suspected AIS admitted to the Second People's Hospital of Fos-han,Foshan from January to April 2023 were selected as the research subjects.Among them,71 patients who were finally diagnosed with AIS were included in the stroke group,and the remaining 24 non-AIS patients were included in the control group.According to the National Institutes of Health Stroke Rating Scale(NIH-SS)score,the stroke group was divided into the moderate-severe stroke group and the mild stroke group.Ac-cording to whether early neurological deterioration(END)occurred,it was divided into the END group and the non-END group.To analyze the correlations between the levels of serum SOD and MDA,SOD/MDA,and the PNI and the severity of stroke.The receiver operating characteristic(ROC)curve was applied to evaluate the predictive value of each index for the risk of END.By fitting the indicators with high diagnostic efficacy,a Fisher discriminant function model for evaluating the risk of END was established to verify the overall accura-cy rate.Results The levels of serum MDA and SOD,SOD/MDA and the PNI in the moderate to severe stroke group were statistically different from those in the mild stroke group(P＜0.05).There were statistically sig-nificant differences in the levels of serum MDA and SOD,SOD/MDA and the PNI among the END group,the non-END group and the control group(P＜0.05).The areas under the curve(AUC)of SOD,MDA,SOD/MDA and PNI for evaluating END were 0.692,0.727,0.777 and 0.819,respectively.The Fisher discriminant function model established by fitting the NIHSS score,the SOD/MDA and the PNI has an overall accuracy rate of 85.9％.Conclusion The END risk prediction model established by applying the Fisher discriminant function can provide early and objective reference basis for clinical prediction of END risk and has certain practical value.

Objective To construct a visual intelligent recognition model for Oncomelania hupensis robertsoni in Yunnan Province based on the EfficientNet-B4 model, and to evaluate the impact of data augmentation methods and model hyperparameters on the recognition of O. hupensis robertsoni. Methods A total of 400 O. hupensis robertsoni and 400 Tricula snails were collected from Yongsheng County, Yunnan Province in June 2024, and snail images were captured following identification and classification of 300 O. hupensis robertsoni and 300 Tricula snails. A total of 925 O. hupensis robertsoni images and 1 062 Tricula snail images were collected as a dataset and divided into a training set and a validation set at a ratio of 8:2, while 352 images captured from the remaining 100 O. hupensis robertsoni and 354 images from the remaining 100 Tricula snails served as an external test set. All acquired images were subjected to preprocessing, including cropping and resizing. Three data augmentation approaches were employed, including baseline, Mixup and Gaussian blurring, and model hyperparameters included two optimization algorithms of adaptive moment estimation (Adam) and stochastic gradient descent (SGD), two loss functions of focal loss and cross entropy loss, and two learning rate decay strategies of cosine annealing and multi-step. The intelligent recognition models of O. hupensis robertsoni and Tricula snails were constructed based on the EfficientNet-B4 model, and 7 training strategy groups were generated by combinations of different data augmentation approaches and hyperparameters. The performance of intelligent recognition models was tested with external test sets, and evaluated with accuracy, precision, recall, F1 score, loss, Youden’s index, and the area under the receiver operating characteristic curve (AUC) under different training strategies. Results The variation of loss values was comparable among intelligent recognition models with different data augmentation approaches. The Group 4 model constructed with Mixup and Gaussian blurring data augmentation approaches showed the optimal performance, with an accuracy of 90.38%, precision of 90.07%, F1 score of 89.44%, Youden’s index of 0.81 and AUC of 0.961 in the external test set. The accuracy of models using the SGD optimizer reduced by 29.16% as compared to those using the Adam optimizer (χ² = 81.325, P < 0.001), and the accuracy of models using the cross entropy loss function reduced by 0.80% as compared to the Group 4 model (χ² = 3.147, P > 0.05), while the accuracy of models using the multi-step learning rate decay strategy increased by 0.65% as compared to the Group 4 model (χ² = 0.208, P > 0.05). In addition, the model with the baseline + Mixup + Gaussianblurring data augmentation approach and hyperparameters of Adam optimizer, focal loss function and multi-step learning rate decay strategy showed the highest performance, with an accuracy of 91.03%, precision of 91.97%, recall of 88.11%, F1 score of 90.00%, Youden’s index of 0.82 and AUC values of 0.969 in external test set, respectively. Conclusions The intelligent recognition model of O. hupensis robertsoni based on EfficientNet-B4 model is accurate for identification of O. hupensis robertsoni and Tricula snails in Yunnan Province.

OBJECTIVE: To analyze the clinical features and genotype of a child with Schmid type metaphyseal chondrodysplasia. METHODS: Clinical data of the child and her parents was collected. The child was subjected to high-throughput sequencing, and candidate variant was verified by Sanger sequencing of her family members. RESULTS: Whole exome sequencing revealed that the child has harbored a heterozygous c.1772G>A (p.C591Y) variant of the COL10A1 gene, which was not found in either of her parents. The variant was not found in the HGMD and ClinVar databases, and was rated as likely pathogenic based on the guidelines from the American College of Medical Genetics and Genomics (ACMG). CONCLUSION The heterozygous c.1772G>A (p.C591Y) variant of the COL10A1 gene probably underlay the Schmid type metaphyseal chondrodysplasia in this child. Genetic testing has facilitated the diagnosis and provided a basis for genetic counselling and prenatal diagnosis for this family. Above finding has also enriched the mutational spectrum of the COL10A1 gene.
Humans ; Child ; Female ; Mutation ; Osteochondrodysplasias/diagnosis* ; Heterozygote ; Molecular Biology

