Objective:To investigate the diagnostic value of different conventional ultrasound-based radiomics models and their combination with clinical ultrasound features in the pathological subtyping of renal cell carcinoma.Methods:Retrospective data from 286 patients diagnosed with renal cell carcinoma by pathology at the Tenth Affiliated Hospital of Southern Medical University between May 1，2017 and June 7，2024 were collected. Among the 286 patients，203 were clear cell carcinoma，44 were papillary renal cell carcinoma，and 39 were chromophobe renal cell carcinoma. The patients were randomly divided into a training group（201 cases）and a validation group（85 cases）in a ratio of 7 to 3. Regions of interest（ROI）were delineated on conventional ultrasound images，and the radiomics features were extracted. Feature selection was performed using Student's t-test，Pearson correlation，and the least absolute shrinkage and selection operator（LASSO）. Six different machine learning methods included category gradient boosting（CatBoost），light gradient boosting machine（LightGBM），Logistic regression（LR），random forest（RF），support vector machine（SVM）and extreme gradient boosting（XGBoost）were used to establish radiomics models. Weight balancing was applied to correct for sample imbalance，and an imaging genomics model was constructed after balancing the samples. Independent predictors of renal cell carcinoma subtyping were selected from clinical ultrasound features using univariate and multivariate logistic regression analyses，and a clinical imaging model was constructed. The best-performing radiomics model was combined with the clinical independent predictors to construct a combined model. Receiver operating characteristic curves and the obuchowski index were plotted to evaluate model performance. Results:Among the radiomics models，the model constructed using Random Forest（RS RF）after balancing the samples exhibited the best predictive performance，with area under the curve（AUCs）of 0.918（micro-average ROC）and 0.903（macro-average ROC），and the obuchowski index was 0.885 in the validation group. The long and short axes of ultrasound image tumor masses were used as imaging independent predictors to construct a clinical imaging model. In the validation group，the AUCs of the clinical model were 0.886（micro-average ROC）and 0.606（macro-average ROC），and the obuchowski index was 0.569. The combined model achieved AUCs of 0.888（micro-average ROC）and 0.967（macro-average ROC），with an obuchowski index of 0.933，outperforming any single model. Conclusions:The combination of conventional ultrasound-based radiomics models with clinical ultrasound features demonstrates high diagnostic value in differentiating clear cell carcinoma，papillary renal cell carcinoma，and chromophobe renal cell carcinoma. It may serve as an auxiliary tool for providing timely and effective clinical guidance.

Objective To develop models for predicting response to chemotherapy combined with immunotherapy in patients with esophageal squamous carcinoma with various machine learning algorithms,and then select the optimal model.Methods A retrospective study was performed for 174 patients with esophageal squamous cell carcinoma undergoing chemotherapy combined with immunotherapy admitted in Department of Thoracic Surgery of the First Affiliated Hospital of Army Medical University from January 2022 to December 2023.The CT scans and clinical information were collected before treatment.They were randomly divided into a training set(n=122)and a testing set(n=52)in a ratio of 7∶3.CT radiomic features were extracted and selected,and then 5 machine-learning algorithms were employed to establish the prediction models,including radiomics model and clinical-radiomics model.Five-fold cross-validation was conducted on the training set,and the performance of the prediction models was evaluated on the testing set using receiver operating characteristic(ROC)curve and the F1 score.The best-performing model was further explained using local interpretable model-agnostic explanations(LIME)algorithm.Results Among the 174 patients,115(66.1%)achieved clinical remission.From the clinical information and CT images,1 clinical features and 10 radiomic features were identified.The area under of ROC curve(AUC)for the radiomics and clinical-radiomics models was 0.750(95%CI:0.616～0.883),and 0.766(95%CI:0.637～0.895),respectively.The F1 score of the optimal clinical-radiomics model was 0.829.LIME algorithm indicated that this best model demonstrated reliability in predicting individual samples.Conclusion The clinical-radiomics prediction model based on machine learning algorithm performs well,and can provide a reference for doctors'clinical decision-making by predicting the response to chemotherapy combined with immunotherapy in patients with esophageal squamous cell carcinoma.

