CLASSIFICATION AND REGRESSION TREES FOR BONE-MARROW IMMUNOPHENOTYPING

Methods are needed to assist with automating three-color now cytometri c immunophenotyping of bone marrow from leukemia patients. Described i s a method in which a normal bone marrow data set is used as a templat e against which to compare leukemic bone marrow data sets. This templa te is obtained using techniques of cluster analysis and cluster editin g. Leukemic cells often inappropriately express antigens and appear in a different part of the multivariate data space than normal cells. To recognize the cells exhibiting inappropriate antigen expression, an a rtificial cluster of ''cells'' is added to the normal template. The '' cells'' in this cluster fill the space not occupied by normal cells. C lassification and regression tree (CART) analysis is used to train a c lassifier that can then be used to isolate the major cell types and th e inappropriate expression cells in a leukemic bone marrow specimen. ( C) 1995 Wiley-Liss, Inc.