Objective: To classify the ABO blood group phenotypes of 5 cases from a family, and to explore the molecular mechanism for reduced B antigen expression in ABO blood group system. Methods: Serological identification of the ABO blood group was performed using microcolumn gel assay and saline tube method. The soluble antigens in saliva were detected by the agglutination inhibition assay. The full-length sequences and upstream promoter regions of ABO gene were sequenced for genotyping using PacBio SMRT sequencing technology. Results: The results of serological tests indicated the expression of B antigen decreased in 3 out of 5 blood samples. A mixed-field agglutination was observed with anti-B antibody. B antigen was not detected in all 5 saliva samples. The ABO genotype for all samples were ABO B.01/ABO O.01.02, and a novel mutation c. 28+5875C>T within the DNA-binding region of RUNX1 in +5.8-kb site were found in the B allele for 3 samples with reduced expression of B antigen. Conclusion: Results of serological and genetic analyses classify the 3 cases with reduced B antigen expression as B phenotype. The novel mutation c. 28+5875C>T of RUNX1 could be the key reason for reduced B antigen expression in 3 cases with B phenotype.

OBJECTIVE To construct ensemble learning models for predicting high-use days of budesonide based on meteorological factors， thereby providing reference for hospital pharmacy management. METHODS Meteorological data for 2024 and outpatient budesonide usage data from the jurisdiction of Sanming Hospital of Integrated Traditional Chinese and Western Medicine were collected. High-use days were defined as the 75th percentile of outpatient budesonide usage， and a corresponding dataset was established. The prediction task was formulated as a classification problem， and three ensemble learning models were developed： Random Forest， Extreme Gradient Boosting （XGBoost）， and Histogram-based Gradient Boosting Classifier. Model performance was evaluated using accuracy， precision， recall， F1-score， and log-loss. Model interpretability was analyzed using Shapley Additive Explanations （SHAP）. RESULTS The Histogram-based Gradient Boosting Classifier achieved the best performance （accuracy＝0.75， F1-score＝0.48）， followed by XGBoost （accuracy＝0.74， F1-score＝0.43） and Random Forest （accuracy＝0.72， F1-score＝0.22）. SHAP results suggested that the prediction results of the last two models have the highest correction. CONCLUSIONS Ensemble learning models can effectively predict high-use days of budesonide， with the Histogram- based Gradient Boosting Classifier demonstrating the best predictive performance. Low temperature， high humidity， and low atmospheric pressure show significant positive impacts on the prediction of daily budesonide usage.

OBJECTIVE: To develop an artificial intelligence-assisted system for the automatic detection of the features of common 21 auricular points based on the YOLOv8 neural network. METHODS: A total of 660 human auricular images from three research centers were collected from June 2019 to February 2024. The rectangle boxes and features of images were annotated using the LabelMe5.3.1 tool and converted them into a format compatible with the YOLO model. Using these data, transfer learning and fine-tuning training were conducted on different scales of pretrained YOLO neural network models. The model's performance was evaluated on validation and test sets, including the mean average precision (mAP) at various thresholds, recall rate (recall), frames per second (FPS) and confusion matrices. Finally, the model was deployed on a local computer, and the real-time detection of human auricular images was conducted using a camera. RESULTS: Five different versions of the YOLOv8 key-point detection model were developed, including YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. On the validation set, YOLOv8n showed the best performance in terms of speed (225.736 frames per second) and precision (0.998). On the external test set, YOLOv8n achieved the accuracy of 0.991, the sensitivity of 1.0, and the F1 score of 0.995. The localization performance of auricular point features showed the average accuracy of 0.990, the precision of 0.995, and the recall of 0.997 under 50% intersection ration (mAP⁵⁰). CONCLUSION The key-point detection model of 21 common auricular points based on YOLOv8n exhibits the excellent predictive performance, which is capable of rapidly and automatically locating and classifying auricular points.
Humans ; Neural Networks, Computer ; Artificial Intelligence ; Acupuncture Points

OBJECTIVES: To develop a heterogeneous graph prediction method based on the fusion of multi-layer semantics and topological information for addressing the challenges in drug-target interaction prediction, including insufficient modeling of high-order semantic dependencies, lack of adaptive fusion of semantic paths, and over-smoothing of node features. METHODS: A heterogeneous graph network with multiple types of entities such as drugs, proteins, side effects, and diseases was constructed, and graph embedding techniques were used to obtain low-dimensional feature representations. An adaptive metapath search module was introduced to automatically discover semantic path combinations for guiding the propagation of high-order semantic information. A semantic aggregation mechanism integrating multi-head attention was designed to automatically learn the importance of each semantic path based on contextual information and achieve differentiated aggregation and dynamic fusion among paths. A structure-aware gated graph convolutional module was then incorporated to regulate the feature propagation intensity for suppressing redundant information and redcuing over-smoothing. Finally, the potential interactions between drugs and targets were predicted through an inner product operation. RESULTS: Compared with existing drug-target interaction prediction methods, the proposed method achieved an average improvement of 3.4% and 2.4%, 3.0% and 3.8% in terms of the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPRC) on public datasets, respectively. CONCLUSIONS The drug-target interaction prediction method developed in this study can effectively extract complex high-order semantic and topological information from heterogeneous biological networks, thereby improving the accuracy and stability of drug-target interaction prediction. This method provides technical support and theoretical foundation for precise drug target discovery and targeted treatment of complex diseases.
Semantics ; Humans ; Drug Interactions ; Neural Networks, Computer ; Algorithms

