Classification methods for the identification of 'case' in epidemiologicaldiagnosis of asthma

The identification of the asthmatic 'case' in epidemiological research is a controversial issue. This study was aimed at classifying asthmatic subject s using a statistical decision rule that minimised the misclassification ra te with respect to the clinicians' diagnosis. The rule was defined by a com bination of predictors that are easily observed in epidemiological studies (asthma-like questions, physiological tests) without necessarily including the clinical opinion of expert physicians. From pooled data on 1103 subject s at the three Italian centres of the European Community Respiratory Health Survey (ECRHS) a post-consensus clinicians' diagnosis of asthma was obtain ed, and seven predictors were selected from among 18 potential candidates ( specificity ranged from 64 to 99%, but sensitivity ranged from 22 to 62%). This data set was processed with tree-structured classifier techniques (the Classification And Regression Trees, CART), classical discriminant analysi s (Fisher's Linear Discriminant Function, LDF), and the neural network meth od (Multi-Layer Perceptron, MLP model). The results suggest that modificati ons of the 'classification tree' provide a more useful decision rule, sensi tive (93%) and specific (85%), than either LDF or MLP. The decision tree is readily interpretable from a clinical perspective and uses five out of the seven predictors (in descending hierarchical order: ever had asthma, curre nt asthma, shortness of breath, atopy and wheezing and breathless). The fin dings seem to indicate a considerable success with respect to previous epid emiological studies and await repetition in other ECHRS populations.