Objective To develop and validate a machine learning model based on preoperative clinical characteristics, laboratory indices, and radiological features for the non-invasive prediction of spread through air spaces (STAS) in patients with early-stage lung adenocarcinoma. Methods Preoperative data from patients with early-stage lung adenocarcinoma who underwent surgical resection at Northern Jiangsu People's Hospital between January 2020 and August 2025 were retrospectively collected. The data included clinical characteristics, laboratory indices, and radiological features. Patients were divided into a STAS-positive and a STAS-negative group based on postoperative pathological findings. The dataset was randomly split into a training set and a testing set at a 7 : 3 ratio. Feature variables were selected using the maximum relevance and minimum redundancy (mRMR) algorithm and the least absolute shrinkage and selection operator (LASSO) regression. Five machine learning models were constructed: logistic regression (LR), random forest (RF), support vector machine (SVM), light gradient boosting machine (LightGBM), and extreme gradient boosting (XGBoost). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). The shapley additive explanations (SHAP) method was employed to interpret the optimal prediction model. Results A total of 377 patients were included, comprising 177 (46.9%) males and 200 (53.1%) females, with a mean age of (63.31±9.73) years. There were 261 patients in the training set and 116 patients in the testing set. In the training set, statistically significant differences were observed between the STAS-positive group (n=130) and STAS-negative group (n=131) across multiple features, including age, sex, neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), clinical T stage, and maximum solid component diameter (P<0.05). A final set of 10 feature variables was selected by combining mRMR and LASSO regression, and five machine learning models (LR, RF, SVM, LightGBM, XGBoost) were developed. The XGBoost model demonstrated optimal performance in both the training and testing sets, achieving AUCs of 0.947 [95%CI (0.920, 0.975)] and 0.943 [95%CI (0.894, 0.993)], respectively. DCA indicated that the XGBoost model provided a high net clinical benefit across a wide range of threshold probabilities. SHAP analysis revealed that the vessel convergence sign, clinical T stage, age, consolidation-to-tumor ratio (CTR), and MLR were the features with the highest contributions to STAS prediction. Conclusion The XGBoost model effectively predicts preoperative STAS status in early-stage lung adenocarcinoma, exhibiting excellent discriminative performance and good clinical interpretability. Key predictors such as the vessel convergence sign, clinical T stage, age and CTR provide a crucial reference for preoperative risk assessment and the individualized selection of surgical strategies, ultimately benefiting patients.

By establishing a complete data organizational structure,technical architecture,quality control framework,and concept framework,hospitals can effectively regulate data management,data security,and quality monitoring,achieving full-cycle monitoring of data management.Breaking down the resource barriers of data systems,improving the efficiency of data usage and circulation,and promoting the increase in data value.It drives the hospital's scientific research innovation,medical insurance cost control,data value monetization,and the improvement of high-quality capabilities.Through the establishment of a sustainable digital culture and operational philosophy,it integrates data with hospital assets,continuously enhancing the value realization of hospital data in operations,management,diagnosis and treatment,and scientific research.

Objective:To investigate the clinical efficacy of minimally invasive percutaneous internal fixation with double screws for delayed union or nonunion of scaphoid fracture.Methods:A retrospective study was conducted to analyze the 12 patients with delayed union or nonunion of scaphoid fracture who had been treated at Department of Hand and Foot Surgery, The Affiliated Hospital of Jining Medical University from March 2021 to December 2023. They were 11 males and 1 female, with an age of (29.9±13.8) years and an interval from injury to surgery of (5.1±2.6) months. They were all treated by minimally invasive percutaneous internal fixation with 2 hollow compression screws. The visual analogue scale (VAS), grip strength (percentage of the affected side to the healthy side), wrist range of motion, modified Mayo wrist score and other data were recorded and compared between pre-surgery and the last follow-up. The incidence of complications was recorded.Results:Follow-up for all patients lasted for (20.8±8.9) months. All patients achieved bony union after (10.1±3.2) weeks with no complications like infection. No post-surgery imaging revealed screw misplacement or penetration. At the last follow-up, the VAS pain score was 0 (0, 1) point, the wrist grip strength 100.6%±7.2%, the wrist flexion 88.3°±2.5°, the wrist dorsiflexion 88.5°±2.2°, and the modified Mayo wrist score (98.3±2.5) points, all significantly better than the pre-surgery values [4 (4, 5) points, 69.1%±16.0%, 61.3°±13.5°, 64.7°±9.1°, and (61.7±10.1) points] (all P < 0.05). Conclusion:In the treatment of delayed union or nonunion of scaphoid fracture, minimally invasive percutaneous internal fixation with double screws shows advantages of minimal invasion, quick fracture healing, fine functional recovery, and no need of bone grafting.

