Okuno, Y. | bioRxiv Science

bioRxiv2018

Prospective randomized controlled study directly comparing tadalafil and tamsulosin for male patients with lower urinary tract symptoms.

Lower urinary tract symptoms are widespread in elderly men and often suggestive of benign prostatic hyperplasia (LUTS/BPH). A randomized, prospective, and open-labeled trial directly comparing the effects of tadalafil (a phosphodiesterase 5 inhibitor) 5 mg once daily and tamsulosin (an 1-blocker) 0.2 mg once daily for 12 weeks in LUTS/BPH patients was conducted. Data were recorded before randomization as well as at 4, 8, and 12 weeks after medication. Fifteen patients allocated tadalafil and 20 allocated tamsulosin completed 12 weeks of medication. Total IPSS, IPSS voiding, and IPSS-QOL scores declined with medication, but there was no difference between drugs. IPSS storage scores reduced more in the tamsulosin group than tadalafil group. OABSS did not decline significantly with medication. IIEF5 was maintained in the tadalafil group, but declined in the tamsulosin group. The maximum flow rate and post-void residual urine volume did not significantly change with medication. Daytime, night-time, and 24-hour urinary frequencies as well as the mean and largest daytime, night-time, and 24-hour voiding volumes per void did not significantly change with medication. In conclusion, tamsulosin was more effective to reduce storage symptoms than tadalafil. Tadalafil had the advantage of maintaining the erectile function.

clinical trials↗

bioRxiv2018

Prediction of prostate cancer by deep learning with multilayer artificial neural network.

ObjectivesTo predict the rate of prostate cancer detection on prostate biopsy more accurately, the performance of deep learning utilizing a multilayer artificial neural network was investigated.\n\nMaterials and methodsA total of 334 patients who underwent multiparametric magnetic resonance imaging before ultrasonography-guided transrectal 12-core prostate biopsy were enrolled in the analysis. Twenty-two non-selected variables as well as selected ones by least absolute shrinkage and selection operator (Lasso) regression analysis and by stepwise logistic regression analysis were input into the constructed multilayer artificial neural network (ANN) programs. 232 patients were used as training cases of ANN programs, and the remaining 102 patients were for the test to output the probability of prostate cancer existence, accuracy of prostate cancer prediction, and area under the receiver operating characteristic (ROC) curve with the learned model.\n\nResultsWith any prostate cancer objective variable, Lasso and stepwise regression analyses selected 12 and 9 explanatory variables from 22, respectively. In common between them, age at biopsy, findings on digital rectal examination, findings in the peripheral zone on MRI diffusion-weighted imaging, and body mass index were positively influential variables, while numbers of previous prostatic biopsy and prostate volume were negatively influential. Using trained ANNs with multiple hidden layers, the accuracy of predicting any prostate cancer in test samples was about 5-10% higher compared with that with logistic regression analysis (LR). The AUCs with multilayer ANN were significantly larger on inputting variables that were selected by the stepwise logistic regression compared with the AUC with LR. The ANN had a higher net-benefit than LR between prostate cancer probability cut-off values of 0.38 and 0.6.\n\nConclusionANN accurately predicted prostate cancer without biopsy marginally better than LR. However, for clinical application, ANN performance may still need improvement.

bioinformatics↗