Large language models (LLMs) such as ChatGPT, Claude, Llama, and Qwen are emerging as transformative technologies for the diagnosis and treatment of various diseases. With their exceptional long-context reasoning capabilities, LLMs are proficient in clinically relevant tasks, particularly in medical text analysis and interactive dialogue. They can enhance diagnostic accuracy by processing vast amounts of patient data and medical literature and have demonstrated their utility in diagnosing common diseases and facilitating the identification of rare diseases by recognizing subtle patterns in symptoms and test results. Building on their image-recognition abilities, multimodal LLMs (MLLMs) show promising potential for diagnosis based on radiography, chest computed tomography (CT), electrocardiography (ECG), and common pathological images. These models can also assist in treatment planning by suggesting evidence-based interventions and improving clinical decision support systems through integrated analysis of patient records. Despite these promising developments, significant challenges persist regarding the use of LLMs in medicine, including concerns regarding algorithmic bias, the potential for hallucinations, and the need for rigorous clinical validation. Ethical considerations also underscore the importance of maintaining the function of supervision in clinical practice. This paper highlights the rapid advancements in research on the diagnostic and therapeutic applications of LLMs across different medical disciplines and emphasizes the importance of policymaking, ethical supervision, and multidisciplinary collaboration in promoting more effective and safer clinical applications of LLMs. Future directions include the integration of proprietary clinical knowledge, the investigation of open-source and customized models, and the evaluation of real-time effects in clinical diagnosis and treatment practices.
Humans ; Large Language Models ; Tomography, X-Ray Computed

Objective To investigate the effects of transcranial direct current stimulation(tDCS)combined with resistance training on the performance of college students completing pull-ups,and explore the potential mechanisms underlying the effects of training intervention from the perspective of neuromuscular activity control.Methods A total of 25 male college student volunteers were randomly divided into the tDCS combined with resistance training group(experiment group)and resistance training group(control group).Twelve subjects in the control group received a lat pull-down strength training intervention lasting for 8 weeks,with 4 sets of 12 movement repetitions each,3 times per week.Thirteen subjects in the experimental group received a 20-minute tDCS before the lat pull-up resistance training intervention.Lat pull-down isometric maximal voluntary contraction(MVC)force,lat pull-down maximal repetitions under 80％one-repetition maximum(1RM)loading,and conventional pull-up exercise were tested before and after the training intervention.Surface electromyography(sEMG)signals of the main exertion muscles of the upper limb were recorded during the pull-up exercise test.Results After the training intervention,the number of pull-ups completed by the experimental group and control group increased by 1.74 times and 1.42 times,respectively.Subjects in both groups showed significant improvements in their MVC and lat pull-down maximal repetitions under 80％1RM loading.However,there were no statistical differences in these indicators between groups.Activation levels of the agonist muscles brachioradialis,posterior deltoid,and pectoralis major were significantly decreased after the training compared to those before training for both groups.In addition,the coactivation level of the antagonist triceps brachii muscle in the experimental group significantly decreased from 0.50±0.22 to 0.37±0.09 after the training,while there was no significant change in the control group before and after the intervention.Conclusions Eight-week tDCS combined with resistance training and resistance training alone can significantly improve the pull-up performance of college students,which may be related to the fact that both types of training can significantly improve the active muscle contraction capacity.Combined with resistance training,tDCS is more effective in decreasing the coactivation level of triceps brachii during pull-ups and increasing the contraction efficiency of elbow joint muscles.

