Lifestyle and occupational risks assessment of bladder cancer using machine learning-based prediction models.

BACKGROUND: Bladder cancer, one of the most prevalent cancers globally, can be regarded as considerable morbidity and mortality for patients. The bladder is an organ that comes in constant exposure to the environment and other risk factors such as inflammation. AIMS: In the current study, we used machine learning (ML) methods and developed risk prediction models for bladder cancer. METHODS: This population-based case-control study is focused on 692 cases of bladder cancer and 692 healthy people. The ML, including Neural Network (NN), Random Forest (RF), Decision Tree (DT), Naive Bayes (NB), Gradient Boosting (GB), and Logistic Regression (LR), were applied, and the model performance was evaluated. RESULTS: The RF (AUC = .86, precision = 79%) had the best performance, and the RT (AUC = .78, precision = 73%) was in the next rank. Based on variable importance analysis in RF, recurrent infection, bladder stone history, neurogenic bladder, smoking and opium use, chronic renal failure, spinal cord paralysis, analgesic, family history of bladder cancer, diabetic mellitus, low dietary intake of fruit and vegetable, high dietary intake of ham, sausage, can and pickles were respectively the most important factors, which effect on the probability of bladder cancer. CONCLUSION: Machine learning approaches can predict the probability of bladder cancer according to medical history, occupational risk factors, and dietary and demographical characteristics.

Effective combination of hydrostatic pressure and aligned nanofibrous scaffolds on human bladder smooth muscle cells: implication for bladder tissue engineering.

Bladder tissue engineering has been the focus of many studies due to its highly therapeutic potential. In this regard many aspects such as biochemical and biomechanical factors need to be studied extensively. Mechanical stimulations such as hydrostatic pressure and topology of the matrices are critical features which affect the normal functions of cells involved in bladder regeneration. In this study, hydrostatic pressure (10 cm H(2)O) and stretch forces were exerted on human bladder smooth muscle cells (hBSMCs) seeded on aligned nanofibrous polycaprolactone/PLLA scaffolds, and the alterations in gene and protein expressions were studied. The gene transcription patterns for collagen type I, III, IV, elastin, α-SMA, calponin and caldesmon were monitored on days 3 and 5 quantitatively. Changes in the expressions of α-SMA, desmin, collagen type I and III were quantified by Enzyme-linked immuno-sorbent assay. The scaffolds were characterized using scanning electron microscope, contact angle measurement and tensile testing. The positive effect of mechanical forces on the functional improvement of the engineered tissue was supported by translational down-regulation of α-SMA and VWF, up-regulation of desmin and improvement of collagen type III:I ratio. Altogether, our study reveals that proper hydrostatic pressure in combination with appropriate surface stimulation on hBSMCs causes a tissue-specific phenotype that needs to be considered in bladder tissue engineering.

Solo Sonographically Guided PCNL under Spinal Anesthesia: Defining Predictors of Success.

Aim. Sonography has been brought in percutaneous nephrolithotripsy (PCNL) as an adjunct to or substitute for X-ray to restrict radiation exposure. This study was designed to investigate the possible predictors for the success of the solo sonographically guided PCNL. Methods. 148 consecutive cases were prospectively enrolled. All steps of PCNL were performed solely with sonography guidance under spinal anesthesia. Residual stones were evaluated the day after surgery using sonography and plain radiography. Results. The mean age was 46 ± 15 years; 40% of kidneys had hydronephrosis. The mean stone burden was 504 ± 350 mm(2). The mean duration of surgery was 43 ± 21 minutes. The early stone-free rate was 92% in inferior or middle calyceal stones, 89.5% in single pelvic stones, 81.5% in partial staghorn stones, and 61.9% in staghorn stones. The mean residual stone size was 13 ± 8 mm. Logistic regression showed that a lower age and a larger stone burden significantly predicted positive residual stones. Fifteen percent of patients presented with grade I or II and six percent showed grade III complication based on Clavien classification. There was no cases of organ injury or death. Conclusion. Solo ultrasonographically guided PCNL under spinal anesthesia is feasible with an acceptable stone-free rate and complication rate.

