Because gene expression profiles in normal cells are different from those of cancer cells, experimental results of the tests can diagnose a cancerous person. However, the gene data are usually with high variable dependent, high dimensional, and very noisy. It is not appropriate to use the original data to train or to test the forecasting model. Depending on the unique properties of the genes expression data, a new statistical dimension reduction method called horizon-vertical dimension reduction method (HVDRM) is developed in this paper. The feature set dimension is reduced from 2000 to 5 by applying HVDRM. Then, the extracted feature set is arranged to train in an artificial neural network (ANN) and a fuzzy neural network (FNN). Keep these two trained models, which is then send to the classification system to examine whether the testing sample is normal or not. Three kinds of experiments are conducted to test the validity, namely, original data for an ANN, reduction feature data for an ANN, and reduced feature data for a FNN. It is found that the testing accuracy of the FNN has the best result. It is concluded that the proposed HVDRM is an effective method to extract feature data and the FNN is more suitable than ANN in the given cancer cell gene detection as the forecasting model.