Affiliated Hospital of Guangdong Medical University

The mortality rate of patients undergoing maintenance hemodialysis (MHD) remains high. The C-reactive protein-albumin-lymphocyte (CALLY) index is a novel biomarker that reflects inflammation, nutritional and immune status, all merged into one single derived parameter. No study has yet linked the CALLY index to survival in hemodialysis. This study aims to explore the correlation between the CALLY index and mortality in MHD patients, and develop and validate a nomogram to estimate the likelihood of death in this population.

This retrospective cohort study collected data from 436 patients and they were divided into survival group (n = 335) and non-survival group (n = 101). Multivariate logistic regression analysis was used to screen factors associated with death, and nomograms were developed to estimate the risk of death in MHD patients. The discrimination and calibration of nomograms were validated using the area under the receiver operating characteristic (ROC) curve (AUC) and calibration curve. In the study, stratification analysis and covariate adjustment were conducted to explore the correlation between the CALLY index and the mortality of MHD patients.

In the final model, logistic regression showed that the CALLY index, creatinine, triglycerides, dialysis duration, absolute neutrophil count, blood urea nitrogen, sodium and ferritin were variables associated with mortality in MHD patients. A nomogram was developed to assess the risk of death in MHD patients. The AUC of the model was 0.821 (95% CI: 0.778-0.861). The results of stratified analysis and calibration model showed that the CALLY index was a protective factor for maintaining the mortality of MHD patients.

The CALLY index is closely related to the mortality of MHD patients. A nomogram constructed based on CALLY index can effectively evaluate the mortality risk of MHD patients.

Accurate preoperative prediction of vascular invasion in breast cancer is crucial for surgical planning and patient management. MRI radiomics has shown promise in enhancing diagnostic precision. This study aims to evaluate the effectiveness of integrating MRI radiomic features with clinical data using a deep learning approach to predict vascular invasion in breast cancer patients.

A retrospective analysis was conducted on 102 patients with invasive breast cancer confirmed by surgical pathology. Using the MR750 3.0 T as the examination device, the subject underwent the examination in standard breast positions and sequences. Diffusion-weighted imaging (DWI) was performed with two selected b-values, specifically 0 and 1000 s/mm². Following the injection of the contrast agent, dynamic scans were conducted across six phases, and delayed phase sagittal images were acquired using the VIBRANT sequence. Texture features were extracted from MRI images, and key radiomic and clinical features were selected using variance thresholding, correlation filtering, and logistic regression. A predictive model was developed combining these features, and its performance was evaluated through sensitivity, specificity, and area under the curve (AUC) metrics.

The univariate models based on individual MRI sequences or clinical data demonstrated variable diagnostic performance. In contrast, the multifactorial model that combined radiomic features with clinical data achieved significantly higher accuracy, with an AUC of 0.829, sensitivity of 76.9 %, and specificity of 83.3 %.

Integrating MRI radiomics and clinical data enhances the preoperative prediction of vascular invasion in breast cancer. This approach can improve diagnostic accuracy, providing valuable insights for clinical decision-making and personalized treatment strategies.

Depression associated with Chronic Obstructive Pulmonary Disease (COPD) is a detrimental complication that significantly impairs patients' quality of life. This study aims to develop an online predictive model to estimate the risk of depression in COPD patients.

This study included 2921 COPD patients from the 2018 China Health and Retirement Longitudinal Study (CHARLS), analyzing 36 behavioral, health, psychological, and socio-demographic indicators. LASSO regression filtered predictive factors, and six machine learning models-Logistic Regression, Support Vector Machine, Multilayer Perceptron, LightGBM, XGBoost, and Random Forest-were applied to identify the best model for predicting depression risk in COPD patients. Temporal validation used 2013 CHARLS data. We developed a personalized, interpretable risk prediction platform using SHAP.

A total of 2921 patients with COPD were included in the analysis, of whom 1451 (49.7 %) presented with depressive symptoms. 11 variables were selected to develop 6 machine learning models. Among these, the XGBoost model exhibited exceptional predictive performance in terms of discrimination, calibration, and clinical applicability, with an AUROC range of 0.747-0.811. In validation sets encompassing diverse population characteristics, XGBoost achieved the highest accuracy (70.63 %), sensitivity (59.05 %), and F1 score (63.17 %).

The target population for the model is COPD patients. And the clinical benefits of interventions based on the prediction results remain uncertain.

We developed an online prediction platform for clinical application, allowing healthcare professionals to swiftly and efficiently evaluate the risk of depression in COPD patients, facilitating timely interventions and treatments.