Background: Early detection of the risk of pre-diabetes can lessen the likelihood of the development of diabetes mellitus. Various studies have shown a significant correlation between obesity and the incidence of pre-diabetes and diabetes. However, none of the studies has presented the value of fasting plasma glucose (FPG) or the oral glucose tolerance test (OGTT) as parameters for diagnosing pre-diabetes or diabetes. This study aimed to estimate the value of FPG and the OGTT to predict pre-diabetes based on body mass index (BMI). Methods: This cross-sectional study was conducted in Kembaran sub district, Banyumas Regency, Indonesia. The research sample consisted of 231 apparently healthy respondents (not showing any clinical symptoms of diabetes) who were underweight, normal weight, overweight and obese in terms of their BMI, and the sample was selected through random sampling. All samples were measured for BMI, FPG, and OGTT. Data were then analyzed with linear regression. Results: From 231 subjects, 133 (57.5%) were considered as normal, while 90 (39.0%) were diagnosed with pre-diabetes. We were unable to predict eight (3.5%) subjects. There was a positive correlation between BMI, FPG and the OGTT (FPG: r0.543; p<0.01; FPG prediction: 56.800+2.232*BMI), (OGTT: r0.462; p<0.01; OGTT prediction: 85.231+2.202*BMI). Conclusions and recommendation: BMI can be utilized as the prediction of pre-diabetic occurrence; a person the apparently healthy but has a BMI ≥ 25kg/m2 is considered to have pre-diabetes. [Ethiop.J. Health Dev. 2019; 33(1):38-45]