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 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 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 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.

Fibromyalgia syndrome （FMS） is a refractory， chronic non-articular rheumatic disease characterized by widespread pain throughout the body， for which there are no satisfactory therapeutic drugs or options. There are rich Chinese medical therapies， and some non-drug therapies， such as acupuncture， Tai Chi， and Ba-Duan-Jin， have shown satisfactory efficacy and safety and definite advantages of simultaneously adjusting mind and body. FMS is taken as a disease responding specifically to traditional Chinese medicine （TCM） by the National Administration of Traditional Chinese Medicine in 2018. In order to clarify the research progress in FMS and the clinical advantages of TCM/integrated Chinese and Western medicine， the China Academy of Chinese Medicine organized a seminar for nearly 20 experts in Chinese and Western medicine， including rheumatology， psychology， acupuncture and moxibustion， and encephalopathy， with the topic of difficulties in clinical diagnosis and treatment of FMS and advantages of TCM and Western medicine. The recommendations were reached on the difficulties in early diagnosis and solutions of FMS， mitigation of common non-specific symptoms， preferential analgesic therapy， TCM pathogenesis and treatment advantages， and direction of treatment with integrated Chinese and Western medicine. FMS is currently facing the triple dilemma of low early correct diagnosis， poor patient participation， and unsatisfactory benefit from pure Western medicine treatment. To solve the above problems， this paper suggests that rheumatologists should serve as the main diagnostic force of this disease， and they should improve patient participation in treatment decision-making， implement exercise therapy， and fully utilize the holistic and multidimensional features of TCM， which is effective in alleviating pain， improving mood， and decreasing adverse events. In addition， it is suggested that FMS treatment should rely on both TCM and Western medicine and adopt multidisciplinary joint treatment， which is expected to improve the standard of diagnosis and treatment of FMS in China.

Solenopsis invicta is a kind of invasive pest that causes serious damage to local agriculture, environment, and human health. They attack mainly with venom within stingers. Those who are allergic to the venom would suffer a systemic anaphylaxis, even fatal shock, after being stinged by these ants. Many studies reveal that their venom is mainly composed by water, insoluble alkaloids and trace proteins, within which alkaloids are the main cause of burning sensation and blisters, while allergic reactions are caused by proteins or peptides. The research progress of toxic substances in the venom of Solenopsis invicta as well as the roles and functions of each component were reviewed in this paper.

Objective:To assess the future risk of bleeding events and ischemic events in a two-year follow-up of elderly patients with acute coronary syndromes(ACS)who experienced upper gastrointestinal bleeding during hospitalization, and to analyze the related factors for the recurrence.Methods:This was a retrospective case-control study.Elderly ACS patients who underwent percutaneous coronary intervention(PCI)in Beijing Hospital from January 1, 2015 to December 31, 2018 were continuously included.According to whether upper gastrointestinal bleeding occurred during hospitalization, they were divided into the bleeding group(n=51)and the control group(n=2 834). Baseline data were compared between the two groups.The incidence of major adverse cardiovascular events(MACE)and the recurrence of bleeding defined by the Bleeding Academic Research Consortium(BARC)consensus classification were monitored during the 2-year followed-up.Related factors for clinically significant bleeding events(BARC type 2, 3 and 5)were analyzed.Results:The median bleeding time in the bleeding group was 3.3 days after PCI, and the main cause was gastroduodenal ulcer(43 cases, 84.3%). Compared with the control group, patients in the bleeding group had a lower body mass index, a higher proportion of patients with a history of atrial fibrillation, chronic kidney disease, peptic ulcer, ST-segment elevation myocardial infarction and non-ST-segment elevation myocardial infarction, higher usage rates of ticagrelor and oral anticoagulants, a lower usage rate of proton pump inhibitor(PPI), a higher proportion of patients with coronary artery disease involving ≥ 2 vessels, higher GRACE scores, higher usage rates of tirofiban and aspiration catheters and a lower complete revascularization rate( P<0.05). Patients were followed up for(22.4±1.5)months.Compared with the control group, the incidence of MACE(19 cases or 37.3% vs.698 cases or 24.6%, HR=1.655, 95% CI: 1.026-2.673, χ 2=4.513, P<0.05)and the recurrence of clinically significant bleeding(BARC type 2, 3 and 5)(10 cases or 19.6% vs.283 cases or 10.0%, HR=2.242, 95% CI: 1.209-4.157, χ2=5.083, P<0.05)increased in the bleeding group.Logistic multivariate regression analysis showed that age ≥70 years( RR=1.813, 95% CI: 1.021-3.219), chronic kidney disease ≥ stage 2( RR=1.623, 95% CI: 1.196-2.202), history of peptic ulcer( RR=2.152, 95% CI: 1.156-4.006), ticagrelor( RR=2.014, 95% CI: 1.253-3.237), and oral anticoagulants( RR=1.352, 95% CI: 1.032-1.771)were independent risk factors for clinically significant bleeding(BARC type 2, 3 and 5), and PPI was a protective factor( RR=0.573, 95% CI: 0.345-0.952). Conclusions:A history of upper gastrointestinal bleeding in elderly patients with ACS during hospitalization can increase the recurrence risk of clinically significant bleeding and MACE events in subsequent two years.Advanced age, chronic kidney disease ≥stage 2, a history of peptic ulcer, and preoperative use of ticagrelor and oral anticoagulants are independent risk factors for the recurrence risk of clinically significant bleeding, and PPI can decrease the recurrence risk of bleeding.

