A hybrid framework integrating Random Forest and Logistic Regression is proposed and implemented for genome-wide epistasis study. The two-stage approach first uses random forest model to capture a pool of epistasis-prone single nucleotide polymorphisms (SNPs), followed by using logistic regression to identify the significant pair-wise epistasis SNPs. We tested the proposed framework on data obtained from Singapore Malay Eye Study (SiMES), in which, 3280 subjects were genotyped on Illumina 610 quad arrays and optic nerve parameters were measured in ocular examination. Case-control data set is labeled by choosing the high/low end of vertical Cup-to-Disc ratio (vCDR) values which is a measure of optic nerve degeneration. Our method identified 230 pairs of interacting SNPs with P-values below 5 × 10(-8). A preliminary search identified a protein interaction network at a high confidence score of 0.9. The proteins are known to participate in the WNT pathway with involvement in the survival and differentiation of the retina ganglion cells, inferring a strong association with vCDR. The experimental results demonstrate that the proposed framework is valid and efficient for large scale epistatsis study.