Objective:To investigate the effects of long-term X-ray radiation exposure on the tumor risk of medical X-ray workers in Jiangsu province, and to provide a scientific basis for the development of occupational protection policies and the improvement of workers′ health.Methods:By using a combination of retrospective and prospective cohort research method, the medical diagnostic X-ray workers who worked in the radiology department of all hospitals in Jiangsu province between 1950 and 1980 were selected as the radiology group.In the meantime medical personnel in internal medicine, otorhinolaryngology, pediatrics and other medical departments who had not been engaged in radiology during the same period of time at the same hospital were selected as the control group to form a survey cohort. The cumulative number of person-years of observation of the cohort during 1950-2011 was calculated, and the relative risk of various malignant tumors among medical X-ray workers was calculated by using Cox regression model after adjusting for sex, attained age, year of birth, and year of work initiation.Results:A total of 6 954 follow-ups was completed for the cohort, including 3 649 in the irradiation group and 3 305 in the control group, totally 340 483 person-years of observation. As of December 31, 2021, there were 1 328 patients with malignant tumors in this cohort. Cox regression result showed that compared with the control group, the irradiation group who had developed lung cancer ( RR=1.60, 95% CI 1.24-2.08), lymphoma ( RR =4.28, 95% CI 1.54-11.93), solid cancer ( RR =1.17, 95% CI 1.04-1.31), and total cancer ( RR =1.29, 95% CI 1.14-1.46) had significantly higher relative risks ( Z=3.56, 2.78, 2.71, 3.96, P<0.05). Stratified analyses showed that the risks of lung, lymphoma, solid and total cancers were higher in the radiation group than in the control group for males and for those who arrived at the age of 61 years or older ( χ2=6.70-33.86, P<0.05). The risks of lung, solid and total cancers were higher in the radiation group than in the control group for those who started to work in the age group of 21 to 25 years ( χ2=6.46, 6.16, 5.62, P<0.05). Conclusions:The relative risks of lung, lymphoma, solid and total cancers among medical X-ray workers in Jiangsu province are significantly higher, suggesting that attention should be paid to strengthening radiation protection for radiation workers in their radiological practices.

Objective:To explore the mechanism of Huangqi Jiedu Decoction (HQJD) in the treatment of breast cancer with the syndrome of Zheng deficiency and toxic incandescence by network pharmacology and molecular docking technology.Methods:The main active ingredients and targets of HQJD were screened through the traditional Chinese medicine (TCM) systematic pharmacology database and analysis platform. The relevant targets of breast cancer with the syndrome of Zheng-deficiency, toxic-incandescence were obtained using OMIM, GeneGards and Drugbank databases, and the relevant targets of HQJD for the treatment of breast cancer with the syndrome of Zheng-deficiency and toxic incandescence were obtained by intersection; The Cytoscape 3.9.1 software was used to build the protein protein interaction (PPI) network and the " drug active component target disease" network on the basis of String 11.0 database, and the core active components and core targets of HQJD in treating breast cancer with the syndrome of Zheng-deficiency and toxic-incandescence were inferred according to the topological parameters. gene ontology (GO) enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis were performed on core targets using R language; and molecular docking verification on the main active ingredients and core targets were conducted.Results:230 effective targets of active ingredients of HQJD were screened, and 15 467 active ingredients of breast cancer with syndrome of Zheng-deficiency/toxic-incandescence were obtained; 217 intersection targets; GO function enrichment analysis showed that the treatment of HQJD for breast cancer with the syndrome of Zheng-deficiency and toxic-incandescence mainly involved oxidative stress and cytochemical stress; The enrichment analysis of KEGG pathway showed that HQJD treatment of breast cancer with the syndrome of Zheng-deficiency and toxic-incandescence was mainly related to phosphatidylinositol 3-protein kinase B (PI3K-Akt), interleukin-17 (IL-17) and other signal pathways. The molecular docking results showed that the main active ingredients such as β-sitosterol, stigmasterol, luteolin had good binding ability with core targets.Conclusions:HQJD has the characteristics of multi-component, multi target and multi pathway in the treatment of breast cancer with syndrome of Zheng-deficiency and toxic-incandescence, and its main mechanism may be related to PI3K-Akt, IL-17, P53 and other signal pathways.

