Bayesian Approach in Modeling Prostate Cancer

Abstract

ackground: Prostate cancer is an emerging health problem in Sub-Saharan Africa and it is often diagnosed at an advanced stage due to the lack of access to screening and diagnostic facilities.

Method: This study therefore aimed at modelling the effects of risk factors on the outcome of prostate cancer screening using Generalized Bayesian ordinal logistic regression with random effects then compare the results obtained with the model without random effects. The study further used Mean Squared Errors and established that the estimates for the two models were different

Results: The findings in this study indicate that aged individuals have high chances of having prostate cancer at the early, late or advanced stage. The individual with traces of family history and hereditary breast & ovarian cancer syndrome are also most likely to be in late or advanced stage of prostate cancer.

Conclusion: From the findings aged individuals, having traces of family history and individuals with hereditary breast & ovarian cancer history, should be on alert and understand all symptoms of prostate cancer. For any signs or appearance of prostate cancer symptoms, they are supposed seek for screening services at earliest time possible. In addition, the Ministry of Health should create awareness training and increase screening facilities, this will also encourage for early screening and detection of prostate cancer. The different estimates led to identifying the best model, whereby models with presence of random effects had lowest Widely Applicable Information Criterion values hence they were considered to be the best models in each category.