A novel surgical technique to localize small enteropouch fistula.

BACKGROUND: One of the rare complications of ileal neobladder after radical cystectomy is pouch-to-intestine fistula. There isn't a classic method to intraoperative diagnosis of small fistula. CASE PRESENTATION: An entero-pouch fistula was occurred in a patient after radical cystectomy with ileal orthotopic pouch. Because of failed conservative management, the patient was candidate for surgery. The hidden small fistula in the small intestine was diagnosed by high intraluminal hydrostatic pressure (by intraluminal saline injection). CONCLUSION: Intraoperative diagnosis the intestinal opening of a small fistula is very important. At the time of surgery if the fistula tract becomes open (during releasing the adhesions), it may leak in the peritoneum in postoperative period. Intraluminal high pressure is a useful method for intraoperative small hidden intestine opening.

Expression and prognostic significance of bcl-2 and bax in the progression and clinical outcome of transitional bladder cell carcinoma.

OBJECTIVE: To evaluate the mRNA expression ratio of Bcl-2/Bax both in normal and tumoral bladder tissues of patients with transitional cell carcinoma (TCC) of bladder and investigate potential correlation between this expression ratio and clinical outcome. MATERIALS AND METHODS: In this experimental study, we used real time-PCR to investigate the expression of Bcl-2 and Bax both in normal and tumoral bladder tissues. The Bcl-2/ Bax expression ratio was determined in tumoral bladder tissues of patients with transitional cell carcinoma of the bladder (n=40) and correlation between expression ratios and the emergence of early relapses in a follow-up of 14-30 months was examined. RESULTS: Relapse-free time in 14/31 patients (45.16%) with Bcl-2/Bax>1 was shorter than 9 months (range of 2-9 months) with 5.7 months average median while 17/31 patients (54.84%) with Bcl-2/Bax<1 are currently relapse-free (14-30 months). Bcl-2 and Bax expression levels were not solely correlated with clinical outcome and progression of carcinogenesis. CONCLUSION: The mRNA expression ratio of Bcl-2/Bax in tumoral bladder tissues may serve as a significant prognostic indicator in predicting the clinical outcome in low grade non-invasive bladder cancer.

A Feed-forward Neural Network Algorithm to Detect Thermal Lesions Induced by High Intensity Focused Ultrasound in Tissue.

Non-invasive ultrasound surgeries such as high intensity focused ultrasound have been developed to treat tumors or to stop bleeding. In this technique, incorporation of a suitable imaging modality to monitor and control the treatments is essential so several imaging methods such as X-ray, Magnetic resonance imaging and ultrasound imaging have been proposed to monitor the induced thermal lesions. Currently, the only ultrasound imaging technique that is clinically used for monitoring this treatment is standard pulse-echo B-mode ultrasound imaging. This paper describes a novel method for detecting high intensity focused ultrasound-induced thermal lesions using a feed forward neural-network. This study was carried on in vitro animal tissue samples. Backscattered radio frequency signals were acquired in real-time during treatment in order to detect induced thermal lesions. Changes in various tissue properties including tissue's attenuation coefficient, integrated backscatter, scaling parameter of Nakagami distribution, frequency dependent scatterer amplitudes and tissue vibration derived from the backscattered radio frequency data acquired 10 minutes after treatment regarding to before treatment were used in this study. These estimated parameters were used as features of the neural network. Estimated parameters of two sample tissues including two thermal lesions and their segmented B-mode images were used along with the pathological results as training data for the neural network. The results of the study shows that the trained feed forward neural network could effectively detect thermal lesions in vitro. Comparing the estimated size of the thermal lesion (9.6 mm × 8.5 mm) using neural network with the actual size of that from physical examination (10.1 mm × 9 mm) shows that we could detect high intensity focused ultrasound thermal lesions with the difference of 0.5 mm × 0.5 mm.