Background: Many BC patients treated with aromatase inhibitors (AIs) develop AIA; 20% have symptoms severe enough to effect treatment compliance. Results of candidate gene studies to identify AIA risk are limited in scope. In this case-controlled study, we evaluated the potential of a NAA to predict AIA using germline single nucleotide polymorphism (SNP) data obtained prior to treatment initiation. Methods: Systematic chart review of 700 AI-treated patients with stage I-III BC between 2003-2012 identified asymptomatic patients (n = 39) and those with clinically significant AIA resulting in AI termination or therapy switch (n = 123). Germline DNA was obtained from peripheral blood cells and SNP genotyping performed using the Affymetrix UK BioBank Axiom Array to yield 695,277 SNPs. The identity of the cluster of SNPs that most closely defined AIA risk was discovered using an NAA that sequentially combined statistical filtering and a machine learning algorithm. NCBI PhenGenI and Ensemble databases were used to define gene attribution of the 200 most discriminating SNPs. Phenotype, pathway, and ontologic analyses assessed functional and mechanistic validity. Results: Cases and controls were similar in demographic characteristics. A cluster of 70 SNPs, correlated to 57 genes (accounting for linkage disequilibrium), was identified. This SNP group predicted AIA occurrence with a maximum accuracy of 75.93%. Strong associations with arthralgia, breast cancer, and estrogen phenotypes were seen in 19/57 genes (33%) and were functionally and ontologically consistent. Conclusions: Using a NAA, we identified a 70 SNP cluster that predicted AIA risk with fair accuracy. Phenotype, functional, and pathway analysis of attributed genes was consistent with clinical phenotypes. This study is the first to link a specific SNP/gene cluster to AIA risk independent of candidate gene bias. An ongoing prospective companion study will be used to validate and to expand upon results.