To assess shifts in long-term survival outcomes for prostate cancer patients, the present study conducted conditional survival (CS) analysis and developed a personalized CS-nomogram to provide dynamic prognostic predictions. Data from 301,441 prostate cancer patients in the Surveillance, epidemiology, and end results (SEER) database were analyzed, with cancer-specific survival (CSS) estimated using the Aalen Johansen estimator. Key predictive factors, including tumor size, lymph node involvement, distant metastasis, and histological grade, were identified via LASSO and multivariable Cox regression analyses to construct the nomogram. Results showed an increase in 12-year CSS from 94.3% at diagnosis to 99.4% for those surviving more than 5 years, with prostate cancer-specific mortality falling below 5% after 5–6 years of survival. The CS-nomogram demonstrated high predictive accuracy, achieving a concordance index (C-index) of 0.869 and area under the curve (AUC) values between 0.847 and 0.904 over a 12-year follow-up period, which provides dynamic, individualized prognostic estimates, supporting the long-term management of prostate cancer patients.

Accurate structural and functional imaging is vital for the diagnosis and prognosis of the urinary system diseases. Near-infrared region (NIR) II fluorescence imaging has shown advantages of high sensitivity, high safety, and fast feedback compared to the conventional imaging methods but limited to its clinical applicability. Herein, we first report that in vivo NIR-II fluorescence imaging of the urinary system enabled by clinically approved and renal-clearable NIR dye methylene blue, which can not only achieve clear invasive/non-invasive urography but also noninvasively detect renal function. These results demonstrate that MB assisted NIR-II fluorescence imaging holds great promise for invasive/noninvasive structural imaging of the urinary system clinically and investigation of renal function in animal models preclinically.

Background: Renal cell carcinoma (RCC) is biologically heterogeneous, complicating prognosis and treatment. Our study aims to clarify prognostic factors and support evidence-based clinical decision-making in RCC management. Methods: This study analyzed clinical data of RCC patients diagnosed between 2010 and 2021 from the Surveillance, Epidemiology, and End Results database. Prognostic factors associated with patient outcomes were selected using least absolute shrinkage and selection operator regression and Boruta. Seven machine learning algorithms were employed to construct predictive models for 5-year survival in RCC patients. Shapley Additive Explanations (SHAP) analysis was utilized to visually interpret the model’s predictions. Model performance was evaluated using the following metrics: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, area under the receiver operating characteristic curve (AUC), Brier score, and estimated calibration index (ECI). Results: In the realm of predicting 5-year survival for RCC patients, the gradient boosting machine (GBM) model achieved the best overall performance with an AUC of 0.841 [95% confidence interval (CI): 0.833–0.850], along with the lowest Brier score (0.127; 95% CI: 0.126–0.128) and ECI (0.005; 95% CI: 0.003–0.007). Furthermore, SHAP analysis highlighted key clinical factors influencing 5-year survival of RCC patients, reinforcing their prognostic significance in RCC. Conclusions: This study developed an accurate predictive model for 5-year survival in RCC patients using machine learning, which may offer valuable support to clinicians in making informed clinical decisions.