Objective Objective To analyze the potential spatial factors affecting the genetic differentiation of Oncomelania hupensis robertsoni in Yunnan Province. Methods A total of 13 administrative villages were selected from schistosomiasis-endemic areas of Yunnan Province as O. hupensis snail sampling sites. At least 200 snails were collected in each site, and the spatial variable data of each site were recorded, including longitude, latitude and altitude. Thirty active and Schistosoma japonicum uninfected O. hupensis snails were selected from each sampling site by means of the crawling method and the cercarial shedding method. Genomic DNA was extracted from O. hupensis snails. Following PCR amplification, purification of PCR amplification products and sequencing, the gene sequences of O. hupensis snail samples were spliced and edited using the DNAstar software and the NCBI database to yield the complete mitochondrial sequences of O. hupensis snails at each sampling site, and the mitochondrial genetic distance matrix of O. hupensis robertsoni was calculated at each sampling site. The geographical coordinates of each sampling site were marked using the software ArcGIS 10.2, and the straight-line geographical distance between each sampling site was calculated. The altitude difference, longitude difference and latitude difference between each sampling site were calculated using the Excel software, and the correlation between the mitochondrial genetic distance matrix of O. hupensis robertsoni and each spatial variable matrix was examined by using the Mantel test at 13 sampling sites in Yunnan Province. Results Among the 13 O. hupensis snail sampling sites in Yunnan Province, the largest mitochondrial genetic distance of O. hupensis robertsoni snail populations was seen between Anding Village, Nanjian Yi Autonomous County and Caizhuang Village, Midu County (26.244 2), and the largest geographical distance was seen between Dongyuan Village, Gucheng District and Cangling Village, Chuxiong County (272.64 km). The highest altitude difference was seen between Anding Village, Nanjian Yi Autonomous County and Dongyuan Village, Gucheng District (1 086.10 m), and the largest longitude difference was found between Qiandian Village, Eryuan County and Cangling Village, Chuxiong County (1.86°), while the largest latitude difference was measured between Leqiu Village, Nanjian Yi Autonomous County and Dongyuan Village, Gucheng District (1.81°). In addition, the mitochondrial genetic distance of O. hupensis robertsoni snail populations was positively correlated with altitude at 13 snail sampling sites in Yunnan Province (r = 0.542 8, P < 0.001), and showed no significant correlations with geographical distance (r = 0.093 4, P > 0.05), longitude (r = −0.199 5, P > 0.05) or latitude (r = 0.205 7, P > 0.05). Conclusion Altitude may be a potential spatial factor affecting the genetic differentiation of O. hupensis robertsoni in Yunnan Province.

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 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.

Image 1.

Objective:To analyze the differences in endoscopic and pathological features in autoimmune gastritis (AIG) patients with and without Helicobacter pylori ( HP) infection, and to explore the effects of HP on the clinical manifestations and disease development in AIG patients. Methods:From January 2022 to April 2024, 174 AIG patients who visited Beijing Hospital and met the 2022 AIG diagnostic criteria established by Japanese Gastroenterological Endoscopy Society were enrolled and divided into the HP-infected group (including current and previous infection, 77 cases) and the HP-unifected group (97 cases). The general clinical data, laboratory examinations endoscopic findings, and pathological characteristics of the two groups were analyzed. Independent sample t-test and chi-square test were used for statistical analyses. Results:The vitamin B 12 level of HP-infected group was higher than that of HP-unifected group ((573.81±460.77) ng/L vs. (411.86±335.00) ng/L), and the difference was statistically significant ( t=-2.57, P=0.011). The average red blood cell volume of HP-infected group was lower than that of HP-unifected group ((87.30±8.86) fL vs. (98.50±49.82) fL), and the difference was statistically significant ( t=2.16, P=0.033). The proportion of intestinal metaplasia in gastric fundus in HP-infected group was lower than that in HP-unifected group (50.6% (39/77) vs. 73.2% (71/97)), and the difference was statistically significant ( χ2=9.38, P=0.002). Conclusion:HP infection in AIG patients may delay the malabsorption of vitamin B 12 and the occurrence of intestinal metaplasia in gastric fundus.

