BACKGROUND:The sports medicine community has widely called for the use of machine learning technology to efficiently process the huge and complicated sports data resources,and construct intelligent sports injury prediction models,enabling accurate early warning of sports injuries.It is of great significance to comprehensively summarize and review such research results so as to grasp the direction of early warning model improvement and to guide the construction of sports injury prediction models in China. OBJECTIVE:To systematically review and analyze relevant research on sports injury prediction models based on machine learning technology,thereby providing references for the development of sports injury prediction models in China. METHODS:Literature search was conducted on CNKI,Web of Science and EBSCO databases,which mainly searched for literature related to machine learning techniques and sports injuries.Finally,61 articles related to sports injury prediction models were included for analysis. RESULTS AND CONCLUSION:(1)In terms of external risk feature indicators,there is a lack of competition scenario indicators,and the inclusion of related feature indicators needs to be further improved to further enrich the dimensions of the dataset for model training.In addition,the inclusion feature weighting methods of the sports injury prediction model are mainly based on filtering methods and the use of embedding and wrapping weighting methods needs to be strengthened in order to enhance the analysis of the interaction effects of multiple risk factors.(2)In terms of model body training,supervised learning algorithms become the mainstream choice.Such algorithms have higher requirements for the completeness of sample labeling information,and the application scenarios are easily limited.Therefore,the application of unsupervised and semi-supervised algorithms can be increased in the later stage.(3)In terms of model performance evaluation and optimization,the current studies mainly adopt two verification methods:HoldOut crossover and k-crossover.The range of AUC values is(0.76±0.12),the range of sensitivity is(75.92±11.03)%,the range of specificity is(0.03±4.54)%,the range of F1 score is(80.60±10.63)%,the range of accuracy is(69.96±13.10)%,and the range of precision is(70±14.71)%.Data augmentation and feature optimization are the most common model optimization operations.The accuracy and precision of the current sports injury prediction model are about 70%,and the early warning effect is good.However,the model optimization operation is relatively single,and data augmentation methods are often used to improve model performance.Further adjustments to the model algorithm and hyperparameters are needed to further improve model performance.(4)In terms of model feature extraction,most of the internal risk profile indicators included are mainly based on anthropometrics,training load,years of training,and injury history,but there is a lack of sports recovery and physical function indicators.

Objective: To explore the comorbidity and associated factors of dental caries and overweight/obesity among primary and secondary school students in Guangxi, so as to provide a scientific basis for the development of targeted prevention strategies. Methods: A stratified cluster random sampling method was used to survey 178 700 students from the fourth grade of primary school to the third year of high school in Guangxi Zhuang Autonomous Region from September to November 2023, including physical examination, oral screening, and questionnaire survey. Chisquare tests and binary Logistic regression analysis were employed to investigate the related factors of the cooccurrence of dental caries and overweight/obesity among students. Results: The comorbidity rate of dental caries and overweight/obesity was 9.55%, with urban areas (9.95%) higher than rural counties (9.24%), boys (10.54%) higher than girls (8.54%), primary school students (11.49%) higher than senior high school students (8.92%) and junior high school students (8.05%), and nonboarding students (11.44%) higher than boarding students (7.94%), and all differences were statistically significant (χ2=26.07, 207.91, 471.54, 629.14,P<0.01). Multivariate Logistic regression analysis showed that consuming cereal for breakfast (OR=0.91, 95%CI=0.88-0.94), drinking milk in the past week (OR=0.89, 95%CI=0.83-0.95), meeting sleep standards (OR=0.95, 95%CI=0.91-0.99), and brushing teeth at least once a day (OR=0.82, 95%CI=0.73-0.93) had a lower risk of the comorbidity of dental caries and overweight/obesity. In contrast, drinking beverages in the past week (OR=1.14, 95%CI=1.09-1.20), consuming fried foods in the past week (OR=1.11, 95%CI=1.06-1.17), eating fruit ≥1 time every day (OR=1.06, 95%CI=1.02-1.11), consuming fruit ≥1 type every day (OR=1.07, 95%CI=1.01-1.12), and having fish, poultry, meat, or eggbased breakfasts (OR=1.03, 95%CI=1.05-1.13) had a higher risk of the comorbidity of dental caries and overweight/obesity (P<0.05). Conclusions Dietary habits and lifestyle behaviors are associated with the comorbidity of dental caries and overweight/obesity among primary and secondary school students in Guangxi. Guiding students to form healthy living habits is helpful to preven dental caries and overweight/obesity.

