Objective To analyze the characteristics of clinical indicators in patients with type 2 diabetes,and to establish a simple and effective risk prediction model for type 2 diabetes complicated with coronary heart disease by screening risk prediction indicators with machine learning.Methods A retrospective study was conducted,and 217 patients diagnosed with coronary artery disease combined with type 2 diabetes mellitus who were hospitalized in the Hospital from January 2022 to November 2023 were selected.Additionally,214 patients diagnosed with T2DM during the same period in the outpatient department were selected as the con-trol group.Their routine laboratory test data were recorded.The Least Absolute Shrinkage and Selection Op-erator(Lasso)algorithm was used to select features,and the models were built by using seven machine learn-ing algorithms:Random Forest,Decision Tree,Support Vector Machine,eXtreme Gradient Boosting,Logistic Regression,K-Nearest Neighbor,and Artificial Neural Network.The diagnostic efficacy of different models through receiver operating characteristic curve(ROC),area under curve(AUC),calibration curve,specificity,sensitivity,F1 value,and other indicators were evaluated.Results Twenty key factors,including age,gender,systolic blood pressure,diastolic blood pressure,heart rate,C-reactive protein and blood glucose were selected using Lasso regression.When incorporated into various models,the SVM model exhibited the highest sensitiv-ity(88.37％),negative predictive value(82.14％),and area under curve(0.845).The Random Forest model had the highest accuracy(76.47％),positive predictive value(76.74％),and F1 score(0.77).Meanwhile,the XGBoost algorithm demonstrated relatively good specificity(80.95％).After introducing the SHAP model,it was inferred that blood glucose had a significant positive impact on the occurrence of coronary heart disease in individuals with type 2 diabetes.Conclusion Machine learning can serve as an effective tool for assessing the risk of coronary heart disease in patients with type 2 diabetes.In this study,SVM,Random Forest,and XG-Boost models all demonstrate good predictive performance,indicating promising clinical application prospects.

Objective:To develop a multi-parameter diagnostic model for pediatric McCune-Albright syndrome(MAS) using machine learning techniques based on laboratory data from MAS patients, with the goal of providing a rapid and reliable auxiliary diagnostic tool for clinical practice.Methods:In this retrospective study, 232 children diagnosed with MAS at the Department of Pediatrics, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine from March 2023 to November 2024 were enrolled as the positive group. After removing duplicate or missing data, 119 cases were finally selected for statistical analysis as the positive group. Meanwhile, 113 children with normal physical examinations during the same period were selected as the control group. The clinical manifestations of the classic " triad" in the positive group were documented. Fasting serum samples were obtained from both groups at 8: 00 AM for laboratory testing, including bone metabolism-related and hormone-related indicators, which served as candidate features. Baseline descriptive analysis was conducted on the hormone-related indicators. For the bone metabolism indicators, six machine learning models—support vector machine(SVM), XGBoost, decision tree, random forest, Logistic regression, and K-nearest neighbor(KNN)—were constructed using R software. XGBoost subgroup analysis was performed based on the triad symptoms. The contribution of individual features to model predictions was visualized using SHAP diagrams. Results:SHAP visualization indicated that age, serum phosphorus, osteocalcin, and β-C-terminal cross-linked telopeptide of type Ⅰ collagen had the greatest average impact on model predictions. Among the six models, the SVM model achieved the highest diagnostic performance, with a sensitivity of 0.742 9, a specificity of 0.909 1, and an area under the curve (AUC) of 0.917.Conclusion:This study demonstrates that machine learning models, based on data from the positive patients and normal controls, can effectively distinguish MAS patients from healthy controls. The diagnostic model developed offers clinicians a valuable tool for early detection of MAS in children, contributing to earlier diagnosis, timely intervention, and improved clinical management.

Objective:To develop a multi-parameter diagnostic model for pediatric McCune-Albright syndrome(MAS) using machine learning techniques based on laboratory data from MAS patients, with the goal of providing a rapid and reliable auxiliary diagnostic tool for clinical practice.Methods:In this retrospective study, 232 children diagnosed with MAS at the Department of Pediatrics, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine from March 2023 to November 2024 were enrolled as the positive group. After removing duplicate or missing data, 119 cases were finally selected for statistical analysis as the positive group. Meanwhile, 113 children with normal physical examinations during the same period were selected as the control group. The clinical manifestations of the classic " triad" in the positive group were documented. Fasting serum samples were obtained from both groups at 8: 00 AM for laboratory testing, including bone metabolism-related and hormone-related indicators, which served as candidate features. Baseline descriptive analysis was conducted on the hormone-related indicators. For the bone metabolism indicators, six machine learning models—support vector machine(SVM), XGBoost, decision tree, random forest, Logistic regression, and K-nearest neighbor(KNN)—were constructed using R software. XGBoost subgroup analysis was performed based on the triad symptoms. The contribution of individual features to model predictions was visualized using SHAP diagrams. Results:SHAP visualization indicated that age, serum phosphorus, osteocalcin, and β-C-terminal cross-linked telopeptide of type Ⅰ collagen had the greatest average impact on model predictions. Among the six models, the SVM model achieved the highest diagnostic performance, with a sensitivity of 0.742 9, a specificity of 0.909 1, and an area under the curve (AUC) of 0.917.Conclusion:This study demonstrates that machine learning models, based on data from the positive patients and normal controls, can effectively distinguish MAS patients from healthy controls. The diagnostic model developed offers clinicians a valuable tool for early detection of MAS in children, contributing to earlier diagnosis, timely intervention, and improved clinical management.