Objective To explore the correlation between the pathogenesis of coronary heart disease and the polymorphism of methylenetetrahydrofolate reductase ( MTHFR ) .Methods 130 cases of coronary heart disease diagnosed and treated in Heze Municiple Hospital from July 2015 to July 2017 were selected as observation group .At the same time,130 healthy people were selected as control group .The serum folate and homocysteine ( HCY) levels were compared between the two groups .At the same time, polymerase chain reaction -restriction fragment length polymorphism was used to analyze the MTHFR gene polymorphisms .The distribution of MTHFR gene polymorphism was compared between the two groups .Results The level of serum folic acid in the observation group was (5.76 ± 2.14)g/L,which was significantly lower than (7.34 ±2.43)g/L in the control group (t=5.64,P<0.05).The level of serum HCY in the observation group was (15.46 ±5.74)μmol/L,which was significantly higher than (10.28 ± 4.38)μmol/L in the control group (t=6.43,P<0.05).The frequencies of TT type,TC type and CC type of MTHFR gene in the observation group were 36.92％,46.92％and 16.15％,respectively.The frequencies of TT type,TC type and CC type of MTHFR gene in the control group were 21.54％,55.38％ and 23.08％,respectively.The frequency of TT type in the observation group was significantly higher than that of the control group (χ2 =8.25,P<0.05). There were no statistically significant differences in folic acid levels among different gene types in the observationgroup(t=1.31,0.55,0.73,all P>0.05),but the serum HCY level of TT type was significantly higher than that of CT type and CC type in the observation group (t=5.33,4.62,all P<0.05).Conclusion Serum folic acid level, HCY level and homozygous mutations of MTHFR gene type have certain relationship with the occurrence of coronary heart disease ,the body serum folic acid level and the distribution of MTHFR genotypes can affect the concentration of HCY,thus affecting the occurrence of coronary heart disease .

The secondary metabolites, phenazine products, produced by Pseudomonas aeruginosa can mediate the electrons transfer in microbial fuel cells (MFCs). How increase the total electricity production in MFCs by improving the characteristics of Pseudomonas aeruginosa is one of research hot spots and problems. In this study, P. aeruginosa strain SJTD-1 and its knockout mutant strain SJTD-1 (ΔmvaT) were used to construct MFCs, and the discharge processes of the two MFCs were analyzed to determine the key factors to electricity yields. Results indicated that not only phenazine but also the viable cells in the fermentation broth were essential for the discharge of MFCs. The mutant strain SJTD-1 (ΔmvaT) could produce more phenazine products and continue discharging over 160 hours in MFCs, more than that of the wild-type SJTD-1 strain (90 hours discharging time). The total electricity generated by SJTD-1 (ΔmvaT) strain could achieve 2.32 J in the fermentation process, much higher than the total 1.30 J electricity of the wild-type SJTD-1 strain. Further cell growth analysis showed that the mutant strain SJTD-1 (ΔmvaT) could keep a longer stationary period, survive much longer in MFCs and therefore, discharge more electron than those of the wild-type SJTD-1 strain. Therefore, the cell survival elongation of P. aeruginosa in MFCs could enhance its discharging time and improve the overall energy yield. This work could give a clue to improve the characteristics of MFCs using genetic engineering strain, and could promote related application studies on MFCs.

Objective To evaluate the clinical outcomes of internal fixation with extra-articular distal humerus locking compression plate (LCP) for the treatment of mid-distal humerus diaphyseal fracture.Methods From December 2012 to December 2016,a cohort of 22 patients with mid-distal humerus shaft fracture were treated by open reduction and internal fixation using extra-articular distal humerus LCP.They were 14 males and 8 females with an average age of 42.7 years (range,from 18 to 86 years).According to AO classification,there were 13 cases of type 12-A,7 cases of type 12-B,and 2 cases of type 12-C.The surgical time,intra-operative blood loss and hospital stay were recorded.The clinical outcomes were evaluated by the Mayo elbow performance score (MEPS) at the last follow-ups.Results Surgical time ranged from 46 to 95 minutes with an average of 57 minutes.The average blood loss was 220 mL (range,from 150 to 400 mL).The average hospital stay was 10.5 days (range,from 9 to 13 days).The mean follow-up was 23.8 months (range,from 6 to 48 months).Bone union was achieved in 21 cases after an average of 4.6 months (range,from 3 to 9 months),and one patient experienced bone non-union which was uneventfully healed after secondary auto platelet rich plasma (PRP) graft management.The average MEPS elbow performance score was 88.2,resulting in 16 excellent,4 fine and 2 fair cases (excellent and fine rate:90.9％).Conclusions Since extra-articular distal humerus LCP can provide stable internal fixation,facilitating early postoperative rehabilitation,it may be considered an effective alternative osteosynthesis for mid-distal comminuted humeral diaphyseal fractures.