Objective:To evaluate the elbow joint function of patients with endemic skeletal fluorosis based on Mayo elbow joint function score and to study its application value.Methods:Based on the monitoring results of drinking water-borne endemic fluorosis in Gansu Province from 2018 to 2023, and the results of the 2019 survey on the current cases of endemic diseases, 8 typical endemic counties were selected from 48 counties with drinking water-borne endemic fluorosis. A cluster sampling method was used to investigate all adult skeletal fluorosis patients over 25 years old in the endemic fluorosis villages under the jurisdiction of the 8 counties. A total of 1 096 skeletal fluorosis patients were included as study subjects. By extracting demographic basic information, follow-up records, elbow joint X-ray films, diagnostic information, and the Mayo elbow joint function score scale of patients, a retrospective analysis was conducted on the distribution characteristics of the Mayo elbow joint function score in different genders, ages, clinical grades, disease duration, and Kellgren-Lawrence (K-L) grading of osteoarthritis.Results:(1) The distribution of total scores on the scale: 638 cases (58.21%) were rated as "poor" (< 60 points), 345 cases (31.48%) were rated as "fair" (60 - 74 points), 96 cases (8.76%) were rated as "good" (75 - 89 points), and 17 cases (1.55%) were rated as "excellent" (≥90 points). There were statistically significant differences in the total score grading of the scale among patients with different genders, ages, clinical grades, disease duration, and K-L grading of osteoarthritis (χ 2 = 44.90, 147.20, 264.41, 211.96, 262.85, P < 0.001). (2) The scores of each dimension of the scale: the joint stability dimension scores were compared among different ages, clinical grades, disease duration, and K-L grading of osteoarthritis, and the differences were statistically significant ( P < 0.05). The scores of joint pain, range of motion, and daily living ability dimensions were compared among different genders, ages, clinical grades, disease duration, and K-L grading of osteoarthritis, and the differences were statistically significant ( P < 0.05). Conclusions:Based on the Mayo elbow joint function score scale, patients with endemic skeletal fluorosis have relatively poor elbow joint function. The scores of each dimension of the scale are influenced by factors such as genders, ages, clinical grades, disease duration, and joint degeneration. The distribution of scale scores is consistent with the clinical reality of endemic skeletal fluorosis and has certain application value in assessing disease condition.

Objective:To explore the application value of radiomics models based on MRI of vertebrae and paravertebral muscles in identifying potential vertebral fragility fracture risk in osteoporosis and osteopenia.Methods:This cross-sectional study collected data from patients who underwent both dual-energy X-ray absorptiometry (DXA) and lumbar MRI at the Third Affiliated Hospital of Southern Medical University between January 2014 and December 2023,retrospectively. Based on DXA results, patients were categorized into osteoporosis group ( n=302) and osteopenia group ( n=264), with fracture and non-fracture patients matched at 1∶1 ratio by propensity score matching based on age, gender, and body mass index. The fourth lumbar vertebra was selected as the region of interest (ROI) for the vertebral body, and the bilateral psoas major, erector spinae, and multifidus muscles were selected as the ROIs for the paraspinal muscles. A total of 7 259 radiomics features were extracted from these ROIs. The dataset was divided into a training set and a test set in an 8∶2 ratio by simple random sampling (osteoporosis group 241 and 61 cases, osteopenia group 211 and 53 cases). The T-score was used to establish the clinical model. After feature normalization and dimensionality reduction, logistic regression was applied to build three radiomics models: vertebral model, paraspinal muscle model, and vertebral-paraspinal muscle model. The T-score was then combined with the radiomics model that achieved the highest area under the receiver operating characteristic curve (AUC) in the test set to construct a clinical-radiomics combined model. Model performance was evaluated using the AUC. The DeLong test was used to compare the diagnostic efficacy between models. Results:In the test set, the vertebral-paravertebral muscle model achieved the highest AUC among radiomics models and was selected for combination with the T-score. In identifying potential vertebral fragility fractures of osteoporosis group, the AUC (95% CI) of the clinical model, vertebral model, paraspinal muscle model, vertebral-paraspinal muscle model, and clinical-radiomics model were 0.523 (0.373-0.672), 0.869 (0.779-0.959), 0.608 (0.464-0.752), 0.876 (0.791-0.961), and 0.860 (0.769-0.952), respectively. For osteopenia group, the corresponding AUC(95% CI) were 0.625 (0.467-0.783), 0.696 (0.547-0.845), 0.706 (0.563-0.848), 0.816 (0.702-0.930), and 0.820 (0.710-0.930). The DeLong test showed that the vertebral model for identifying the potential vertebral fracture risk in osteoporosis group had better performance than the paraspinal muscle model ( Z=3.28, P=0.001). While for osteopenia group, there was no significant difference in diagnostic performance between the vertebral model and the paraspinal muscle model ( Z=0.09, P=0.932). The recognition efficacy of the clinical model and the vertebral-paraspinal muscle model was significantly different ( Z=3.69, 1.98; P<0.001, P=0.047), while there was no significant difference between the clinical-radiomics combined model and the vertebral-paraspinal muscle model ( Z=1.51, 0.12; P=0.131, 0.904). Conclusion:The MRI-based vertebral-paraspinal muscle radiomics model can effectively identify osteoporosis or osteopenia patients with potential fragility fracture risk. In osteopenia group, the efficacy of the MRI radiomics models based on the vertebra and paraspinal muscles in identifying potential vertebral fragility fracture risk is comparable.

