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.

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: To explore the early clinical efficacy of a three-stage external treatment with traditional Chinese medicine (TCM) in the treatment of talar bone contusion caused by acute ankle sprain. METHODS: A retrospective analysis was performed on 360 patients with primary lateral ankle sprain admitted from September 2021 to July 2024. Patients with talar bone contusion were selected based on MRI examination, and 73 cases were finally included. According to different treatment methods, they were divided into the observation group and the control group. The observation group consisted of 35 cases, including 16 males and 19 females, aged 24 to 37 years old with an average of (30.34±2.68) years old, and received the three-stage external TCM treatment combined with the "POLICE" protocol. The control group included 38 cases, including 18 males and 20 females, aged 24 to 35 years old with an average of (29.87±2.57) years old, and was treated with the "POLICE" protocol alone. The volume of bone marrow edema (BME) area shown by MRI before treatment and 6 weeks after treatment was measured using 3D Slicer software, and the BME improvement rate was calculated. The "Figure of 8" measurement method was used to assess ankle swelling before treatment and at 1 and 3 weeks after treatment. The visual analogue scale (VAS) was used to evaluate ankle pain before treatment and at 1 and 6 weeks after treatment. At 6 weeks after treatment, the American Orthopaedic Foot and Ankle Society (AOFAS) ankle-hindfoot score and Karlsson ankle function score system were used to evaluate the improvement of ankle function. RESULTS: A total of 73 patients with talar bone contusion caused by ankle sprain completed the 6-week follow-up. At 6 weeks after treatment, the BME improvement rate in the observation group was (39.18±0.06)%, which was higher than (26.75±0.03)% in the control group, with a statistically significant difference (P<0.05). After 1 week of treatment, the VAS score in the observation group was (2.89±0.72) points, lower than (3.37±0.79) points in the control group, and the difference was statistically significant (P<0.05). The ankle swelling degree in the observation group was (50.20±3.19) cm, lower than (52.00±3.60) cm in the control group, with a statistically significant difference (P<0.05). After 3 weeks of treatment, there was no statistically significant difference in ankle swelling between the two groups. At 6 weeks after treatment, there was no statistically significant difference in VAS scores between the two groups. At 6 weeks after treatment, the AOFAS ankle-hindfoot score and Karlsson score in the observation group were (87.43±4.18) and (82.77±5.93) points, respectively, which were higher than (82.92±4.87) and (76.45±6.85) points in the control group, with statistically significant differences (P<0.05). According to the AOFAS ankle-hindfoot score, 8 cases were excellent and 27 cases were good in the observation group;2 cases were excellent, 33 cases were good, and 3 cases were fair in the control group. The difference between the two groups was statistically significant (χ²=7.089, P=0.029). CONCLUSION The three-stage external TCM treatment combined with the "POLICE" protocol has a significant early clinical efficacy. It can significantly reduce ankle pain and swelling in patients with bone contusion caused by acute lateral ankle sprain, promote the absorption of bone marrow edema, and accelerate the recovery of ankle function.
Ankle Injuries/drug therapy* ; Drugs, Chinese Herbal/administration & dosage* ; Talus/injuries* ; Retrospective Studies ; Administration, Cutaneous ; Magnetic Resonance Imaging ; Humans ; Male ; Female ; Young Adult ; Adult ; Contusions/etiology* ; Visual Analog Scale ; Musculoskeletal Pain/etiology* ; Recovery of Function/drug effects* ; Treatment Outcome ; Follow-Up Studies

PURPOSE: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. METHODS: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. RESULTS: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. CONCLUSION In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons.
Humans ; Hip Fractures/diagnostic imaging* ; Orthopedic Surgeons ; Algorithms ; Artificial Intelligence

Objective： The aim of this study is to explore the predictive value of biparametric magnetic resonance imaging(bpMRI)for pelvic lymph node metastasis in prostate cancer patients with PSA≤20 μg/L and establish a nomogram. Methods： The imaging data and clinical data of 363 patients undergoing radical prostatectomy and pelvic lymph node dissection in the First Affiliated Hospital of Nanjing Medical University from July 2018 to December 2023 were retrospectively analyzed. Univariate analysis and multivariate logistic regression were used to screen independent risk factors for pelvic lymph node metastasis in prostate cancer, and a nomogram of the clinical prediction model was established. Calibration curves were drawn to evaluate the accuracy of the model. Results： Multivariate logistic regression analysis showed extrocapusular extension (OR=8.08,95%CI=2.62－24.97, P<0.01), enlargement of pelvic lymph nodes (OR=4.45,95%CI=1.16－17.11,P=0.030), and biopsy ISUP grade(OR=1.97,95%CI=1.12－3.46, P=0.018)were independent risk factors for pelvic lymph node metastasis. The C-index of the prediction model was 0.834, which indicated that the model had a good prediction ability. The actual value of the model calibration curve and the prediction probability of the model fitted well, indicating that the model had a good accuracy. Further analysis of DCA curve showed that the model had good clinical application value when the risk threshold ranged from 0.05 to 0.70.Conclusion： For prostate cancer patients with PSA≤20 μg/L, bpMRI has a good predictive value for the pelvic lymph node metastasis of prostate cancer with extrocapusular extension, enlargement of pelvic lymph nodes and ISUP grade≥4.
Humans ; Male ; Prostatic Neoplasms/diagnostic imaging* ; Lymphatic Metastasis ; Retrospective Studies ; Nomograms ; Prostate-Specific Antigen/blood* ; Lymph Nodes/pathology* ; Pelvis ; Predictive Value of Tests ; Prostatectomy ; Lymph Node Excision ; Risk Factors ; Magnetic Resonance Imaging ; Logistic Models ; Middle Aged ; Aged