Previous studies have identified two group-level processes, neural representations of interracial between-group difference and intraracial within-group similarity, that contribute to the racial categorization of faces. What remains unclear is how the brain tracks race-related information that varies across different faces as an individual-level neural process involved in race perception. In three studies, we recorded functional MRI signals when Chinese adults performed different tasks on morphed faces in which proportions of pixels contributing to perceived racial identity (Asian vs White) and expression (pain vs neutral) varied independently. We found that, during a pain expression judgment task, tracking other-race and same-race-related information in perceived faces recruited the ventral occipitotemporal cortices and medial prefrontal/anterior temporal cortices, respectively. However, neural tracking of race-related information tended to be weakened during explicit race judgments on perceived faces. During a donation task, the medial prefrontal activity also tracked race-related information that distinguished between two perceived faces for altruistic decision-making and encoded the Euclidean distance between the two faces that predicted decision-making speeds. Our findings revealed task-dependent neural mechanisms underlying the tracking of race-related information during face perception and altruistic decision-making.
Adult ; Female ; Humans ; Male ; Young Adult ; Brain/diagnostic imaging* ; Brain Mapping ; Decision Making/physiology* ; Facial Recognition/physiology* ; Judgment/physiology* ; Magnetic Resonance Imaging ; Photic Stimulation ; Racial Groups ; Social Perception ; East Asian People

OBJECTIVE To explore the specific application and evaluation effect of objective structured clinical examination(OSCE)-guided scenario-based practical teaching mode in training clinical pharmacists. METHODS Fifty-six trainees who participated in the clinical pharmacist training program in the Second Xiangya Hospital of Central South University from October 2020 to September 2022 were selected as the research objects. OSCE-guided teaching was conducted, and the application effect of OSCE-guided teaching mode in clinical pharmacist training was explored and analyzed by using theoretical examination results and OSCE assessment results as evaluation indicators. RESULTS Through comparative analysis, it was found that the OSCE-guided teaching mode not only enabled students to better grasp the theoretical knowledge points required by the training outline, but also improved their clinical thinking ability, problem-solving ability, and communication and coordination skills to varying degrees. CONCLUSION For clinical pharmacist trainees, the OSCE teaching mode is conducive to the comprehensive improvement of clinical pharmacist skills and is suitable for cultivating clinical pharmacists who are capable of independently carrying out clinical pharmacy services in the new situation.

OBJECTIVE To evaluate the quality and existing problems of Compound Paracetamol and Chlorphenamine Tablets for Infant. METHODS Using legal standards to inspect sampled samples, and several analytical methods were subsequently established or improved for the exploratory research on related substances, assay, dissolution, subdivision characteristics of scored tablets, and genotoxic impurities. RESULTS All samples met the regulatory specification, and the pass rate was 100%. However, the control for related substances was lacking, and the method for assay and content uniformity was defective. The exploratory studies showed that the assay and content uniformity met the requirements, and the risk of related substances and genotoxic impurities was acceptable. As a divisible tablet, the subdivision characteristics could not meet the requirements of the scored tablet, and the dissolution performance of some enterprise samples could not meet the requirements of similar products in foreign pharmacopoeias. CONCLUSION The overall quality of this product is adequate. However, due to the early time on the market, some quality attributes no longer meet the requirements of current regulations or relevant guidelines. The manufacturers should further optimize the prescription and production process, referring to foreign similar products. The current specification needs to be revised and improved.

Objective To investigate the expression and prognostic significance of serum protease C1 inhib-itor(SERPING1)and plasminogen activator inhibitor type 1(SERPINE1)in patients with sepsis.Methods A total of 132 patients with sepsis treated in the hospital from March 2018 to March 2020 were se-lected as the sepsis group.According to whether they died within 28 days of admission,they were divided into a death group(n=34)and a survival group(n=98).Enzyme linked immunosorbent assay was used to detect the expression of serum SERPING1 and SERPINE1.Multivariate Logistic regression model and receiver oper-ating characteristic curve were used to study the value of serum SERPING1 and serpine1 in evaluating the prognosis of patients'death.Results[Compared with the control group,serum SERPING1(331.12±51.80 ng/L vs.639.04±91.12 ng/L)was lower and serum serpine1(412.67±64.84 ng/L vs.42.33±10.32 ng/L)was higher in the sepsis group,and the differences were statistically significant(P＜0.05).[Compared to the survival group,the levels of serum SERPINE1,procalcitonin,C-reactive protein,Acute Physiology and Chronic Health Evaluation Ⅱ(APACHE Ⅱ)score and Sequential Organ Failure Assessment(SOFA)score in the death group were higher,while serum SERPING1 was lower,and the differences were statistically significant(all P＜0.05).Serum SERPING1 showed negative correlation with APACHE Ⅱ and SOFA scores(r=-0.779,-0.653,P＜0.05),while serum SERPINE1 showed positive correlation with APACHE Ⅱ and SO-FA scores(r=0.740,0.685,P＜0.05).APACHE Ⅱ score,SOFA score,and serum SERPINE1 were risk fac-tors affecting the prognosis of sepsis patients,while serum SERPING1 was a protective factor.The area under the curve of serum SERPING1 and SERPINE1 combined for the evaluation of the death in sepsis patients was 0.938(95％CI:0.893-0.968),which was significantly higher than 0.860(95％CI:0.812-0.899)and 0.838(95％CI:0.781-0.868)of the single detection,and the differences were statistically significant(Z=3.861,4.015,P＜0.001).Conclusion The elevated levels of serum SERPING1 and SERPINE1 in patients with sepsis are related to the severity of the patient's condition.The combination of the two has high prognos-tic value for sepsis patients.