Objective To investigate the factors affecting the vaginal birth after cesarean (VBAC). Methods Totaly 298 women who underwent trial of labor after cesarean section (TOLAC) from Jan 2015 to Dec 2015 were recruited from Beijing Obstetrics and Gynecology Hospital, FuXing Hospital, Tongzhou Maternal and Child Health Hospital of Beijing, the Second Affiliated Hospital of Chongqing Medical University and the People′s Hospital of Chengyang District of Qingdao. The maternal age, the interval from the last cesarean section, the body mass index (BMI) before pregnancy, the weight gain during pregnancy, the way into labor, the Bishop score before labor, the gestational age and the birth weight of the neonate were recorded in a self-made form. The factors affecting VBAC were analyzed by univariate analysis and multivariable logistic regression. Results (1)The incidence of VBAC, uterine rupture, postpartum hemorrhage and neonatal asphyxia were 70.5%(210/298), 2.7%(8/298), 9.4% (28/298) and 1.3% (4/298), respectively. No maternal death and perinatal death occurred. (2)The univariate analysis suggested that the maternal age, the BMI before pregnancy, the Bishop score before labor, the labor induction, the gestational age at delivery and the neonatal weight were factors affecting VBAC. The maternal age and the Bishop score before labor were significantly higher in the VBAC group than in the unsuccessful TOLAC group(P<0.05). While the BMI before pregnancy, the induction rate, the gestational weeks at delivery and the birth weight of the neonate were significantly lower in the VBAC group than in the unsuccessful TOLAC group (P<0.05). Multivariable logistic regression analysis showed that successful VBAC was affected by the maternal age, the BMI before pregnancy, the Bishop score before labor and the birth weight of the neonates(P<0.05). Conclusion The maternal age, the BMI before pregnancy, the Bishop score before labor and the birth weight of neonate are the main factors affecting VBAC.

Objective To investigate the role of large-diameter magnetic resonance imaging (MRI) simulation in target volume delineation in radiotherapy for nasopharyngeal carcinoma (NPC).Methods Eighteen patients with NPC underwent computed tomography (CT) simulation and MRI simulation scans and localization in the same body position,with SOMATOM Sensation Open 40-row 82-cm large-diameter CT simulator and Siemens 3T MRI MAGNETOM Skyra 70-cm large-diameter simulator,respectively.The gross tumor volume (GTV) and parotid glands were delineated on all images according to the ICRU Report 50/62,and MRI was applied to observe the changes in GTV and parotid volume during radiotherapy.Paired t-test was applied to analyze the differences between GTVCT and GTVMRI and between GTVnx-CT and GTVnx-MRI.Results GTVMRI decreased significantly compared with GTVCT,and the average volume decreased from (213.64±84.59) cm3 to (199.68±84.69) cm3(p=0.006).As for the volume of primary lesions in the nasopharynx,GTVnx-MRI was significantly smaller than GTVnx-CT,and the volume decreased from (95.75± 24.76) cm3 to (88.12±26.25) cm3 (P =0.001);as for the volume of cervical lymph nodes,GTVnd-MRI was significantly smaller than GTVnd-CT,and the volume decreased from (117.89± 72.69) cm3 to (111.56± 70.69) cm3 (P=0.018).The targets delineated by CT and MRI did not overlap completely,with major differences in skull base bone and cervical soft tissue.The volume of both parotid glands delineated on MRI image was higher than that delineated on CT image,with a major difference in the deep lobe.MRI showed that GTV was reduced by 82.64± 16.87％ during radiotherapy,and the volumes of the left and right parotid glands were reduced by (32.7± 23.95) ％ and (34.7± 21.72) ％,respectively.Conclusions The delineation of target volume based on MRI simulation is more accurate than that based on CT simulation and can achieve a smaller volume range,which helps to guide target volume delineation in radiotherapy for NPC accurately.

[ABSTRACT]AIM:Toinvestigatetheeffectofsilencingisocitratedehydrogenase2(IDH-2)genebysmallinter-fering RNA (siRNA) on the biological characteristics of human small cell lung cancer cell line NCI -H446.METHODS:IDH-2 expression was knocked down in human small cell lung cancer cell line NCI -H446 by siRNA-IDH-2.The expression level of IDH-2 was determined by real-time PCR and Western blotting .The cell proliferation was measured by CCK-8 as-say , the protein expression of MAPK p 42 was detected by Western blotting , and the cell cycle was analyzed by flow cytome-try.The migration was observed using Transwell cell migration system .BALB/c nude mice were subcutaneously injected on the back with NCI-H446 cells transfected with siRNA-IDH-2/negative control siRNA or non-transfected cells to study the tumor growth .RESULTS:siRNA-IDH-2 remarkably down-regulated the expression of IDH-2 and MAPK p42 in the NCI-H446 cells.siRNA-IDH-2 inhibited both the proliferation and migration abilities of NCI-H446 cells, and the cell cycle was arrested in S phase as compared with negative control group .Additionally, the volume of xenograft tumors in siRNA-IDH-2 group was significantly decreased as compared with control group .CONCLUSION:siRNA-IDH-2 down-regulates the expres-sion of IDH-2 in NCI-H446 cells, reduces the cell migration efficiency and inhibits the tumor growth in vitro and in vivo.