We consider the problem of predicting whether a given patient has Type 2 Diabetes Mellitus using his or her electronic health records (EHR), which often lack common indicators of diabetes. Effective heuristics such as FINDRISC exist for detecting undiagnosed diabetes, but require that patients be screened to collect all necessary information. We compare FINDRISC, restricted to the information i...

Type 2 diabetes is a serious, costly, and increasingly common disease. Several conditions commonly seen in family medicine settings confer increased risk of developing diabetes. Among these conditions are impaired glucose tolerance, impaired fasting glucose, obesity, gestational diabetes, hypertension, hyperlipidemia, and menopause. We here present the results of a systematic review of the lite...