To assess the cross-contamination risk and genetic evolution ofStaphylococcus aureus(S.aureus)at various stages in a swine slaughterhouse,and to provide a reference for risk evalua-tion and control measures of S.aureus contamination during swine slaughtering,we conducted whole-genome sequencing on 31 isolates of S.aureus collected and preserved from the slaughter-house.Bioinformatics analyses were performed to investigate the genomic characteristics and genet-ic relationships of these isolates.Results revealed cross-contamination across different slaughter-house stages,predominantly with ST398-t1451 strains.Additionally,highly virulent ST9-t899 strains and ST398-t11 strains with numerous resistance genes were detected at various stages.The strains predominantly carried virulence genes such as hlgA,hlgB,and hlgC,with varying num-bers of resistance genes.Notably,two strains carried the optrA gene and three strains carried the cfr gene;the presence of the optrA gene is relatively rare among S.aureus.These genes confer re-sistance to novel synthetic antibiotics such as oxazolidinones and florfenicol and have the potential for horizontal gene transfer,increasing the risk of dissemination both within and beyond the slaughterhouse.Importantly,the study also detected a LA-MRSA-ST9 strain in water samples from the slaughterhouse,which could potentially infect humans.This strain exhibits zoonotic char-acteristics,highlighting the need for stricter protective measures for slaughterhouse workers to mitigate occupational exposure and infection risks.

Objective:To explore the application value of radiomics models based on MRI of vertebrae and paravertebral muscles in identifying potential vertebral fragility fracture risk in osteoporosis and osteopenia.Methods:This cross-sectional study collected data from patients who underwent both dual-energy X-ray absorptiometry (DXA) and lumbar MRI at the Third Affiliated Hospital of Southern Medical University between January 2014 and December 2023,retrospectively. Based on DXA results, patients were categorized into osteoporosis group ( n=302) and osteopenia group ( n=264), with fracture and non-fracture patients matched at 1∶1 ratio by propensity score matching based on age, gender, and body mass index. The fourth lumbar vertebra was selected as the region of interest (ROI) for the vertebral body, and the bilateral psoas major, erector spinae, and multifidus muscles were selected as the ROIs for the paraspinal muscles. A total of 7 259 radiomics features were extracted from these ROIs. The dataset was divided into a training set and a test set in an 8∶2 ratio by simple random sampling (osteoporosis group 241 and 61 cases, osteopenia group 211 and 53 cases). The T-score was used to establish the clinical model. After feature normalization and dimensionality reduction, logistic regression was applied to build three radiomics models: vertebral model, paraspinal muscle model, and vertebral-paraspinal muscle model. The T-score was then combined with the radiomics model that achieved the highest area under the receiver operating characteristic curve (AUC) in the test set to construct a clinical-radiomics combined model. Model performance was evaluated using the AUC. The DeLong test was used to compare the diagnostic efficacy between models. Results:In the test set, the vertebral-paravertebral muscle model achieved the highest AUC among radiomics models and was selected for combination with the T-score. In identifying potential vertebral fragility fractures of osteoporosis group, the AUC (95% CI) of the clinical model, vertebral model, paraspinal muscle model, vertebral-paraspinal muscle model, and clinical-radiomics model were 0.523 (0.373-0.672), 0.869 (0.779-0.959), 0.608 (0.464-0.752), 0.876 (0.791-0.961), and 0.860 (0.769-0.952), respectively. For osteopenia group, the corresponding AUC(95% CI) were 0.625 (0.467-0.783), 0.696 (0.547-0.845), 0.706 (0.563-0.848), 0.816 (0.702-0.930), and 0.820 (0.710-0.930). The DeLong test showed that the vertebral model for identifying the potential vertebral fracture risk in osteoporosis group had better performance than the paraspinal muscle model ( Z=3.28, P=0.001). While for osteopenia group, there was no significant difference in diagnostic performance between the vertebral model and the paraspinal muscle model ( Z=0.09, P=0.932). The recognition efficacy of the clinical model and the vertebral-paraspinal muscle model was significantly different ( Z=3.69, 1.98; P<0.001, P=0.047), while there was no significant difference between the clinical-radiomics combined model and the vertebral-paraspinal muscle model ( Z=1.51, 0.12; P=0.131, 0.904). Conclusion:The MRI-based vertebral-paraspinal muscle radiomics model can effectively identify osteoporosis or osteopenia patients with potential fragility fracture risk. In osteopenia group, the efficacy of the MRI radiomics models based on the vertebra and paraspinal muscles in identifying potential vertebral fragility fracture risk is comparable.

