A Comparison of Multi-Layer Neural Network and Logistic Regression in Hereditary Non-Polyposis Colorectal Cancer Risk Assessment

Hereditary non-polyposis colorectal cancer (HN-PCC) is one of the most common autosomal dominant diseases in developed countries. Here, we report on a system to identify the risk of a family having HNPCC based on its history. This is important since population-wide genetic screening for HNPCC is not currently considered feasible due to its complexity and expense. If the risk of a family having HNPCC can be identified/assessed, then only the high risk fraction of the population would undergo intensive screening. Here, we have developed a multi-layer feed-forward neural network to classify families into high-, intermediate- and low-risk categories and compared the result with the benchmark logistic regression model