摘要：Historically, diabetes is diagnosed by measuring fasting (FPG) and two-hour post oral glucose load (OGTT) plasma concentration and interpreting it against recommended clinical thresholds of the patient. More recently, glycated haemoglobin A1c (HbA1c) has been included as a diagnostic criterion. Within-individual biological variation (CVi), analytical variation (CVa) and analytical bias of a test can impact on the accuracy and reproducibility of the classification of a disease. A test with large biological and analytical variation increases the likelihood of erroneous classification of the underlying disease state of a patient. Through numerical simulations based on the laboratory results generated from a large population health survey, we examined the impact of CVi, CVa and bias on the classification of diabetes using fasting plasma glucose (FPG), oral glucose tolerance test (OGTT) and HbA1c. From the results of the simulations, HbA1c has comparable performance to FPG and is better than OGTT in classifying subjects with diabetes, particularly when laboratory methods with smaller CVa are used. The use of the average of the results of the repeat laboratory tests has the effect of ameliorating the combined (analytical and biological) variation. The averaged result improves the consistency of the disease classification.
