Objective To investigate the association of the preoperative systemic immune‐inflammation index (SII) with recurrence‐free survival (RFS) after transurethral resection of the bladder tumor (TURBT) of non‐muscle‐invasive bladder cancer (NMIBC) using propensity score matching (PSM) analysis. Methods The clinicopathological characteristics and follow‐up data of NMIBC patients were collected retrospectively from two tertiary medical centers. A 1:1 PSM analysis was carried out using the nearest‐neighbor method (caliper size: 0.02). Cox regression analysis was used to identify the risk factors associated with RFS. Results A total of 416 NMIBC patients were included in this study. Before and after matching, patients with increased SII had worse RFS ( p < 0.0001 and p = 0.027, respectively). Multivariate Cox analysis identified SII as an independent predictor of RFS before (HR [95% CI]: 1.789 [1.232, 2.599], p = 0.002) and after matching (HR [95% CI]: 1.646 [1.077, 2.515], p = 0.021). In the matched subgroup analysis, an elevated SII had a significant association with postoperative worse RFS in the T1 stage ( p = 0.025), primary status ( p = 0.049), high‐grade ( p = 0.0015), and multiple lesions ( p = 0.043) subgroups. Conclusion SII could accurately stratify the prognosis of NMIBC patients before and after PSM analysis. An elevated SII was significantly associated with worse RFS in NMIBC patients.

Background Previous studies suggested that bone metastasis has a significant effect on the time of progression to metastatic castration-resistant prostate cancer (CRPC) for newly diagnosed de novo bone metastatic hormone-sensitive prostate cancer (mHSPC). Nevertheless, the effect of different bone metastasis sites was not fully evaluated. This study aimed to develop and validate a novel bone metastatic risk model. Methods We enrolled 122 patients who were newly diagnosed with de novo bone metastatic prostate cancer following primary androgen deprivation based therapy at our institution from January 2008 to June 2021. The metastatic bone sites were classified into six sites: skull; cervical, thoracic, and lumbar vertebrae; chest (ribs and sternum); pelvis; upper limbs; and lower limbs. We calculated the bone metastatic score (BMS) for each site: 0 points were assigned for non-metastasis and 1 point was assigned for metastasis. The X-tile was adopted to acquire optimal cutoff points of BMS. We defined high-risk group (HRG) as BMS ≥ 3 and low-risk group (LRG) as BMS < 3. The new bone risk stratification was validated by calculating the area under the receiver operating characteristic curve (AUC). Subsequently, the relevant clinical prognostic variables were added to construct a predictive nomogram for predicting CRPC. Results The median patient age was 73 years. Most patients had Gleason score ≤8 (93 cases, 76.2%). The median follow-up duration was 11.5 months (range: 2–92 months). Eighty-six patients progressed to CRPC during the follow-up. The most common bone metastatic site was the pelvis (90.2%). The median BMS was 4. Seventy-six patients had HRG, while forty-six had LRG. The 1-, 2-, and 3-year AUCs for H/LRG were 0.620, 0.754, and 0.793, respectively. The HRG was associated with earlier time to CRPC. A nomogram based on four parameters (Gleason score, H/LRG, prostate-specific antigen [PSA] nadir, and time to PSA nadir) was developed to predict CRPC. Internal validation using bootstrapping demonstrated good accuracy for predicting the CRPC (C-index: 0.727). The calibration analysis demonstrated that the model performed well. Conclusion We established a novel H/LRG risk model for newly diagnosed de novo bone metastatic prostate cancer, which provided evidence to support clinical decision-making.