Acute lateral ankle sprain (ALAS) is one of the most common sport injuries, with high incidence, recurrence and disability rates. Currently, exercise rehabilitation-based non-surgical treatment is the primary management approach for ALAS. However, there remain improper practices such as excessive immobilization or uncontrolled activity, which contribute to recurrent sprains and chronic ankle instability, significantly impairing patients′ athletic function and quality of life. To standardize the non-surgical management of ALAS, improve the cure rates, and reduce the recurrence and disability rates, Chinese Sports Rehabilitation Medicine Training Project of Chinese Medical Association, Foot and Ankle Basics and Orthopedics Group, Orthopedic Branch of Chinese Medical Doctor Association, and Sports Medicine Branch of Jiangsu Medical Association organized relevant experts to formulate Expert consensus on non-surgical treatment for acute lateral ankle sprain ( version 2025), following the principles of scientific vigor, practicality, and innovation. Thirteen recommendations were proposed for standardized treatment protocols across different healing phases, aiming to provide references for standard management of ALAS and improve the therapeutic outcomes.

By establishing a complete data organizational structure,technical architecture,quality control framework,and concept framework,hospitals can effectively regulate data management,data security,and quality monitoring,achieving full-cycle monitoring of data management.Breaking down the resource barriers of data systems,improving the efficiency of data usage and circulation,and promoting the increase in data value.It drives the hospital's scientific research innovation,medical insurance cost control,data value monetization,and the improvement of high-quality capabilities.Through the establishment of a sustainable digital culture and operational philosophy,it integrates data with hospital assets,continuously enhancing the value realization of hospital data in operations,management,diagnosis and treatment,and scientific research.

Objective:To study the effects of TCM ointment rubbing technique on pain, swelling, and knee joint function in patients with knee osteoarthritis (KOA) after total knee arthroplasty (TKA).Methods:A randomized controlled trial was conducted. In this study, 80 patients with KOA who underwent TKA treatment in the Department of Sports Medicine I, Wangjing Hospital, China Academy of Traditional Chinese Medicine from October 2022 to March 2024 were taken as the study subjects. They were divided into two groups with random number table method, with 40 cases in each group. Both groups were treated with conventional Western medicine + rehabilitation training after surgery, and the observation group was combined with TCM paste mo technique on this basis. VAS score was used to assess the degree of pain at different time points, and skin fold was used to measure the circumference of the upper knee circumference and the circumference of the lower knee circumference, and knee Injury and osteoarthritis outcome score (KOOS) was used to assess the degree of knee joint function recovery.Results:After treatment, the observation group after surgerythe at 7 d (2.57 ± 0.84 vs. 4.00 ± 0.85, t=7.54) and 14 d (0.80 ± 0.93 vs. 2.70 ± 1.04, t=8.56) VAS scores were lower than those in the control group ( P<0.001). After treatment, the observation group after surgerythe at 7 d the superior circumference [(48.32 ± 4.57) cm vs. (50.53 ± 3.97) cm, t=2.32], and inferior circumference [(36.71 ± 2.95) cm vs. (39.21 ± 6.86) cm, t=2.12], at 14 d the superior circumference [(45.68 ± 4.69) cm vs. (47.96 ± 3.89) cm, t=2.37], and inferior circumference [(34.96 ± 2.96) cm vs. (36.70 ± 4.35) cm, t=2.10] were lower than those in the control group ( P<0.05). The observation group after surgerythe at 14 d the the knee joint mobility [(115.32 ± 2.12) ° vs. (113.34 ± 2.16) °, t=4.14] and KOOS scores (85.52 ± 0.82 vs. 80.32 ± 1.13, t=23.56) were higher than those in the control group ( P<0.01). Conclusion:TCM ointment rubbing technique has significant advantages in improving pain, swelling and knee joint mobility after artificial knee arthroplasty, which can effectively restore knee joint function.