Shanshan Su

Objectives: To explore the effectiveness of utilizing ChatGPT 4.0 to assist human physicians in assessing dysphagia in patients undergoing radiotherapy for head and neck cancer. Methods: This prospective study included 100 head and neck cancer (HNC) patients who visited our hospital between January 2025 and October 2025. All participants first underwent an independent dysphagia assessment in the control group conducted by a human physician (Physician A). Subsequently, they were evaluated in the experimental group by a similarly qualified physician (Physician B) with the assistance of ChatGPT 4.0. The comprehensive assessment results from an expert group consisting of two senior head and neck surgeons with ten years of experience served as the “gold standard.” Consistency comparisons of the evaluation results among the three groups were conducted to validate the effectiveness of the language model-assisted assessment. Results: The consistency Kappa index between the experimental group and the expert group was 0.87, indicating a “good” level of consistency, significantly superior to the control group’s 0.70. Subgroup analysis of different EAT-10 and MDADI score ranges showed that in 85 patients with EAT-10 scores ≥ 3: the control group accurately identified 72 cases, achieving an accuracy of 84.7%; the experimental group accurately identified 80 cases, with an accuracy of 94.1%. Among 78 patients with MDADI scores ≤ 69, the control group accurately identified 65 cases (accuracy of 83.3%), while the experimental group identified 73 cases accurately (93.6%). Conclusions: The assessment model combining large language models with human physicians effectively improves the accuracy and consistency of dysphagia assessment in patients undergoing radiotherapy for head and neck cancer.

Objectives: This study is the first to develop and evaluate a machine learning (ML) model for predicting pelvic adhesions based on ultrasound features, utilizing the SHapley Additive Explanations (SHAP) framework for interpretability analysis. Methods: This prospective study included 220 patients who underwent laparoscopic surgery and preoperative ultrasound assessments at our hospital between April 2023 and June 2024. Patients were randomly assigned to training and validation sets. A Least Absolute Shrinkage and Selection Operator regression was used to identify independent risk factors, followed by incorporation into an Extreme Gradient Boosting prediction model. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and a decision curve analysis. Results: The included patients were randomly divided into a training set and a validation set in a 7:3 ratio. The final model included four predictors—obstructed ovarian activity, surgical history, endometriosis, and gynecological inflammation—and demonstrated strong discriminatory performance, with an area under the ROC curve of 0.869 and 0.846 in the training and validation sets, respectively. The ML model demonstrated a sensitivity of 0.946 and a specificity of 0.597 in the training set, while in the validation set, it achieved a sensitivity of 1.000 and a specificity of 0.600. Calibration analyses showed good agreement between predicted and observed outcomes. The model exhibited high clinical utility. SHAP analysis revealed that endometriosis contributed most significantly to the predictions, followed by surgical history, obstructed ovarian activity, and gynecological inflammation. Conclusions: The interpretable ML model developed in this study demonstrates strong predictive performance for assessing the risk of pelvic adhesions in patients prior to surgery. It can be utilized to accurately identify high-risk patients before the procedure, enabling the implementation of appropriate measures during surgery to reduce the occurrence of postoperative pelvic adhesions.

Background/objectives: The epidermal growth factor receptor (EGFR) is a clinically important target, as its expression in patients with breast cancer influences both overall and disease-free survival. Current methods for assessing EGFR expression status in a patient are invasive. Therefore, in this study, we developed a machine learning-based approach utilizing ultrasound radiomics to non-invasively predict EGFR expression status in patients with breast cancer.Methods: Radiomic features were extracted from grayscale and wavelet-transformed ultrasound images of 321 patients. The dataset was randomly split into training (n = 225) and test (n = 96) sets at a 7:3 ratio with stratified sampling to preserve the EGFR+/– ratio. Key predictors were identified using a multi-step procedure—including reproducibility filtering (ICC > 0.75), univariate F-test filtering (p < 0.05), and L1-regularized selection via LASSO regression. Seven machine-learning models were trained. Model interpretability was assessed using SHAP (Shapley Additive Explanations). In addition to the hold-out evaluation, we performed stratified 10-fold cross-validation to reduce selection bias.Results: The random forest model demonstrated the optimal performance, with an area under the receiver operating characteristic curve of 0.86 in the training set and 0.70 in the test set. It significantly outperformed the other models (P < 0.001). The Shapley additive explanation method was used to interpret the model, revealing that original_ngtdm_Coarseness, original_ngtdm_Strength, and wavelet.LL_glcm_ClusterProminence were the top predictors. These features reflect structural compactness and heterogeneity associated with EGFR overexpression.Conclusions: We present a reliable and interpretable tool for non-invasively assessing EGFR expression status in patients with breast cancer. The most important predictors captured tumor heterogeneity and microstructural uniformity, highlighting the biological relevance of radiomic patterns in EGFR-positive tumors. This model integrates advanced imaging analyses with machine learning, underscoring the potential of radiomics to advance precision oncology.