Objective:To explore the predictive factors for adverse clinical outcomes in critically ill adult patients with autoimmune encephalitis by analyzing their clinical characteristics and prognosis.Methods:Clinical data of patients diagnosed with " confirmed" or " possible" autoimmune encephalitis who were hospitalized in the intensive care unit (ICU) of the Department of Neurology at the Second Xiangya Hospital of Central South University from January 2015 to December 2023 were retrospectively collected. The neurological function of patients at 3, 6, and 12 months of onset was followed up, and the modified Rankin Scale (mRS) at 12 months was used as an evaluation index for clinical prognosis; Further analysis was conducted on the relationship between clinical features, auxiliary examinations, and prognosis.Results:The 12-month survival rate of critically ill adult patients with autoimmune encephalitis in our center was 90.7%(117/129), and the 6-month poor prognosis rate was 28.7%(37/129). Univariate logistic regression analysis found that age of onset ( P<0.01), presence of tumors ( P<0.01), mechanical ventilation ( P<0.01), Glasgow Coma Scale (GCS) at ICU admission ( P<0.01), Acute Physiology and Chronic Health Evaluation Ⅱ (APACHE Ⅱ) score ( P<0.01), cerebrospinal fluid glucose ( P<0.01), cerebrospinal fluid protein level ( P=0.02), epileptic waves in electroencephalography (EEG) ( P=0.03), use of glucocorticoids ( P=0.04), and time interval between initiation of intravenous immunoglobulin (IVIG) and onset ( P=0.04) were associated with prognosis. The results of multiple logistic regression analysis showed that mechanical ventilation [ P=0.01, area under the curve (AUC)=0.72)], APACHE Ⅱ score ( P=0.04, AUC=0.68), cerebrospinal fluid protein content ( P=0.04, AUC=0.65), and the time interval between initiation of IVIG and onset ( P=0.02, AUC=0.64) were independent predictive factors for the prognosis of adult critical autoimmune encephalitis. The prognostic prediction model for adult critical autoimmune encephalitis established by combining these four indicators has a higher AUC (0.85). Conclusions:Mechanical ventilation, APACHE Ⅱ score, cerebrospinal fluid protein level, and the time interval between initiation of IVIG and onset are predictive factors for poor clinical outcomes in critically ill autoimmune encephalitis in adults; The prognostic prediction model for adult critical autoimmune encephalitis established by combining these four indicators can identify patients with poor prognosis early, which is beneficial for early comprehensive management and intervention treatment to improve patient prognosis.

Objective: To determine the main components of Astragalus membranaceus (Fisch.) Bge (A. membranaceus, Huang Qi), Astragaloside IV (AIV) and Astragalus polysaccharides (AP), to characterize their properties, evaluate their in vivo efficacy, and to analyze drug diffusion using dissolving microneedle (DMN) technology in vivo. Methods: Respectively, AIV- and AP-loaded DMNs comprising chitosan (CTS) and polyvinyl alcohol (PVA) were prepared via dual-mold forming. Their morphology, mechanical properties, in vivo solubility, and skin irritation characteristics were tested. In vivo efficacy was assessed in cyclophosphamide-induced immunosuppressed mice, in vivo diffusion of AIV and AP by DMNs and conventional methods was compared, and the rheological properties of AIV-CTS-PVA and AP-CTS-PVA mixtures were measured. Results: Subcutaneous dissolution and absorption of AIV-CTS-PVA and AP-CTS-PVA microneedles (MNs) at low doses (50%–17% of intraperitoneal AIV injection and 12%–4% of intravenous AP injection) reduced the spleen index and acid phosphatase activity in immunosuppressed mouse models, increased the thymus index, and achieved equivalent or better systemic therapeutic effects. Compared with injections, AIV and AP achieved controllable solid-liquid conversion through delivery with CTS-PVA MNs, resulting in highly localized aggregation within 48 h, reducing the initial explosive effect of the drug, and achieving stable and slow drug release. Conclusion The present study enhances our understanding of the efficacy and remote effects of drug-loaded DMNs from a traditional Chinese medicine (TCM) perspective, thereby promoting the development of precise and efficient delivery of TCM and further expanding the drug-loading range and application scenarios for DMNs.

