Determination of prostate cancer risk with fuzzy logic approach

Objective: Prostate cancer biopsy decision is a complex process which is based on various variables but no definitive cut-off value can be used. Due to this limitation, a person who does not actually have the disease may undergo biopsy, a difficult process with infection risk. The aim of this study is to determine the risk of prostate cancer and to provide support to the physician during biopsy decision and to determine which method is more successful when fuzzy logic and logistic regression analysis are compared to prostate cancer risk determination performances. Method: As a result of the interviews with urologists, it was not possible to establish a common opinion about the input variables of the system and their evaluation in a single system. Therefore, the risk of cancer was determined by fuzzy models designed with different approaches and fuzzy models were integrated to each other according to their performance in determining prostate cancer risk. As a result of this integration a new fuzzy system has been developed. Prostate cancer risk estimation performance of fuzzy system was compared with logistic regression analysis. Results: The fuzzy system developed with this study predicted prostate cancer risk with 0.710 AUC, while logistic regression analysis predicted prostate cancer risk with 0.770 AUC. When the AUC values of fuzzy system and logistic regression analysis were compared, a statistically significant difference was found (p <0.001). Conclusion: The fuzzy system developed with this study is created by integrating multiple approaches and has the flexibility of data entry and interpretation. The system decides with five rule tables. This allows the system to repeat the success of the new entries that are outside the data set. However, logistic regression analysis was found to be more successful when were compared the predictive performance of the fuzzy system and binary logistic regression analysis developed on the existing data set. Key words: fuzzy logic, prostate cancer, fuzzy models