Purpose This study aimed to investigate the expression,function,and molecular mechanisms of ZNF384 in esophageal squamous cell carcinoma(ESCC),as well as its role in tumor progression and chemoresistance.Methods The expression of ZNF384 in ESCC cell lines and tissues was assessed using RT-qPCR.Correlations with TNM stage,invasion depth,lymph node metastasis,and prognosis were evaluated.In vitro assays were performed to examine the effects of ZNF384 on ESCC cell proliferation,migration,invasion,and chemosensitivity.Dual-luciferase reporter assays were conducted to determine the interaction between ZNF384 and FZD3,and to assess the activation of the Wnt signaling pathway.Results ZNF384 expression was significantly upregulated in ESCC cell lines and tissues(P＜0.01).Elevated ZNF384 expression was associated with advanced TNM stage,greater invasion depth,lymph node metastasis,and poor prognosis(P＜0.05).Functional assays demonstrated that ZNF384 overexpression promo-ted ESCC cell proliferation,migration,and invasion(all P＜0.01),whereas ZNF384 knockdown inhibited these processes and enhanced chemosensitivity to cisplatin(all P＜0.01).Mechanistic studies showed that ZNF384 directly bound to the FZD3 promoter,upregulated FZD3 expression,and activated the Wnt signaling pathway(P＜0.05).Overexpression of FZD3 partially reversed the inhibitory effects of ZNF384 knockdown on cell malignancy and chemore-sistance(P＜0.05).Conclusion ZNF384 promotes ESCC progression and reduces chemosensitivity through activa-tion of the FZD3/Wnt signaling pathway,suggesting its potential as a therapeutic target in ESCC.

Objective:To investigate the dynamic cerebral oxygen metabolism characteristics in drug-naive patients with primary insomnia (PI), and analyze the association between the cerebral oxygen metabolism and insomnia symptoms.Methods:A total of 31 drug-naive patients with PI and 36 healthy controls were recruited from July 2024 to February 2025. Insomnia symptoms were assessed by the Pittsburgh sleep quality index (PSQI). Functional near infrared spectroscopy (fNIRS) technique was employed to collect 180 s resting-state oxygenated hemoglobin concentration changes from dorsolateral prefrontal cortex (DLPFC), medial prefrontal cortex, temporal lobe (TL), parietal lobe (PL) and occipital lobe. Sliding time window analysis and K-means clustering algorithm were applied to cluster the oxygenation data into K temporal categories. Statistical analysis, including t-test, Wilcoxon rank-sum test, chi-square test, Pearson/Spearman correlation analysis, and multiple linear regression were performed using SPSS 26.0 software. Results:Clustering analysis revealed 4 characteristic temporal categories (K=4) during the 180 s resting-state. Compared to healthy controls, drug-naive PI patients exhibited higher oxygenation levels in bilateral TLs during the second temporal category(left TL(18.19±6.18)mmol/dL, (16.82±4.47)mmol/dL; right TL(18.20±8.97)mmol/dL, (16.17±5.64)mmol/dL), but lower levels during the third temporal category(left TL(16.54± 5.09)mmol/dL, (17.98±5.34)mmol/dL; right TL(15.82±7.29)mmol/dL, (17.84±5.94)mmol/dL), and exhibited lower oxygenation level in right PL during the second category((16.16±6.56)mmol/dL, (17.60±5.84)mmol/dL) (all P<0.05). Oxygenation levels in the right DLPFC during the first temporal category ( β=0.44, t=2.52, P=0.018), in the left DLPFC during the second temporal category( β=-0.47, t=-2.82, P=0.009), and in the right PL during the second temporal category( β=-0.46, t=-2.78, P=0.010) were influencing factors for the PSQI score. Conclusions:The bilateral TLs and right PL in drug-naive PI patients exhibit phase-specific abnormalities in oxygen metabolism, potentially attributable to the insomnia-induced dysregulation of endogenous neural oscillations. The oxygen concentration changes in bilateral DLPFCs and right TL are associated with insomnia symptoms.

