POPULATION SCREENING FOR GLUCOSE INTOLERANT SUBJECTS USING DECISION TREE ANALYSES

The purpose of this study was to develop a method of screening for imp aired glucose tolerance and previously undiagnosed NIDDM that could be used preliminary to the administration of an oral glucose tolerance t est (OGTT) for final classification of glucose tolerance status. The p urpose of a preliminary screening of this type would be to reduce the number of OGTT's needed to identify cases of IGT and NIDDM in the popu lation. We used NIDDM risk indicators and decision tree analysis metho ds (CART software) to identify subgroups of the population at increase d risk. We examined a population of Hispanic (n=583) and non-Hispanic white (n=768) subjects without a prior history of diabetes. Subjects w ere classified as normal, IGT or NIDDM (WHO criteria) based on results from a 75 g oral glucose tolerance test (OGTT). Sensitivity (SEN) and specificity (SPE) of the CART models were calculated using the OGTT a s the 'gold standard.' Two approaches to screening were simulated. In the simultaneous approach all risk variables were entered into CART mo dels at once. In the serial approach, risk variables were grouped acco rding to degree of effort required for data collection, and were enter ed into CART models in stages. Fasting glucose, age and body mass inde x (BMI) were selected as risk;variables by CART when simulating the si multaneous approach (SEN=91%, SPE=55%). In the serial approach, CART u sed age and BMI to eliminate 35% of the population from further screen ing, and then used fasting glucose, glycohemoglobin, age and BMI to cl assify the remaining higher risk subjects (SEN=85% SPE=64%). These mod els suggest that screening for IGT and previously undiagnosed NIDDM ca n be based on measurement of relatively simple indicators, and yet mai ntain a level of both sensitivity and specificity acceptable for this type of preliminary screening.