The oral glucose tolerance test (OGTT) is regarded as the gold standard for diagnosing diabetes and impaired glucose tolerance, and it is widely used in epidemiological studies to estimate the prevalence of diabetes, prediabetes and gestational diabetes mellitus in different populations, including those in sub-Saharan Africa. However, there is a lot of debate on the usefulness of this test, especially in low-resource settings. This thesis aims to determine the accuracy and utility of OGTT in sub-Saharan Africa through four different studies done in Uganda and Malawi. OGTT results in sub-Saharan Africa are influenced by challenges in sample handling before the analysis. In Chapter 2, we show that in the absence of the recommended sodium fluoride (NaF) sample collecting tubes for glucose measurement, the readily available EDTA tubes can be used provided that the samples are kept in a cooler box with ice and are centrifuged or analysed within six hours. The accuracy of OGTT based prevalence studies in regions with high food insecurity is unknown. In Chapter 3, we conducted a randomised cross over study in rural Uganda to explore factors that impact fasting and post-load glucose results. We demonstrated that the OGTT is affected by alteration of a single evening meal before the test. The two-hour glucose results are significantly higher after a low-carbohydrate evening meal compared to after a normal carbohydrate evening meal, even if the total daily carbohydrate intake was the recommended amount. The prevalence of abnormal glucose tolerance doubled after a restricted evening meal. 4 This finding raises questions on the utility of OGTT in populations with high levels of food insecurity. In Chapter 4, we followed up participants with prediabetes classified by impaired fasting glucose levels in urban and rural Malawi. By a period of 4 years, we found that the progression to diabetes in Malawi is high, with 30% of participants progressing to diabetes in the study period. The incident rate of diabetes was 63 per 1000 person-years. We also found that the waist circumference and the baseline glucose levels were the strongest predictors of progression. A simple chart with probabilities of progression based on these risk factors could be used to identify those at risk of developing diabetes in this population. In Chapter 5, we analysed the relationship between birth weight and adverse pregnancy outcomes with maternal fasting plasma glucose and stimulated glucose in Uganda. We found that the contribution of maternal glucose to birthweight is much lower in this population than what has been reported in other populations. Fasting plasma glucose was just as good at predicting large for gestational age babies than either one or two-hour glucose results. An overview of the major findings of each chapter, their implications, and potential future research are discussed in Chapter 6.