Investigating the genetic architecture of complex diseases is challenging due to the highly polygenic and interactive landscape of genetic and environmental factors. Although genome-wide association studies (GWAS) have identified thousands of variants for multiple complex phenotypes, conventional statistical approaches can be limited by simplified assumptions such as linearity and lack of epistasis models. In this work, we trained artificial neural networks for predicting complex traits using both simulated and real genotype/phenotype datasets. We extracted feature importance scores via different post hoc interpretability methods to identify potentially associated loci (PAL) for the target phenotype. Simulations we performed with various parameters demonstrated that associated loci can be detected with good precision using strict selection criteria, but downstream analyses are required for fine-mapping the exact variants due to linkage disequilibrium, similarly to conventional GWAS. By applying our approach to the schizophrenia cohort in the Estonian Biobank, we were able to detect multiple PAL related to this highly polygenic and heritable disorder. We also performed enrichment analyses with PAL in genic regions, which predominantly identified terms associated with brain morphology. With further improvements in model optimization and confidence measures, artificial neural networks can enhance the identification of genomic loci associated with complex diseases, providing a more comprehensive approach for GWAS and serving as initial screening tools for subsequent functional studies. Keywords: Deep learning, interpretability, genome-wide association studies, complex diseases