OBJECTIVE: To analyze RELT gene mutation found in a pedigree with clinical features and inheritable pattern consistent with amelogenesis imperfecta (AI) in China, and to study the relationship between its genotype and phenotype. METHODS: Clinical and radiological features were recorded for the affected individuals. Peripheral venous blood samples of the patient and family members were collected for further study, and the genomic DNA was extracted to identify the pathogenic gene. Whole exome sequencing (WES) was performed to analyze the possible pathogenic genes, and Sanger sequencing was performed for validation. SIFT and PolyPhen-2 were used to predict and analyze the mutation effect. Comparison of RELT amino acids across different species were performed by using Uniprot website. In addition, the three-dimen-sional structures of the wild type and mutant proteins were predicted by Alphafold 2. RESULTS: The proband exhibited typical hypocalcified AI, with heavy wear, soft enamel, rough and discolored surface, and partial enamel loss, while his parents didn ' t have similar manifestations. WES and Sanger sequencing results indicated that the proband carries a homozygous frameshift mutation in RELT gene, NM_032871.3: c.1169_1170del, and both of his parents were carriers. This mutation was predicted to be pathogenic by SIFT and PolyPhen-2. Up to now, there were 11 mutation sites in RELT gene were reported to be associated with AI, and all of the patients exhibited with hypocalcified AI. Compared with the wild-type RELT protein, the mutant protein p. Pro390fs35 conformation terminated prematurely, affecting the normal function of the protein. CONCLUSION Through phenotype analysis, gene sequencing, and functional prediction of a Chinese family with typical amelogenesis imperfecta, this study found that RELT gene frameshift mutation can lead to protein dysfunction in AI patients. Further research will focus on the role and mechanism of RELT in enamel development at the molecular and animal levels, providing molecular biology evidence for the genetic counseling, prenatal diagnosis, and early prevention and treatment of AI.
Humans ; Amelogenesis Imperfecta/genetics* ; Frameshift Mutation ; Male ; Pedigree ; Female ; China ; Exome Sequencing ; Phenotype ; Adult

Functional dyspepsia (FD), characterized by persistent or recurrent dyspeptic symptoms without identifiable organic, systemic or metabolic causes, is an increasingly recognized global health issue. The objective of this guideline is to equip clinicians and nursing professionals with evidence-based strategies for the management and treatment of adult patients with FD using traditional Chinese medicine (TCM). The Guideline Development Group consulted existing TCM consensus documents on FD and convened a panel of 35 clinicians to generate initial clinical queries. To address these queries, a systematic literature search was conducted across PubMed, EMBASE, the Cochrane Library, China National Knowledge Infrastructure (CNKI), VIP Database, China Biology Medicine (SinoMed) Database, Wanfang Database, Traditional Medicine Research Data Expanded (TMRDE), and the Traditional Chinese Medical Literature Analysis and Retrieval System (TCMLARS). The evidence from the literature was critically appraised using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) approach. The strength of the recommendations was ascertained through a consensus-building process involving TCM and allopathic medicine experts, methodologists, pharmacologists, nursing specialists, and health economists, leveraging their collective expertise and empirical knowledge. The guideline comprises a total of 43 evidence-informed recommendations that span a range of clinical aspects, including the pathogenesis according to TCM, diagnostic approaches, therapeutic interventions, efficacy assessments, and prognostic considerations. Please cite this article as: Zhang SS, Zhao LQ, Hou XH, Bian ZX, Zheng JH, Tian HH, Yang GH, Hong WS, He YY, Liu L, Shen H, Li YP, Xie S, Shu J, Zeng BF, Li JX, Liu Z, Xiao ZH, Xiao JD, Zheng PY, Huang SG, Chen SL, Fei GJ. International clinical practice guideline on the use of traditional Chinese medicine for functional dyspepsia (2025). J Integr Med. 2025; 23(5):502-518.
Dyspepsia/drug therapy* ; Humans ; Medicine, Chinese Traditional/methods* ; Practice Guidelines as Topic ; Drugs, Chinese Herbal/therapeutic use*