Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

ObjectiveTo elucidate the critical role of rehabilitation medical records (including electronic records) in rehabilitation medicine's clinical practice and management, comprehensively analyzed the structure, core content and data standards of rehabilitation medical records, to develop a standardized medical record data architecture and core dataset suitable for rehabilitation medicine and to explore the application of rehabilitation data in performance evaluation and payment. MethodsBased on the regulatory documents Basic Specifications for Medical Record Writing and Basic Specifications for Electronic Medical Records (Trial) issued by National Health Commission of China, and referencing the World Health Organization (WHO) Family of International Classifications (WHO-FICs) classifications, International Classification of Diseases (ICD-10/ICD-11), International Classification of Functioning, Disability and Health (ICF), and International Classification of Health Interventions (ICHI Beta-3), this study constructed the data architecture, core content and data standards for rehabilitation medical records. Furthermore, it explored the application of rehabilitation record summary sheets (home page) data in rehabilitation medical statistics and payment methods, including Diagnosis-related Groups (DRG), Diagnosis-Intervention Packet (DIP) and Case Mix Index. ResultsThis study proposed a systematic standard framework for rehabilitation medical records, covering key components such as patient demographics, rehabilitation diagnosis, functional assessment, rehabilitation treatment prescriptions, progress evaluations and discharge summaries. The research analyzed the systematic application methods and data standards of ICD-10/ICD-11, ICF and ICHI Beta-3 in the fields of medical record terminology, coding and assessment. Constructing a standardized data structure and data standards for rehabilitation medical records can significantly improve the quality of data reporting based on the medical record summary sheet, thereby enhancing the quality control of rehabilitation services, effectively supporting the optimization of rehabilitation medical insurance payment mechanisms, and contributing to the establishment of rehabilitation medical performance evaluation and payment based on DRG and DIP. ConclusionStructured rehabilitation records and data standardization are crucial tools for quality control in rehabilitation. Systematically applying the three reference classifications of the WHO-FICs, and aligning with national medical record and electronic health record specifications, facilitate the development of a standardized rehabilitation record architecture and core dataset. Standardizing rehabilitation care pathways based on the ICF methodology, and developing ICF- and ICD-11-based rehabilitation assessment tools, auxiliary diagnostic and therapeutic systems, and supporting terminology and coding systems, can effectively enhance the quality of rehabilitation records and enable interoperability and sharing of rehabilitation data with other medical data, ultimately improving the quality and safety of rehabilitation services.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Aim To investigate the enhanced efficacy and reduced toxicity of GanoExtra in combination with cyclophosphamide(CTX)on inhibiting lung metastasis and immune function in mice.Methods The CCK-8 method was used to verify the cytotoxic effects of Gano-Extra on MCF-7 and 4T1 tumor cells.In vivo experi-ment,a mouse model of lung metastasis of breast canc-er was established by injecting 4T1 tumor cells into the tail vein,which was divided into four groups including 4T1 model group,CTX group,GanoExtra group and GanoExtra+CTX group.The control group was set.After 21 days,the mice were euthanized under anes-thesia,and the body weight of the mice was recorded.Average lung index and spleen index were calculated.The mouse spleen lymphocyte transformation experi-ment was used to determine the activity of spleen cells.The NK cell activity assay was used to determine the activity of NK cells.Blood cells were determined in mouse blood samples.Flow cytometry was used to de-termine the levels of CD4+and CD8+T cells in blood samples.ELISA was used to measure the levels of TNF-α and IL-6 in serum.HE staining was used to ob-serve the pathological morphological changes in tumors and various tissues;and CFSE staining was used to de-termine the proliferative effect of GanoExtra on CD8+cells.Results In vitro GanoExtra at 50 mg·L-1 sig-nificantly inhibited the activity of MCF-7 and 4T1 tumor cells.In the breast cancer pulmonary metastasis model,compared with the model group,the spleen in-dex and blood WBCs content were significantly re-duced,while the activity of NK cells,spleen cells,and the proportion of RBCs,CD 3+and CD 8+T cells in the blood were significantly increased.At the end of the treatment,compared with the CTX group,the number of lung metastases and lung index of the Gano-Extra+CTX group were significantly reduced,and the levels of HGB,CD8+cells,IL-6,and TNF-α in the blood of mice were significantly increased.GanoExtra at 10 mg·L-1 significantly promoted the proliferation of CD8+T cells in vitro.Conclusions GanoExtra can enhance the inhibitory effect of CTX on tumor metasta-sis,alleviate adverse reactions such as splenomegaly and pulmonary enlargement caused by CTX,and have a health-promoting function of promoting the prolifera-tion of CD8+T cells to enhance the immune efficacy of the body.