Objective To investigate the basic situation and occupational health conditions of nuclear medicine radiation workers in Jiangsu Province based on the research protocol developed by the Institute of Radiation Medicine, Chinese Academy of Medical Sciences for the nationwide study on the health effects of nuclear medicine radiation in China, understand the impact of occupational radiation on the physical health of nuclear medicine radiation workers, and provide a basis for improving the occupational protection of nuclear medicine radiation workers and reducing the risk of occupational radiation-related health issues. Methods A census approach was used to collect general data and occupational health information of nuclear medicine radiation workers in Jiangsu Province. The analysis focused on the abnormalities in physical examination indicators among radiation workers of different genders, ages, and working years to evaluate the health effects of occupational radiation exposure. Results The occupational health examination data of 472 nuclear medicine radiation workers were collected from 76 medical institutions in Jiangsu Province. The results showed that the detection rate of abnormal hypothyroidism in female workers (8.90%) was higher than that in male workers (2.54%) (P=0.028). With increasing working years, the detection rates of cataract and continuous decrease in white blood cell count increased (P＜0.001). The multivariate logistic regression identified working years as a risk factor for cataract and continuous decrease in white blood cell count (OR=1.59, 95%CI=1.40-3.35, P=0.0003; OR=4.15, 95%CI=3.11-29.91, P=0.0001). In addition, working years was also a risk factor for hypertension, fatty liver, and tumor (OR=2.28, 95%CI=1.51-3.47, P=8.76 × 10⁻⁵; OR=1.69, 95%CI=1.10-2.58, P=0.0145; OR=2.04, 95%CI=1.00-4.16, P=0.0469). Conclusion The study found that working in nuclear medicine could increase the risk of various radiation-related diseases, and the risk is influenced by factors such as working years.

Objective To analyze the causal relationship between Sjogren's syndrome(SS)and primary biliary cholangitis(PBC)and abnormal liver function by two-sample Mendelian randomization.Methods From the ge-nome-wide association study,single nucleotide polymorphisms of SS,PBC,alkaline phosphatase,alanine amin-otransferase,aspartate aminotransferase,γ-glutamyltransferase,direct bilirubin and total bilirubin levels were extrac-ted as instrumental variables.Inverse-variance weighted(IVW)analysis was used as the main analysis,supplemen-ted by weighted median,MR-Egger,weighted mode,and simple mode.And a series of sensitivity analyses were car-ried out to verify the robustness of the results.Results The IVW analysis results of PBC on SS were as follows:P=8.57E-11,OR=1.185 9,95％CI=1.126 4-1.248 5;IVW analysis of PBC on SS(P＞0.05).IVW analysis results of SS on alkaline phosphatase were as follows:P=0.041 5,Beta=-0.007 2,95％CI=-0.014 0--0.000 3;IVW analysis results of SS on alanine aminotransferase,aspartate aminotransferase,γ-glutamyltransferase,direct bilirubin,total bilirubin levels showed no statistically significant difference.Conclusion PBC can significantly increase the risk of SS,but SS cannot be proved to have a causal effect on the occurrence of PBC.SS has a potential effect on re-ducing alkaline phosphatase levels,but it is not proved that SS has causal relationship with alanine aminotransferase,aspartate aminotransferase,γ-glutamyltransferase,direct bilirubin,total bilirubin levels.

Objective To investigate the basic situation and occupational health conditions of nuclear medicine radiation workers in Jiangsu Province based on the research protocol developed by the Institute of Radiation Medicine, Chinese Academy of Medical Sciences for the nationwide study on the health effects of nuclear medicine radiation in China, understand the impact of occupational radiation on the physical health of nuclear medicine radiation workers, and provide a basis for improving the occupational protection of nuclear medicine radiation workers and reducing the risk of occupational radiation-related health issues. Methods A census approach was used to collect general data and occupational health information of nuclear medicine radiation workers in Jiangsu Province. The analysis focused on the abnormalities in physical examination indicators among radiation workers of different genders, ages, and working years to evaluate the health effects of occupational radiation exposure. Results The occupational health examination data of 472 nuclear medicine radiation workers were collected from 76 medical institutions in Jiangsu Province. The results showed that the detection rate of abnormal hypothyroidism in female workers (8.90%) was higher than that in male workers (2.54%) (P=0.028). With increasing working years, the detection rates of cataract and continuous decrease in white blood cell count increased (P＜0.001). The multivariate logistic regression identified working years as a risk factor for cataract and continuous decrease in white blood cell count (OR=1.59, 95%CI=1.40-3.35, P=0.0003; OR=4.15, 95%CI=3.11-29.91, P=0.0001). In addition, working years was also a risk factor for hypertension, fatty liver, and tumor (OR=2.28, 95%CI=1.51-3.47, P=8.76 × 10⁻⁵; OR=1.69, 95%CI=1.10-2.58, P=0.0145; OR=2.04, 95%CI=1.00-4.16, P=0.0469). Conclusion The study found that working in nuclear medicine could increase the risk of various radiation-related diseases, and the risk is influenced by factors such as working years.

According to the International League Against Epilepsy (ILAE) standards, the Newborn Working Group of the ILAE put forward 6 necessary questions about the management of neonatal anti-seizure medication and gave evidence-based recommendations in 2023. The basic framework is systematic review+expert consensus. The clinical recommendations of ILAE guidelines 2023 and the similarities and differences between ILAE guidelines 2023 and ILAE guidelines 2011 were analyzed and interpreted in this paper, in order to provide reference for colleagues involved in neonatal convulsion management in China.