An automatic diagnostic system for the urodynamic study applying in lower urinary tract dysfunction.

OBJECTIVE: To establish an automatic diagnostic system based on machine learning for preliminarily analysis of urodynamic study applying in lower urinary tract dysfunction (LUTD). METHODS: The eight most common conditions of LUTDs were included in the present study. A total of 527 eligible patients with complete data, from the year of 2015 to 2020, were enrolled in this study. In total, two global parameters (patients' age and sex) and 13 urodynamic parameters were considered to be the input for machine learning algorithms. Three machine learning approaches were applied and evaluated in this study, including Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM). RESULTS: By applying machine learning algorithms into the 8 common LUTDs, the DT models achieved the AUC of 0.63-0.98, the LR models achieved the AUC of 0.73-0.99, and the SVM models achieved the AUC of 0.64-1.00. For mutually exclusive diagnoses of underactive detrusor and acontractile detrusor, we developed a classification model that classifies the patients into either of these two diseases or double-negative class. For this classification method, the DT models achieved the AUC of 0.82-0.85 and the SVM models achieved the AUC of 0.86-0.90. Among all these models, the LR and the SVM models showed better performance. The best model of these diagnostic tasks achieved an average AUC of 0.90 (0.90 ± 0.08). CONCLUSIONS: An automatic diagnostic system was developed using three machine learning models in urodynamic studies. This automated machine learning process could lead to promising assistance and enhancements of diagnosis and provide more useful reference for LUTD treatment.

SEMA3G functions as a novel prognostic biomarker associated with Wnt pathway in clear cell renal cell carcinoma.

Renal cell cancer (RCC) is one of the most common cancer, and the incidence of clear cell renal cell cancer rank at the first among multiple subtypes of RCC. Tumor heterogeneity and limited therapies expedite researches and studies on prognostic biomarkers and molecular mechanism. SEMA3G mediates various bimolecular processes but few studies have assessed the influence of SEMA3G on ccRCC. The expression of SEMA3G at mRNA level in ccRCC was analyzed using 4 TCGA datasets. The expression at protein level was verified by immunohistochemistry and western blot. Biological pathway was explored by GSEA and western blot. At both mRNA and protein level, SEMA3G expressed significantly lower in ccRCC tissues compared with normal renal tissues, and the expression was highly associated with clinical stage and pathological grade. Low expression of SEMA3G indicated a poorer overall survival and disease specific survival. Transwell and wound-healing assays showed that overexpressed SEMA3G inhibited the cell motility of renal cancer cells. Upregulated SEMA3G suppressed the invasion and proliferation of both 769-P and 786-O cells. Wnt signaling pathway was tested to work in the interfering of SEMA3G on tumorigenesis and progression of ccRCC. The results provide novel insight into the role of SEMA3G in ccRCC, suggesting the prognostic value and potential suppressor role of SEMA3G.

Bladder wall thickness measured by CT can predict bladder outlet obstruction in men: a retrospective cohort study.

PURPOSE: To evaluate whether bladder wall thickness (BWT) measured by CT can be used to predict bladder outlet obstruction in men with low urinary tract symptoms (LUTS). METHODS: From 2015 to 2018, a total of 120 men with lower urinary tract symptoms who underwent both urodynamic studies and CT tests of the lower abdomen or pelvis were involved. Bladder wall thickness values were measured by CT scanning. RESULTS: Based on the urodynamic studies, 120 men were categorized into two groups, including 70/120 men (58.3%) in the bladder outlet obstruction (BOO) group and 50/120 men (41.7%) in the non-BOO group. The mean BWT was thicker in the BOO group than in the non-BOO group (3.87 vs. 2.75 mm, p < 0.001). The mean maximum bladder capacity (MBC) was lower in the BOO group than in the non-BOO group (263.42 vs. 308.96 ml, p < 0.001). The mean detrusor pressure at maximum urinary flow rate (PdetQmax) was higher in the patients in the BOO group than in those in the non-BOO group (102.28 vs. 49.25 cmH2O, p < 0.001). The ROC curve showed that BWT was a good predictor with an AUC of 0.855 (95% CI 0.785-0.924, p < 0.001). At the cutoff value of 3.20 mm, the predictive sensitivity of BWT for BOO was 72.9%, and the specificity was 90%. CONCLUSION: Increased bladder wall thickness was correlated with bladder outlet obstruction in men with LUTS. Bladder wall thickness measured by CT scans may be a noninvasive parameter to predict bladder outlet obstruction in men with LUTS.

Comprehensive exploration of the expression and prognostic value of AQPs in clear cell renal cell carcinoma.

Aquaporins (AQPs) are a family of membrane water channels that facilitate the passive transport of water across the plasma membrane of cells in response to osmotic gradients created by the active transport of solutes. Water-selective AQPs are involved in tumor angiogenesis, invasion, metastasis and growth. However, the polytype expression patterns and prognostic values of eleven AQPs in clear cell Renal Cell Cancer (ccRCC) have yet to be filled. We preliminarily investigated the transcriptional expression, survival data and immune infiltration of AQPs in patients with renal cell cancer via the Oncomine database, Kaplan-Meier Plotter, UALCAN cancer database, and cBioPortal databases. The ethical approval was waived by the local ethics committee of Peking University People's Hospital for the natural feature of mine into databases. The mRNA expression of AQP1/2/3/4/5/6/7/11 was significantly decreased in ccRCC patients. Meanwhile, MIP and AQP1/2/4/6/7/8/9/11 are notably related to the clinical stage or pathological grade of ccRCC. Lower levels of AQP1/3/4/5/7/10 expression were related to worse overall survival (OS) in patients diagnosed with ccRCC. The AQP mutation rate was 25% in ccRCC patients, but genetic alterations in AQPs were unlikely to be associated with OS and disease free survival in ccRCC patients. In addition, the expression of AQP1, AQP3, AQP4 and AQP10 was positively correlated with immune cells, and the expression of AQP6, AQP7 and AQP11 was negatively correlated with immune cells. AQP9 had a strong and significantly positive correlation with multiple immune cells. Abnormal expression of AQPs in ccRCC indicated the prognosis and immunomodulatory state of ccRCC. Further study needs to be performed to explore AQPs as new biomarkers for ccRCC.