Objective:To investigate the dynamic cerebral oxygen metabolism characteristics in drug-naive patients with primary insomnia (PI), and analyze the association between the cerebral oxygen metabolism and insomnia symptoms.Methods:A total of 31 drug-naive patients with PI and 36 healthy controls were recruited from July 2024 to February 2025. Insomnia symptoms were assessed by the Pittsburgh sleep quality index (PSQI). Functional near infrared spectroscopy (fNIRS) technique was employed to collect 180 s resting-state oxygenated hemoglobin concentration changes from dorsolateral prefrontal cortex (DLPFC), medial prefrontal cortex, temporal lobe (TL), parietal lobe (PL) and occipital lobe. Sliding time window analysis and K-means clustering algorithm were applied to cluster the oxygenation data into K temporal categories. Statistical analysis, including t-test, Wilcoxon rank-sum test, chi-square test, Pearson/Spearman correlation analysis, and multiple linear regression were performed using SPSS 26.0 software. Results:Clustering analysis revealed 4 characteristic temporal categories (K=4) during the 180 s resting-state. Compared to healthy controls, drug-naive PI patients exhibited higher oxygenation levels in bilateral TLs during the second temporal category(left TL(18.19±6.18)mmol/dL, (16.82±4.47)mmol/dL; right TL(18.20±8.97)mmol/dL, (16.17±5.64)mmol/dL), but lower levels during the third temporal category(left TL(16.54± 5.09)mmol/dL, (17.98±5.34)mmol/dL; right TL(15.82±7.29)mmol/dL, (17.84±5.94)mmol/dL), and exhibited lower oxygenation level in right PL during the second category((16.16±6.56)mmol/dL, (17.60±5.84)mmol/dL) (all P<0.05). Oxygenation levels in the right DLPFC during the first temporal category ( β=0.44, t=2.52, P=0.018), in the left DLPFC during the second temporal category( β=-0.47, t=-2.82, P=0.009), and in the right PL during the second temporal category( β=-0.46, t=-2.78, P=0.010) were influencing factors for the PSQI score. Conclusions:The bilateral TLs and right PL in drug-naive PI patients exhibit phase-specific abnormalities in oxygen metabolism, potentially attributable to the insomnia-induced dysregulation of endogenous neural oscillations. The oxygen concentration changes in bilateral DLPFCs and right TL are associated with insomnia symptoms.

Purpose This study aimed to investigate the expression,function,and molecular mechanisms of ZNF384 in esophageal squamous cell carcinoma(ESCC),as well as its role in tumor progression and chemoresistance.Methods The expression of ZNF384 in ESCC cell lines and tissues was assessed using RT-qPCR.Correlations with TNM stage,invasion depth,lymph node metastasis,and prognosis were evaluated.In vitro assays were performed to examine the effects of ZNF384 on ESCC cell proliferation,migration,invasion,and chemosensitivity.Dual-luciferase reporter assays were conducted to determine the interaction between ZNF384 and FZD3,and to assess the activation of the Wnt signaling pathway.Results ZNF384 expression was significantly upregulated in ESCC cell lines and tissues(P＜0.01).Elevated ZNF384 expression was associated with advanced TNM stage,greater invasion depth,lymph node metastasis,and poor prognosis(P＜0.05).Functional assays demonstrated that ZNF384 overexpression promo-ted ESCC cell proliferation,migration,and invasion(all P＜0.01),whereas ZNF384 knockdown inhibited these processes and enhanced chemosensitivity to cisplatin(all P＜0.01).Mechanistic studies showed that ZNF384 directly bound to the FZD3 promoter,upregulated FZD3 expression,and activated the Wnt signaling pathway(P＜0.05).Overexpression of FZD3 partially reversed the inhibitory effects of ZNF384 knockdown on cell malignancy and chemore-sistance(P＜0.05).Conclusion ZNF384 promotes ESCC progression and reduces chemosensitivity through activa-tion of the FZD3/Wnt signaling pathway,suggesting its potential as a therapeutic target in ESCC.