Aim To investigate the mechanism of py-roptosis mediated by the NLRP3/caspase-1/GSDMD signaling pathway and the intervention effect of Radix Angelica Sinensis and Radix Astragalus ultrafiltration extract(RAS-RA)in radiation-induced pulmonary fi-brosis.Methods Fifty Wistar rats were randomly di-vided into five groups,with ten rats in each group.Ex-cept for the blank control group,all other groups of rats were anesthetized and received a single dose of 40 Gy X-ray local chest radiation to establish a radiation-in-duced pulmonary fibrosis rat model.After radiation,the rats in the RAS-RA intervention groups were orally administered doses of 0.12,0.24 and 0.48 g·kg-1 once a day for 30 days.The average weight and lung index of the rats were observed after 30 days of contin-uous administration.Hydroxyproline(HYP)content in lung tissue was determined by hydrolysis method.The levels of IL-18 and IL-1 β in serum were detected by ELISA.Lung tissue pathological changes were ob-served by HE and Masson staining.Ultrastructural changes in lung tissue were observed by transmission e-lectron microscopy.The expression levels of NLRP3/caspase-1/GSDMD pyroptosis pathway-related proteins and fibrosis-related proteins in lung tissue were detec-ted by Western blot.Results Compared with the blank group,the HYP content in lung tissue and the levels of IL-18 and IL-1 β in serum significantly in-creased in the model group(P＜0.01).HE and Mas-son staining showed inflammatory cell infiltration and collagen fiber deposition.Transmission electron mi-croscopy revealed increased damaged mitochondria,disordered arrangement,irregular morphology,shallow matrix,outer membrane rupture,mostly fractured and shortened cristae,mild expansion,increased electron density of individual mitochondrial matrix,mild sparse structure of lamellar bodies,partial disorder,unclear organelles,and characteristic changes of pyroptosis.Western blot analysis showed increased expression of caspase-1,GSDMD,NLRP3,CoL-Ⅰ,α-SMA,and CoL-Ⅲ proteins(P＜0.01).Compared with the model group,the RAS-RA intervention group showed signifi-cant improvement in body mass index and lung index of rats,decreased levels of IL-18 and IL-1 β inflammatory factors(P＜0.01),improved mitochondrial structure,reduced degree of fibrosis,and decreased expression of caspase-1,GSDMD,NLRP3,COL-Ⅰ,COL-Ⅲ,and α-SMA proteins in lung tissue(P＜0.01).Conclusion RAS-RA has an inhibitory effect on radiation-in-duced pulmonary fibrosis,and its mechanism may be related to the inhibition of pyroptosis through the regu-lation of the NLRP3/caspase-1/GSDMD signaling pathway.

