The application of an artificial neural network (ANN) in prediction of outcomes using clinical data is being increasingly used. The aim of this study was to assess whether an ANN model is a useful tool for predicting skeletal metastasis in patients with prostate cancer. Consecutive patients with prostate cancer who underwent the technetium-99m methylene diphosphate (Tc-99m MDP) whole body bone scintigraphies were retrospectively analyzed between 2001 and 2005. The predictors were the patient's age and radioimmunometric serum PSA concentration. The outcome variable was dichotomous, either skeletal metastasis or non-skeletal metastasis, based on the results of Tc-99m MDP whole body bone scintigraphy. To assess the performance for classification model in clinical study, the discrimination and calibration of an ANN model was calculated. The enrolled subjects consisted of 111 consecutive male patients aged 72.41 +/- 7.69 years with prostate cancer. Sixty-seven patients (60.4%) had skeletal metastasis based on the scintigraphic diagnosis. The final best architecture of neural network model was four-layered perceptrons. The area under the receiver-operating characteristics curve (0.88 +/- 0.07) revealed excellent discriminatory power (p < 0.001) with the best simultaneous sensitivity (87.5%) and specificity (83.3%). The Hosmer-Lemeshow statistic was 6.74 (p = 0.08 > 0.05), which represented a good-fit calibration. These results suggest that an ANN, which is based on limited clinical parameters, appears to be a promising method in forecasting of the skeletal metastasis in patients with prostate cancer.

Hepatocellular carcinoma (HCC) is a highly invasive malignancy. Recently, GATOR1 (Gap Activity TOward Rags 1) complexes have been shown to play an important role in regulating tumor growth. NPRL2 is a critical component of the GATOR1 complex. Therefore, this study used NPRL2 knockdown to investigate how GATORC1 regulates the prognosis and development of HCC via the mammalian target of rapamycin (mTOR) and autophagy signaling pathways. We established HepG2 cells with NPRL2 knockdown using small interfering RNA (siRNA) and short hairpin RNA (shRNA) systems. The siRNA‐mediated and shRNA‐mediated NPRL2 down‐regulation significantly reduced the expression of NPRL2 and two other GATPOR1 complex components, NPRL3 and DEPDC5, in HepG2 cells; furthermore, the efficient down‐regulation of NPRL2 protein expression by both the shRNA and siRNA systems enhanced the proliferation, migration, and colony formation in vitro. Additionally, the NPRL2 down‐regulation significantly increased HCC growth in the subcutaneous and orthotopic xenograft mouse models. The NPRL2 down‐regulation increased the Rag GTPases and mTOR activation and inhibited autophagy in vitro and in vivo. Moreover, the NPRL2 level in the tumors was significantly associated with mortality, recurrence, the serum alpha fetoprotein level, the tumor size, the American Joint Committee on Cancer stage, and the Barcelona Clinic Liver Cancer stage. Low NPRL2, NPRL3, DEPDC5, and LC3, and high p62 and mTOR protein expression in the tumors was significantly associated with disease‐free survival and overall survival in 300 patients with HCC after surgical resection. Conclusion: The efficient down‐regulation of NPRL2 significantly increased HCC proliferation, migration, and colony formation in vitro, and increased HCC growth in vivo. Low NPRL2 protein expression in the tumors was closely correlated with poorer clinical outcomes in patients with HCC. These results provide a mechanistic understanding of HCC and aid the development of treatments for HCC.

These results suggest that upper extremity radionuclide venography is an easily performed and effective method for diagnosing Port-A catheter thrombosis in clinical practice.