Develop a radiomics-based machine learning model to predict the stone-free rate post-percutaneous nephrolithotomy.

Radiomics and machine learning have been extensively utilized in the realm of urinary stones, particularly in forecasting stone treatment outcomes. The objective of this study was to integrate clinical variables and radiomic features to develop a machine learning model for predicting the stone-free rate (SFR) following percutaneous nephrolithotomy (PCNL). A total of 212 eligible patients who underwent PCNL surgery at the Second Affiliated Hospital of Nanchang University were included in a retrospective analysis. Preoperative clinical variables and non-contrast-enhanced CT images of all patients were collected, and radiomic features were extracted after delineating the stone ROI. Univariate analysis was conducted to identify clinical variables strongly correlated with the stone-free rate after PCNL, and the least absolute shrinkage and selection operator algorithm (lasso regression) was utilized to screen radiomic features. Four supervised machine learning algorithms, including Logistic Regression, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Decision Tree (GBDT), were employed. The clinical variables with strong correlation and screened radiomic features were integrated into the four machine learning algorithms to construct a prediction model, and the receiver operating curve was plotted. The area under the receiver operating curve (AUC), the accuracy rate, the specificity, etc., were used to evaluate the predictive performance of the four models. After analyzing postoperative statistics, the stone-free rate following the procedure was found to be 70.3% (n = 149). Among the various clinical variables examined, factors, such as stone number, stone diameter, stone CT value, stone location, and history of stone surgery, were identified as statistically significant in relation to the stone-free rate after PCNL. A total of 121 radiomic features were extracted, and through lasso regression, 7 features most closely associated with the stone-free rate post-PCNL were identified. The predictive accuracy of different models (Logistic Regression, RF, XGBoost, and GBDT) for determining the stone-free rate after PCNL was evaluated, yielding accuracies of 78.1%, 76.6%, 75.0%, and 73.4%, respectively. The corresponding area under the curve AUC (95%CI) were 0.85 (0.83-0.89), 0.81 (0.76-0.85), 0.82 (0.78-0.85), and 0.77 (0.73-0.81), positioning these models among the top performers in logistic regression prediction. In terms of predictive importance scores, the key factors identified by the logistic regression model were number of stone, zone percentage, stone diameter, and surface area. Similarly, the RF model highlighted number of stone, stone CT value, stone diameter, and surface area as the top predictors. Among the four machine learning models, the logistic regression model demonstrated the highest accuracy and discrimination ability in predicting the stone-free rate following PCNL. In comparison to XGBoost and GBDT, RF also exhibited superior accuracy and a certain level of discrimination ability. However, based on the performance of all four models, logistic regression is more likely to aid in clinical decision-making by assisting clinicians in diagnosing PCNL in patients. This enables us to effectively predict the presence of residual stones post-surgery and ultimately select patients who are suitable candidates for PCNL.

Investigating the role of circulating CXCR5-expressing CD8+ T-cells as a biomarker for bacterial infection in subjects with pneumonia.

BACKGROUND: Recently, lymphoid follicle-confined and circulating CD8+ T-cells expressing the C-X-C chemokine receptor type 5 (CXCR5) were described, which was involved in anti-virus immune response. However, the dynamics and role of circulating CXCR5-expressing CD8+ T-cells during bacterial infection is unknown. So, we asked whether CXCR5+ CD8+ T cells were also generated during bacterial infections in lower respiratory tract. METHODS: The clinical data of 65 pneumonia patients were analyzed. The patients were divided into groups as tuberculosis, bronchiectasis and community or hospital acquired pneumonia (CAP, HAP). The sputum/bronchial secretion or bronchoalveolar lavage fluid (BALF) samples were taken for microbiological examination. The procalcitonin (PCT) was used to evaluate disease severity of these groups and compared among patients. We characterized the number and phenotype (PD-1 and CD103) of CXCR5 + CD8+ T cells in the peripheral circulation by flow cytometry in all individuals and analyzed their association with the serum PCT level and disease severity. RESULTS: Patients were mainly infected with Escherichia coli, Acinetobacter baumannii, Klebsiella pneumonia (K.p), Pseudomonas aeruginosa, and Staphylococcus aureus. Of note is the finding that PCT was weakly correlated with severity of respiratory infections. Furthermore, it was revealed an increase of CXCR5-expressing CD8+ T cells in peripheral blood of un-controlled CAP and progressive HAP compared controlled CAP and HAP, respectively (P < 0.05). Strikingly, the circulating CXCR5-expressing CD8+ T-cells in K.p-infected group was higher than that non-K.p-infected group (P < 0.05). Meanwhile, the ratio of CXCR5 + CD8+/CD8 was positively correlated with PCT level (P < 0.05). In clinic, the determination of CXCR5-expressing CD8+ T-cells showed better results compared to PCT and can be useful for the prediction of exacerbation of CAP or HAP. Phenotypically, CXCR5+ CD8 + T cell expressed comparable level of inhibitory molecules PD-1 and lower CD103 compared to their CXCR5- counterparts. CONCLUSION: The circulating CXCR5-expressing CD8+ T-cell has diagnostic value for current pneumonia severity, and could act as a biomarker for identifying a bacteria-associated exacerbation. These cells may provide novel insight for the pathogenesis of pneumonia.