Objective Evaluation of the clinical efficacy of f trochanteric flip osteotomy combined with Kocher-Langen-beck approach for high acetabular posterior wall fracture.Methods Between January 2020 and December 2022,20 patients with high acetabular posterior wall fractures were retrospectively analyzed,including 12 males and 8 females,aged 18 to 75 years old.They were divided into two groups according to the different surgical methods.Ten patients were treated with greater trochanteric osteotomy combined with Kocher-Langenbeck approach as the observation group,including 5 males and 5 fe-males,aged from 18 to 75 years old.Ten patients were treated with Kocher-Langenbeck approach alone as the control group,including 7 males and 3 females,aged from 18 to 71 years old.Matta reduction criteria were used to evaluate the reduction quality of the two groups,and Harris score was used to compare the hip function of the two groups at the latest follow-up.The operation time,blood loss and postoperative complications of the two groups were analyzed.Results All patients were followed up for 10 to 24 months.According to the Matta fracture reduction quality evaluation criteria,the observation group achieved anatomical reduction in 6 cases,satisfactory reduction in 3 cases,and unsatisfactory reduction in 1 case,while the control group only achieved anatomical reduction in 3 cases,satisfactory reduction in 3 cases,and unsatisfactory reduction in 4 cases.At the final follow-up,the Harris hip score ranged from 71.4 to 96.6 in the observation group and 65.3 to 94.5 in the control group.According to the results of Harris score.The hip joint function of the observation group was excellent in 6 cases,good in 3 cases,and fair in 1 case.The hip joint function of the control group was excellent in 2 cases,good in 3 cases,fair in 3 cases,and poor in 2 cases.In the observation group,the intraoperative blood loss ranged from 300 to 700 ml,and the operation dura-tion ranged from 120 to 180 min;in the control group,the intraoperative blood loss ranged from 300 to 650 ml,and the opera-tion duration ranged from 100 to 180 min.Complications in the observation group included 1 case of traumatic arthritis and 1 case of heterotopic ossification,while complications in the control group included 3 cases of traumatic arthritis,3 cases of het-erotopic ossification and 1 case of hip abduction weakness.Conclusions Trochanteric flip osteotomy combined with the Kocher-Langenbeck approach significantly improved anatomical fracture reduction rates,enhanced excellent and good hip joint function outcomes,and reduced surgical complication incidence compared to the Kocher-Langenbeck approach alone.Clinical application of this combined approach is promising,although larger studies are needed for further validation.

Objective To investigate the effect of Ilizarov technique combined with rotational center dome-shaped osteoto-my in the treatment of juvenile distal femoral valgus deformity.Methods A retrospective study was conducted to analyze the clinical data of 11 patients with valgus deformity of the distal femur who had been admitted and followed up completely from January 2016 to October 2020.There were 7 males and 4 females.The 6 patients were on the right side and 5 patients were on the left side.The age ranged from 10 to 14 years old.The center of roration of angulation(CORA)was identified at the distal femur deformity,and dome-shaped osteotomy was performed with the CORA as the midpoint.The annular external fixator was installed according to the needle threading principle of Ilizarov external fixation,and the distal femur was cut off.The valgus deformity under visual inspection of the distal femur was corrected immediately,and the external fixator was fixed and main-tained.The residual deformity and shortening were corrected according to the force line and length of the lower limbs suggested by the weight-bearing full-length anteroposterior and lateral X-rays of both lower limbs.Results All 11 patients were followed up for 13 to 25 months.The time of wearing external fixator was 12 to 17 weeks.In the last follow-up,both lower limbs were measured by the weight-bearing full-length anteroposterior and lateral X-rays,and the length of both lower limbs of 11 patients were equal,and the deformities were corrected.The score of hospital for special surgery(HSS)was used to evaluate the knee function,all of which were excellent.Conclusion The Ilizarov technique was applied in the treatment of distal femoral valgus deformity in adolescents using a rotating central dome-shaped osteotomy.Visual femoral valgus deformity was corrected imme-diately during the operation.After the operation,residual deformities and shortening were dynamically adjusted and corrected according to the force line and shortening degree of lower extremities indicated by the weight-bearing anteroposterior and lateral radiographs of both lower limbs,with minimal damage and fast recovery.