Objective:To construct a prediction model for the risk of sarcopenia in middle-aged and elderly patients with knee osteoarthritis (KOA) based on machine learning, and to provide a basis for carrying out the prevention of sarcopenia in patients with KOA.Methods:Clinical data of KOA patients from three tertiary hospitals in Guangdong Province were collected between December 2023 and September 2024 using a convenience sampling method. The data were randomly split into training and test sets at an 8:2 ratio, with the occurrence of sarcopenia as the outcome variable. Risk prediction models for sarcopenia were constructed using eight machine learning algorithms: logistic regression, K-nearest neighbors, support vector machine, decision tree, neural network, random forest, gradient boosting machine (GBM), and eXtreme gradient boosting. Model performance was evaluated based on metrics including the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, specificity, and F1 score. The optimal model was selected, and feature importance was visualized using the Shapley Additive exPlanations (SHAP) method.Results:Data from 640 KOA patients were analyzed, 143 males and 497 females, (67.51± 7.72) years, with 136 cases (21.25%) developing sarcopenia. All eight prediction models showed high AUC values, with the GBM model demonstrating the best performance. Its metrics included an AUC of 0.926 (95% CI 0.874 - 0.965), accuracy of 0.852, precision of 0.611, sensitivity of 0.815, specificity of 0.861, and F1 score of 0.698. SHAP analysis identified body mass index, calf circumference, body fat percentage, WOMAC score, and age as the most important predictive features. Conclusions:The GBM-based risk prediction model for sarcopenia in middle- aged and elderly KOA patients demonstrated optimal performance, enabling healthcare professionals to accurately and promptly identify high-risk groups among these patients and to develop effective, evidence-based intervention strategies.

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 construct a prediction model for the risk of sarcopenia in middle-aged and elderly patients with knee osteoarthritis (KOA) based on machine learning, and to provide a basis for carrying out the prevention of sarcopenia in patients with KOA.Methods:Clinical data of KOA patients from three tertiary hospitals in Guangdong Province were collected between December 2023 and September 2024 using a convenience sampling method. The data were randomly split into training and test sets at an 8:2 ratio, with the occurrence of sarcopenia as the outcome variable. Risk prediction models for sarcopenia were constructed using eight machine learning algorithms: logistic regression, K-nearest neighbors, support vector machine, decision tree, neural network, random forest, gradient boosting machine (GBM), and eXtreme gradient boosting. Model performance was evaluated based on metrics including the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, specificity, and F1 score. The optimal model was selected, and feature importance was visualized using the Shapley Additive exPlanations (SHAP) method.Results:Data from 640 KOA patients were analyzed, 143 males and 497 females, (67.51± 7.72) years, with 136 cases (21.25%) developing sarcopenia. All eight prediction models showed high AUC values, with the GBM model demonstrating the best performance. Its metrics included an AUC of 0.926 (95% CI 0.874 - 0.965), accuracy of 0.852, precision of 0.611, sensitivity of 0.815, specificity of 0.861, and F1 score of 0.698. SHAP analysis identified body mass index, calf circumference, body fat percentage, WOMAC score, and age as the most important predictive features. Conclusions:The GBM-based risk prediction model for sarcopenia in middle- aged and elderly KOA patients demonstrated optimal performance, enabling healthcare professionals to accurately and promptly identify high-risk groups among these patients and to develop effective, evidence-based intervention strategies.

Objective:To analyze the differences in endoscopic and pathological features in autoimmune gastritis (AIG) patients with and without Helicobacter pylori ( HP) infection, and to explore the effects of HP on the clinical manifestations and disease development in AIG patients. Methods:From January 2022 to April 2024, 174 AIG patients who visited Beijing Hospital and met the 2022 AIG diagnostic criteria established by Japanese Gastroenterological Endoscopy Society were enrolled and divided into the HP-infected group (including current and previous infection, 77 cases) and the HP-unifected group (97 cases). The general clinical data, laboratory examinations endoscopic findings, and pathological characteristics of the two groups were analyzed. Independent sample t-test and chi-square test were used for statistical analyses. Results:The vitamin B 12 level of HP-infected group was higher than that of HP-unifected group ((573.81±460.77) ng/L vs. (411.86±335.00) ng/L), and the difference was statistically significant ( t=-2.57, P=0.011). The average red blood cell volume of HP-infected group was lower than that of HP-unifected group ((87.30±8.86) fL vs. (98.50±49.82) fL), and the difference was statistically significant ( t=2.16, P=0.033). The proportion of intestinal metaplasia in gastric fundus in HP-infected group was lower than that in HP-unifected group (50.6% (39/77) vs. 73.2% (71/97)), and the difference was statistically significant ( χ2=9.38, P=0.002). Conclusion:HP infection in AIG patients may delay the malabsorption of vitamin B 12 and the occurrence of intestinal metaplasia in gastric fundus.

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.