57 Utility of Digital Phenotyping in Big Data to Answer Clinical Questions: Puberty as a Transdisciplinary Science Case Example

Abstract

OBJECTIVES/GOALS: A disease-agnostic translational science framework for data mining is proposed for use across disciplines to: Answer clinical questions, justify future clinical research recruitment, and explore under-represented populations. As a case example, male puberty demonstrates utility of the framework. METHODS/STUDY POPULATION: As a case example using the generalizable framework, the following interdisciplinary question was asked: Does early pubertal timing increase the risk of developing type II diabetes (T2d) in boys? A digital phenotype of males 85th percentile. Boys diagnosed with precocious puberty (E30.1) were 6.89 times more likely to develop T2d when aged 14-18 years old than those without (OR 6.89, 95%CI: 5.17-9.19, p. DISCUSSION/SIGNIFICANCE: Boys are under-represented in the early pubertal timing literature, justifying future human subjects research on male puberty. This case example demonstrates a broader disease-agnostic framework which can be adapted across disciplines. Opportunities may include public health digital phenotyping.