ABSTRACT The proposed study brings together a team of researchers and leverages already collected data within the American College Health Association National College Health Assessment (ACHA-NCHA) to examine the portability of an automated method of classifying gender groupings using the two-step method and expanded options for gender identity. While the two-step method has been recommended as the gold standard for assessing sex assigned at birth and gender identity, there is a lack of clarity as to how to classify and identify gender expansive individuals (i.e., individuals whose identities are not masculine or feminine alone) via that method. This is important as gender expansive individuals do not identify with the binary framework imposed when assigning gender identity based on discordance between sex assigned at birth and gender identity. Additionally, research indicates that there are differences in the health status (such as substance use) and social determinants of health of individuals who identify as transgender versus individuals who identify as gender expansive. Our team has created an automated coding method developed with sexual and gender minority (SGM) people that takes into account multiple gender selections, write-in gender responses, and sex assigned at birth. In this study we will refine and expand that coding method to use on a sample that includes both SGM and non-SGM people: the ACHA-NCHA. We expect that our refined automated coding method can be expanded to a non-SGM data set and can improve classification of people who use write-in responses over the ACHA-NCHA recommended method. We also expect that our method will significantly reduce the number of people classified as missing when compared to the ACHA-NCHA recommended method. We will also test the capability of our method to better predict substance use involvement over the ACHA-NCHA recommended method. This study will lay the groundwork for rigorous and replicable SGM health research with robust gender identity methods.