Objectives: This study aims to construct and evaluate 8 machine learning models by integrating ultrasound imaging features, clinical characteristics, and serological features to assess the risk of gallbladder cancer (GBC) occurrence in patients. Methods: A retrospective analysis was conducted on ultrasound and clinical data of 300 suspected GBC patients who visited the Second Affiliated Hospital of Fujian Medical University from January 2020 to January 2024 and 69 patients who visited the Zhongshan Hospital Affiliated to Xiamen University from January 2024 to January 2025. Key relevant features were selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression. Predictive models were constructed using XGBoost, logistic regression, support vector machine, k‐nearest neighbors, random forest, decision tree, naive Bayes, and neural network, with the SHapley Additive exPlanations (SHAP) method employed to explain model interpretability. Results: The LASSO regression demonstrated that gender, age, alkaline phosphatase (ALP), clarity of interface with liver, stratification of the gallbladder wall, intracapsular anechoic lesions, and intracapsular punctiform strong lesions were key features for GBC. The XGBoost model demonstrated an area under receiver operating characteristic curve (AUC) of 0.934, 0.916, and 0.813 in the training, validating, and test sets. SHAP analysis revealed the importance ranking of factors as clarity of interface with liver, stratification of the gallbladder wall, intracapsular anechoic lesions, and intracapsular punctiform strong lesions, ALP, gender, and age. Personalized prediction explanations through SHAP values demonstrated the contribution of each feature to the final prediction, enhancing result interpretability. Furthermore, decision plots were generated to display the influence trajectory of each feature on model predictions, aiding in analyzing which features had the greatest impact on these mispredictions; thereby facilitating further model optimization or feature adjustment. Conclusion: This study proposed a GBC ML model based on ultrasound, clinical, and serological characteristics, indicating the superior performance of the XGBoost model and enhancing the interpretability of the model through the SHAP method.

Objective: Substantial experimental evidence has demonstrated that selenium, an essential micronutrient with pleiotropic physiological effects, also promotes dual antioxidant and anti-inflammatory effects. Meanwhile, the epidemiological association between dietary selenium consumption and mortality risk in diabetic kidney disease (DKD) remains underexplored. This investigation demonstrated a significant association between selenium intake and all-cause mortality among adult populations with DKD. Methods: This study analyzed data from 2183 individuals diagnosed with DKD, obtained from the National Health and Nutrition Examination Survey (NHANES) conducted between 2001 and 2014. The mortality rate was determined through linkage to the National Death Index until December 31, 2015. The hazard ratios (HRs) and their corresponding 95% confidence intervals (95% CIs) were calculated using Cox proportional hazards regression models. Kaplan–Meier survival curves were generated to examine the association between survival probabilities and selenium intake. Results: A total of 1063 mortalities were recorded over an average follow-up period of 8 years. All-cause mortality decreased with higher selenium intake levels. Adjusted for demographic variables, dietary habits, lifestyle factors, glucose regulation, and significant comorbidities, higher selenium intake was associated with improved all-cause mortality among DKD patients (adjusted HR = 0.705, 95% CI: 0.551–0.901). A significant overall association was observed between selenium intake and all-cause mortality risk, as evidenced by restricted cubic spline (RCS) analysis (poverall < 0.001; pnonlinearity = 0.397). Conclusion: Higher dietary selenium intake was significantly associated with lower risk of all-cause mortality after multivariable adjustment for confounders among individuals with DKD.

Objective: To develop a new ultrasound‐based scoring system for pelvic adhesions and evaluate its predictive performance through intraoperative findings during laparoscopy. Methods: This prospective study was conducted from April 2023 to June 2024, including 152 adult patients undergoing laparoscopic surgery at our hospital. Imaging and clinical data were collected, and preoperative assessment of pelvic adhesions was performed using a novel ultrasound scoring system. Pearson correlation analysis was used to assess its correlation with the revised American Fertility Society (rAFS) score. The predictive performance, accuracy, and clinical utility of the new scoring system were evaluated from multiple perspectives using receiver operating characteristic (ROC) curves, calibration curves, decision curve analysis (DCA), and clinical impact curves. Results: Pearson correlation analysis showed a strong correlation (correlation coefficient = 0.88, P < .001) between the new ultrasound scoring system and rAFS. The area under the ROC curve (AUC) for predicting mild, moderate, and severe pelvic adhesions using the new scoring system were 0.927, 0.952, and 0.937, indicating good predictive performance. Calibration curve analysis demonstrated high predictive accuracy for pelvic adhesions. DCA indicated strong clinical utility of the new scoring system, and the clinical impact curve showed its ability to accurately identify high‐risk pelvic adhesion patients during laparoscopic surgery. Conclusions: The newly established scoring system demonstrated good predictive performance, discrimination, and clinical utility, providing a valuable guiding tool for the prediction of the presence or absence of adhesions.

