A machine learning-based nomogram model for predicting the recurrence of cystitis glandularis.

Background: Cystitis glandularis is a chronic inflammatory disease of the urinary system characterized by high recurrence rates, the reasons for which are still unknown. Objectives: This study aims to identify potential factors contributing to recurrence and propose a simple and feasible prognostic model through nomogram construction. Design: Patients with confirmed recurrence based on outpatient visits or readmissions were included in this study, which was subsequently divided into training and validation cohorts. Methods: Machine learning techniques were utilized to screen for the most important predictors, and these were then employed to construct the nomogram. The reliability of the nomogram was assessed through receiver operating characteristic curve analysis, decision curve analysis, and calibration curves. Results: A total of 252 patients met the screening criteria and were enrolled in this study. Over the 12-month follow-up period, the relapse rate was found to be 57.14% (n = 144). The five final predictors identified through machine learning were urinary infections, urinary calculi, eosinophil count, lymphocyte count, and serum magnesium. The area under curve values for all three time points assessing recurrence exceeded 0.75. Furthermore, both calibration curves and decision curve analyses indicated good performance of the nomogram. Conclusion: We have developed a reliable machine learning-based nomogram for predicting recurrence in cystitis glandularis.

A machine learning-based nomogram model for predicting the recurrence of cystitis glandularis Cystitis glandularis (CG) is a chronic inflammatory disease of the urinary system with a high recurrence rate. However, the cause of the recurrence of cystitis glandularis has been controversial. This study aims to establish a reliable clinical model for predicting the recurrence of cystitis glandularis. The data of this study showed that the recurrence of cystitis glandularis was closely related to urinary tract infection, urinary calculi, eosinophil count, lymphocyte count, and serum magnesium ion concentration, and a reliable recurrence prediction model of cystitis glandularis was established by machine learning.

Key Molecules in Bladder Cancer Affect Patient Prognosis and Immunotherapy Efficacy: Further Exploration for CNTN1 and EMP1.

PURPOSE: Immunotherapy has been widely used in bladder cancer (BCa) in recent years and has significantly improved the prognosis of patients with BCa. However, further identification of immunotherapy-sensitive individuals to improve the efficacy of immunotherapy remains an important unmet need. MATERIALS AND METHODS: The key genes were screened and identified from Gene Expression Omnibus database and The Cancer Genome Atlas database to construct the risk prediction function (risk scores). Real-time polymerase chain reaction, immunohistochemistry, and IMvigor210 data sets were used to verify the roles of key molecules and efficacy of risk scores. The biologic function of CNTN1 and EMP1 was further explored through cell proliferation experiments. RESULTS: Five key genes, CNTN1, MAP1A, EMP1, MFAP5, and PTGIS, which were significantly related to the prognosis and immune checkpoint molecules of patients, were screened out. CNTN1 and EMP1 were further experimentally confirmed for their significant tumor-promoting effects. Besides, the constructed risk scores on the basis of these five key genes can accurately predict the prognosis and immunotherapy efficacy of patients with BCa. Interestingly, the high-risk patients identified by the risk scores have significantly worse prognosis and immunotherapy effects than low-risk patients. CONCLUSION: The key genes we screened can affect the prognosis of BCa, tumor microenvironment immune infiltration, and the efficacy of immunotherapy. The risk scores tool we constructed will contribute to the development of individualized treatment for BCa.

Rad54L promotes bladder cancer progression by regulating cell cycle and cell senescence.

Bladder cancer (BCa) is the most prevalent cancer of the urinary system, but its pathogenesis is still poorly understood. Several reports have suggested that gene damage repair is highly correlated with tumor development and drug resistance, in which homologous recombination repair gene Rad54L seems to play an important role, through yet unclear mechanisms. Therefore, this study stratified cancer patients by Rad54L expression in BCa tissue, and high Rad54L expression was associated with a poor prognosis. Mechanistically, we demonstrate that high Rad54L expression promotes abnormal bladder tumor cell proliferation by changing the cell cycle and cell senescence. In addition, this study also suggests that Rad54L may be associated with p53, p21, and pRB in BCa tissue. In summary, this study exposes Rad54L as potential a prognostic biomarker and precision treatment target in BCa.

Clinical implications of 3D printing technology in preoperative evaluation of partial nephrectomy. / 3D打印技术应用于肾部分切除术术前评估中的临床意义.

OBJECTIVES: Renal cancer is a common malignancy of the urinary system, and the partial nephrectomy is a common surgical modality for early renal cancer. 3D printing technology can create a visual three-dimensional model by using 3D digital models of the patient's imaging data. With this model, surgeons can perform preoperative assessment to clarify the location, depth, and blood supply of the tumor, which helps to develop preoperative plans and achieve better surgical outcomes. In this study, the R.E.N.A.L scoring system was used to stratify patients with renal tumors and to explore the clinical application value of 3D printing technology in laparoscopic partial nephrectomy. METHODS: A total of 114 renal cancer patients who received laparoscopic partial nephrectomy in Xiangya Hospital from June 2019 to December 2020 were enrolled. The patients were assigned into an experimental group (n=52) and a control group (n=62) according to whether 3D printing technology was performed, and the differences in perioperative parameters between the 2 groups were compared. Thirty-nine patients were assigned into a low-complexity group (4-6 points), 32 into a moderate-complexity group (7-9 points), and 43 into a high-complexity group (10-12 points) according to R.E.N.A.L score, and the differences in perioperative parameters between the experimental group and the control group in each score group were compared. RESULTS: The experimental group had shorter operative time, renal ischemia time, and postoperative hospital stay (all P<0.05), less intraoperative blood loss (P=0.047), and smaller postoperative blood creatinine change (P=0.032) compared with the control group. In the low-complexity group, there were no statistically significant differences between the experimental group and the control group in operation time, renal ischemia time, intraoperative blood loss, postoperative blood creatinine changes, and postoperative hospital stay (all P>0.05). In the moderate- and high- complexity groups, the experimental group had shorter operative time, renal ischemia time, and postoperative hospital stay (P<0.05 or P<0.001), less intraoperative blood loss (P=0.022 and P<0.001, respectively), and smaller postoperative blood creatinine changes (P<0.05 and P<0.001, respectively) compared with the control group. CONCLUSIONS: Compared with renal tumor patients with R.E.N.A.L score<7, renal cancer patients with R.E.N.A.L score≥7 may benefit more from 3D printing assessment before undergoing partial nephrectomy.