Objective To analyze the risk of return to sport in athletes using their gait data following anterior cruciate ligament re-construction(ACLR). Methods From May to June,2023,39 athletes after ACLR were recruited in Wuhan Sports University.Their data on sta-ble gait and tandem gait were recorded using a three-dimensional motion capture system,surface electromyogra-phy and a three-dimensional ergometer table.Additionally,return-to-sport scores were calculated using the K-STARTS test.The relationship between each gait indicator and the total score of the K-STARTS test was ana-lyzed with Pearson correlation analysis.Furthermore,the key indicators related to the risk of return to sport were analyzed using linear regression. Results In the stable gait test,the step time was negatively correlated with the total score of K-STARTS(r=-0.479,P=0.002),and the peak amplitude symmetry index of rectus femoris(r=0.448,P=0.004)and vastus lateralis(r=0.595,P=0.001)were positively correlated with the total score of K-STARTS.In the tandem gait test,the lateral displacement distance of the center of gravity was negatively correlated with the total score of K-STARTS(r=-0.341,P=0.034),and the time symmetry index of peak amplitude of vastus lateralis was positively correlated with the total score of K-STARTS(r=0.320,P=0.047).Regression analysis showed that the interpretation of the model based on stable gait(F=15.818,P=0.001,R2=0.650)was better than that based on tandem gait(F=7.692,P=0.001,R2=0.397). Conclusion In stable gait,gait rhythm variability and symmetry are correlated with return to sport risk.In tandem gait,gait balance and symmetry indexes are correlated with return-to-sport risk.Compared with tandem gait,the inter-pretation of return-to-sport risk assessment model based on stable gait information is better,and may be more suitable as a simple return-to-sport risk test method.

Objective:To construct an artificial intelligence (AI)-assisted system based on deep learning for corneal in vivo confocal microscopy (IVCM) image recognition and to evaluate its value in clinical applications. Methods:A diagnostic study was conducted.A total of 18 860 corneal images were collected from 331 subjects who underwent IVCM examination at Renmin Hospital of Wuhan University and Zhongnan Hospital of Wuhan University from May 2021 to September 2022.The collected images were used for model training and testing after being reviewed and classified by corneal experts.The model design included a low-quality image filtering model, a corneal image diagnosis model, and a 4-layer identification model for corneal epithelium, Bowman membrane, stroma, and endothelium, to initially determine normal and abnormal corneal images and corresponding corneal layers.A human-machine competition was conducted with another 360 database-independent IVCM images to compare the accuracy and time spent on image recognition by three senior ophthalmologists and the AI system.In addition, 8 trainees without IVCM training and with less than three years of clinical experience were selected to recognize the same 360 images without and with model assistance to analyze the effectiveness of model assistance.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Renmin Hospital of Wuhan University (No.WDRY2021-K148).Results:The accuracy of this diagnostic model in screening high-quality images was 0.954.Its overall accuracy in identifying normal/abnormal corneal images was 0.916 and 0.896 in the internal and external test sets, respectively.Its accuracy reached 0.983, 0.925 in the internal test sets and 0.988, 0.929 in the external test sets in identifying corneal layers of normal and abnormal images, respectively.In the human-machine competition, the overall recognition accuracy of the model was 0.878, which was similar to the average accuracy of the three senior physicians and was approximately 300 times faster than the experts in recognition speed.Trainees assisted by the system achieved an accuracy of 0.816±0.043 in identifying corneal layers of normal and abnormal images, which was significantly higher than 0.669±0.061 without model assistance ( t=6.304, P<0.001). Conclusions:A deep learning-based assistant system for corneal IVCM image recognition is successfully constructed.This system can discriminate normal/abnormal corneal images and diagnose the corresponding corneal layer of the images, which can improve the efficiency of clinical diagnosis and assist doctors in training and learning.