Background Bone metastasis has been suggested to be a significant impactor on the prognosis of newly diagnosed de novo metastatic hormone-sensitive prostate cancer (mHSPC), and some risk stratification models have been proposed on the basis of this hypothesis. However, the effectiveness of these risk stratification criteria has not been fully evaluated in China. This study aimed to evaluate the effectiveness of the risk stratification models in China. Methods A total of 140 patients who were newly diagnosed with metastatic prostate cancer followed by primary androgen deprivation-based therapy from January 2008 to June 2021 at our institution were enrolled in this study. The patients were divided into different groups on the basis of high- and low-volume disease (H/LVD) criteria, high-and low-risk disease (H/LRD) criteria, extremity bone metastasis criteria (EBM), and extent of disease (EOD) criteria. The area under the receiver operating characteristic (ROC) curve (AUC) and decision curve analysis (DCA) were used to compare the validity and net benefit of these models. Using the Cox proportional hazards model, we performed univariable and multivariable analyses of the factors influencing overall survival (OS) and the time of progression to metastatic castration-resistant prostate cancer (CRPC). Results The median patient age was 72 years. Most patients had a Gleason score ≥8 (102 cases, 72.9%) and clinical T stage >2 (75 cases, 53.6%). The median follow-up time was 25 months (range, 2–95 months). Ninety-two patients progressed to CRPC and fifty-seven patients died during the follow-up. The AUC of OS and CRPC showed that the EOD model had higher validity than the other risk stratification models. DCA shows that the net benefit of the EOD model on OS was better than that of the other risk stratification models. As for CRPC, the net benefit of the EOD model was second only to that of the H/LRD model when the threshold was <0.5; however, when the threshold was >0.5, the EOD model outperformed the other models. The effectiveness of EOD as an independent prognostic variable was verified through univariable and multivariable analyses. Conclusion The EOD model yields reasonable risk stratification for use in Chinese mHSPC patients, providing further evidence supporting its role in clinical decision-making.

BackgroundTransurethral resection of the bladder tumor with or without adjuvant intravesical instillation (IVI) has been the standard treatment for non-muscle-invasive bladder cancer (NMIBC), whereas a high percentage of patients still experience local tumor recurrence and disease progression after receiving the standard treatment modalities. Unfortunately, current relevant prediction models for determining the recurrent and progression risk of NMIBC patients are far from impeccable.MethodsClinicopathological characteristics and follow-up information were retrospectively collected from two tertiary medical centers between October 2018 and June 2021. The least absolute shrinkage and selection operator (LASSO) and Cox regression analysis were used to screen potential risk factors affecting recurrence-free survival (RFS) of patients. A nomogram model was established, and the patients were risk-stratified based on the model scores. Both internal and external validation were performed by sampling the model with 1,000 bootstrap resamples.ResultsThe study included 299 patient data obtained from the Affiliated Hospital of Xuzhou Medical University and 117 patient data obtained from the First Affiliated Hospital of Guangxi Medical University. Univariate regression analysis suggested that urine red blood cell count and different tumor invasion locations might be potential predictors of RFS. LASSO-Cox regression confirmed that prior recurrence status, times of IVI, and systemic immune-inflammation index (SII) were independent factors for predicting RFS. The area under the curve for predicting 1-, 2-, and 3-year RFS was 0.835, 0.833, and 0.871, respectively. Based on the risk stratification, patients at high risk of recurrence and progression could be accurately identified. A user-friendly risk calculator based on the model is deposited at https://dl0710.shinyapps.io/nmibc_rfs/.ConclusionInternal and external validation analyses showed that our model had excellent predictive discriminatory ability and stability. The risk calculator can be used for individualized assessment of survival risk in NMIBC patients and can assist in guiding clinical decision-making.

ObjectiveInguinal lymph node metastasis (ILNM) is significantly associated with poor prognosis in patients with squamous cell carcinoma of the penis (SCCP). Patient prognosis could be improved if the probability of ILNM incidence could be accurately predicted at an early stage. We developed a predictive model based on machine learning combined with big data to achieve this.MethodsData of patients diagnosed with SCCP were obtained from the Surveillance, Epidemiology, and End Results Program Research Data. By combing variables that represented the patients' clinical characteristics, we applied five machine learning algorithms to create predictive models based on logistic regression, eXtreme Gradient Boosting, Random Forest, Support Vector Machine, and k-Nearest Neighbor. Model performance was evaluated by ten-fold cross-validation receiver operating characteristic curves, which were used to calculate the area under the curve of the five models for predictive accuracy. Decision curve analysis was conducted to estimate the clinical utility of the models. An external validation cohort of 74 SCCP patients was selected from the Affiliated Hospital of Xuzhou Medical University (February 2008 to March 2021).ResultsA total of 1,056 patients with SCCP from the SEER database were enrolled as the training cohort, of which 164 (15.5%) developed early-stage ILNM. In the external validation cohort, 16.2% of patients developed early-stage ILNM. Multivariate logistic regression showed that tumor grade, inguinal lymph node dissection, radiotherapy, and chemotherapy were independent predictors of early-stage ILNM risk. The model based on the eXtreme Gradient Boosting algorithm showed stable and efficient prediction performance in both the training and external validation groups.ConclusionThe ML model based on the XGB algorithm has high predictive effectiveness and may be used to predict early-stage ILNM risk in SCCP patients. Therefore, it may show promise in clinical decision-making.