Objectives: Hyperuricaemia has been linked to cognitive decline, yet cerebral structural and haemodynamic changes in this population remain poorly defined. We evaluated transcranial colour-coded duplex (TCCD) sonography as a non-invasive screening tool for early mild cognitive impairment (MCI) in elderly hyperuricaemic men. Methods: In this cross-sectional study, 195 men aged ≥ 60 years with hyperuricaemia were stratified by the Montreal Cognitive Assessment (MoCA) into HUA + MCI (MoCA < 26, n = 46) and HUA (MoCA ≥ 26, n = 149) groups. TCCD measured third-ventricle width (TVW) and peak systolic/end-diastolic velocities to calculate resistive (RI) and pulsatility (PI) indices in the middle (MCA) and posterior (PCA) cerebral arteries. Serum uric acid was recorded. Kernel density plots and receiver operating characteristic (ROC) curves assessed diagnostic performance. Results: The HUA + MCI group exhibited higher serum uric acid (508.5 ± 36.3 vs. 492.9 ± 44.0 µmol/L; p = 0.031), greater TVW (0.55 ± 0.11 vs. 0.51 ± 0.08 cm; p = 0.037), and elevated left PCA RI (0.69 ± 0.07 vs. 0.64 ± 0.06) and PI (1.05 ± 0.17 vs. 0.95 ± 0.12; both p < 0.001). ROC analysis identified left PCA PI as the most specific marker (AUC = 0.701; specificity 90.6%; sensitivity 45.7%). Kernel density plots confirmed distinct distributions of key parameters. Conclusions: TCCD-detected ventricular enlargement and raised PCA pulsatility accurately distinguish MCI among hyperuricaemic men. As a non-invasive, accessible technique with high specificity, TCCD may complement MRI and cognitive testing in early screening of at-risk populations.

Background: This study evaluates the performance of GPT-4o in detecting errors in ACR TIRADS ultrasound reports and its potential to reduce report generation time. Methods: A retrospective analysis of 200 thyroid ultrasound reports from the Second Affiliated Hospital of Fujian Medical University was conducted, with reports categorized as correct or containing up to three errors. GPT-4o's performance was compared with ultrasound physicians of varying experience levels in error detection and processing time. Results: GPT-4o detected 90.0% (180/200) of errors, slightly less than the best-performing senior ultrasound physician's 93.0% (186/200) with no significant difference ( p =  0.281). GPT-4o's error detection rate was comparable to that of ultrasound physicians overall ( p =  0.098 to 0.866). It outperformed Resident 2 in diagnostic errors (87% vs. 69%). Reader agreement was low (Cohen's kappa = 0 to 0.31). GPT-4o reviewed reports significantly faster than all ultrasound physicians (0.79 vs. 1.8 to 3.1 h, p  < 0.001), making it a reliable and efficient tool for error detection in medical imaging. Conclusions: GPT-4o is comparable to experienced ultrasound physicians in error detection and significantly improves report processing efficiency, offering a valuable tool for enhancing diagnostic accuracy and aiding junior residents.

Systemic lupus erythematosus (SLE) is a systemic autoimmune disease with the main clinical characteristics of multi-system and multi-organ involvement of the whole body. It is commonly seen in skin mucosa, skeletal muscle, and respiratory system while rarely involved the spleen. The etiology of SLE is complex and related to many factors such as genetics, sex hormones, and environment. In this case, we present a young female patient with SLE with the symptom of progressing splenic calcification.

Background: We aimed to develop a nomogram that can be combined with point-of-care gastric ultrasound and utilised to predict postoperative nausea and vomiting (PONV) in adult patients after emergency surgery. Methods: Imaging and clinical data of 236 adult patients undergoing emergency surgery in a university hospital between April 2022 and February 2023 were prospectively collected. Patients were divided into a training cohort (n = 177) and a verification cohort (n = 59) in a ratio of 3:1, according to a random number table. After univariate analysis and multivariate logistic regression analysis of the training cohort, independent risk factors for PONV were screened to develop the nomogram model. The receiver operating characteristic curve, calibration curve, decision curve analysis (DCA) and clinical impact curve (CIC) were used to evaluate the prediction efficiency, accuracy, and clinical practicability of the model. Results: Univariate analysis and multivariate logistic regression analysis showed that female sex, history of PONV, history of migraine and gastric cross-sectional area were independent risk factors for PONV. These four independent risk factors were utilised to construct the nomogram model, which achieved significant concordance indices of 0.832 (95% confidence interval [CI], 0.771–0.893) and 0.827 (95% CI, 0.722–0.932) for predicting PONV in the training and validation cohorts, respectively. The nomogram also had well-fitted calibration curves. DCA and CIC indicated that the nomogram had great clinical practicability. Conclusions: This study demonstrated the prediction efficacy, differentiation, and clinical practicability of a nomogram for predicting PONV. This nomogram may serve as an intuitive and visual guide for rapid risk assessment in patients with PONV before emergency surgery.