Objective To investigate the effects of transcranial direct current stimulation(tDCS)combined with resistance training on the performance of college students completing pull-ups,and explore the potential mechanisms underlying the effects of training intervention from the perspective of neuromuscular activity control.Methods A total of 25 male college student volunteers were randomly divided into the tDCS combined with resistance training group(experiment group)and resistance training group(control group).Twelve subjects in the control group received a lat pull-down strength training intervention lasting for 8 weeks,with 4 sets of 12 movement repetitions each,3 times per week.Thirteen subjects in the experimental group received a 20-minute tDCS before the lat pull-up resistance training intervention.Lat pull-down isometric maximal voluntary contraction(MVC)force,lat pull-down maximal repetitions under 80％one-repetition maximum(1RM)loading,and conventional pull-up exercise were tested before and after the training intervention.Surface electromyography(sEMG)signals of the main exertion muscles of the upper limb were recorded during the pull-up exercise test.Results After the training intervention,the number of pull-ups completed by the experimental group and control group increased by 1.74 times and 1.42 times,respectively.Subjects in both groups showed significant improvements in their MVC and lat pull-down maximal repetitions under 80％1RM loading.However,there were no statistical differences in these indicators between groups.Activation levels of the agonist muscles brachioradialis,posterior deltoid,and pectoralis major were significantly decreased after the training compared to those before training for both groups.In addition,the coactivation level of the antagonist triceps brachii muscle in the experimental group significantly decreased from 0.50±0.22 to 0.37±0.09 after the training,while there was no significant change in the control group before and after the intervention.Conclusions Eight-week tDCS combined with resistance training and resistance training alone can significantly improve the pull-up performance of college students,which may be related to the fact that both types of training can significantly improve the active muscle contraction capacity.Combined with resistance training,tDCS is more effective in decreasing the coactivation level of triceps brachii during pull-ups and increasing the contraction efficiency of elbow joint muscles.

Objective:To investigate the diagnostic value of different conventional ultrasound-based radiomics models and their combination with clinical ultrasound features in the pathological subtyping of renal cell carcinoma.Methods:Retrospective data from 286 patients diagnosed with renal cell carcinoma by pathology at the Tenth Affiliated Hospital of Southern Medical University between May 1，2017 and June 7，2024 were collected. Among the 286 patients，203 were clear cell carcinoma，44 were papillary renal cell carcinoma，and 39 were chromophobe renal cell carcinoma. The patients were randomly divided into a training group（201 cases）and a validation group（85 cases）in a ratio of 7 to 3. Regions of interest（ROI）were delineated on conventional ultrasound images，and the radiomics features were extracted. Feature selection was performed using Student's t-test，Pearson correlation，and the least absolute shrinkage and selection operator（LASSO）. Six different machine learning methods included category gradient boosting（CatBoost），light gradient boosting machine（LightGBM），Logistic regression（LR），random forest（RF），support vector machine（SVM）and extreme gradient boosting（XGBoost）were used to establish radiomics models. Weight balancing was applied to correct for sample imbalance，and an imaging genomics model was constructed after balancing the samples. Independent predictors of renal cell carcinoma subtyping were selected from clinical ultrasound features using univariate and multivariate logistic regression analyses，and a clinical imaging model was constructed. The best-performing radiomics model was combined with the clinical independent predictors to construct a combined model. Receiver operating characteristic curves and the obuchowski index were plotted to evaluate model performance. Results:Among the radiomics models，the model constructed using Random Forest（RS RF）after balancing the samples exhibited the best predictive performance，with area under the curve（AUCs）of 0.918（micro-average ROC）and 0.903（macro-average ROC），and the obuchowski index was 0.885 in the validation group. The long and short axes of ultrasound image tumor masses were used as imaging independent predictors to construct a clinical imaging model. In the validation group，the AUCs of the clinical model were 0.886（micro-average ROC）and 0.606（macro-average ROC），and the obuchowski index was 0.569. The combined model achieved AUCs of 0.888（micro-average ROC）and 0.967（macro-average ROC），with an obuchowski index of 0.933，outperforming any single model. Conclusions:The combination of conventional ultrasound-based radiomics models with clinical ultrasound features demonstrates high diagnostic value in differentiating clear cell carcinoma，papillary renal cell carcinoma，and chromophobe renal cell carcinoma. It may serve as an auxiliary tool for providing timely and effective clinical guidance.