PROJECT SUMMARY/ABSTRACT Prediabetes (PD) and type 2 diabetes (T2D) affect 122 million Americans. Although diabetes is the most costly chronic condition in the US—with an annual economic burden of $327 billion—it is severely underdiagnosed, with 84% of those with PD and 21% of those with T2D unaware of their condition. Screening guidelines for PD and T2D include coarse self-reports with low positive predictive value, and therefore have been unable to mitigate this severe diagnostic gap. The ultimate goal of this research is to develop and implement an innovative, practical, and scalable PD and T2D detection strategy by leveraging digital data obtained using personal consumer smart devices (smartphones and smartwatches). Smartphones and smartwatches are now prevalent in the general population, and the technology developed here will be directly translatable for immediate deployment to improve the detection of PD and T2D. Toward this goal, we recently developed wearable-based models using a research-grade wearable wristband to detect personalized glucose deviations, predict interstitial glucose values, and estimate the level of glycated hemoglobin (A1c), which are all key metrics for detecting and monitoring PD and T2D. The wearable-based models currently function on people with a limited A1c range (prediabetic and elevated normal). To translate this work and expand the reach and yield of current screening methods, we propose the following two Specific Aims: (1) Validate and extend the wearable models to distinguish between T2D, PD, and normoglycemia; and (2) Determine how we can leverage smartphones and smartwatches to improve the yield and reach of present screening methods for PD and T2D. In the first Aim, we will validate and extend our preliminary work developing the wearable models to function across a wider range of glycemic variability, interstitial glucose, and A1c values and to move from research-grade wearables to consumer-grade smartwatches. In the second Aim, we will expand the reach of current guideline-based screening using text message delivery of the American Diabetes Association (ADA) “60-second Risk Test” to directly assess and inform patients about their risk for PD and T2D with the goal of increasing A1c testing in patients that meet the risk criteria. We will increase the yield of true positives by adding objective smartwatch and/or smartphone measures (e.g., physical activity, sedentary habits, glycemic health parameter estimations) to the existing ADA 60-second Risk Test model. The innovations from this proposed research could transform PD and T2D detection for the 81 million Americans with undiagnosed PD and T2D through novel methods for real-time, continuous mobile screening. Successful completion of this project could ultimately revolutionize diabetes management by improving early detection and by enabling proactive intervention to prevent or reverse T2D progression.