Objective To evaluate the diagnostic efficacy of pelvic floor ultrasound parameters in post-cesarean stress urinary incontinence (SUI) and biofeedback efficacy evaluation. Methods A total of 215 pregnant women who underwent cesarean section were selected by simple sampling method. According to whether postpartum SUI occurred, they were divided into SUI group (n=88) and non-SUI group (n=127). The SUI group received biofeedback therapy. The ultrasonic parameters of pelvic floor were compared between the two groups. The ultrasound parameters of pelvic floor in the SUI group were compared before and after treatment. Results Bladder neck descent (BND), urethral rotation angle (URA) as well as levator hiatal area (LHA) and posterior urethrovesical angle (PUVA) in Valsalva state of the SUI group were significantly higher than those in the non-SUI group (P < 0.05). After biofeedback therapy, the total effective rate of 88 patients with SUI after cesarean section was 94.32%. The BND, URA as well as LHA and PUVA in Valsalva state of the SUI group after treatment were significantly lower than those before treatment (P < 0.05). The area under the curve (AUC) of BND, URA, LHA and PUVA in predicting the effect of biofeedback on post-cesarean section SUI were 0.853, 0.897, 0.865 and 0.887, respectively. Conclusion Pelvic floor ultrasound parameters are highly effective in diagnosing SUI after cesarean section and evaluating the effect of biofeedback therapy.

Objective:To evaluate the reliability and clinical application of a self-established classification system for the lower 1/3 humeral fractures in adults.Methods:A retrospective study was performed to analyze the 88 patients with lower 1/3 humeral fracture who had been admitted to Department of Orthopedics, The Second Hospital of Fuzhou between January 2013 and December 2020. There were 61 males and 27 females with an age of (34.6±12.7) years. The lower 1/3 humeral fractures were classified according to the location of the fracture line, displacement, and bone mass into 3 types: type Ⅰ: transverse and short oblique ones; type Ⅱ: oblique and spiral ones; type Ⅲ: oblique and spiral ones with butterfly-shaped bone mass. After a junior orthopedic surgeon, an intermediate orthopedic surgeon, a senior orthopedic surgeon, and a radiologist had learned this novel classification system, they were asked to classify the lower 1/3 humeral fractures in this cohort independently to assess the reliability of the classification system. Our treatments were based on this novel classification. Open reduction and internal fixation with a unilateral plate through a lateral approach was performed for type Ⅰ fractures, internal fixation with a unilateral plate plus compression screws through a lateral approach for type Ⅱ fractures, and double plate internal fixation through the ulnar and anterolateral approaches for type Ⅲ fractures. The functions of the radial, ulnar, and musculocutaneous nerves and fracture healing time were observed postoperatively. The shoulder and elbow functions were evaluated using Neer shoulder function score and Mayo elbow function score.Results:Of the 88 patients in this cohort, 20 were type Ⅰ, 25 type Ⅱ, and 43 type Ⅲ. The mean Kappa value for inter-observer reliability was 0.878 at the first stage and 0.914 at the second stage, and the mean Kappa value for intra-observer reliability was 0.950. All patients were followed up for (14.1±3.7) months. Iatrogenic injury to the radial nerve was observed in 2 patients, but no injury to the ulnar nerve, the musculocutaneous nerve or important blood vessels or failure of internal fixation was reported. All patients achieved bony union after (12.7±2.0) weeks. The maximum elbow flexion was 137.8°±4.8°, and the maximum elbow extension 2.4°±1.6°. The Mayo elbow function score was (92.0±3.1) points and the Neer shoulder function score (92.2±3.2) points.Conclusions:Our classification system for the lower 1/3 humeral fractures in adults is reliable. As the treatments corresponding to the novel classification system can achieve satisfactory clinical outcomes, the classification system has a clinical value.