A computer program has been developed for computer-assisted diagnosis
(including subclassification) of flow cytometry data of acute leukaemi
as and non-Hodgkin lymphomas by means of artificial intelligence. The
knowledge base for the system has been formulated as semantic networks
that describe physiological hematopoiesis as well as the pathological
situation (e.g., aberrant antigen expression) of hematological disord
ers. The semantic networks reflect the hierarchy of cells and their oc
currence in diseases, the normal and pathological antigen expression p
atterns of cells, cell maturation, and the frequency of cell populatio
ns in normal blood and bone marrow. Using these semantic networks, the
diagnosis algorithm compares the characteristic antigen expression pa
ttern of a disease with the actual findings in the blood or bone marro
w sample, The algorithm can separate mixed populations by taking doubl
e staining findings into account. Finally, a diagnosis text is generat
ed that describes all identified cell populations and the resulting di
agnosis, The validation of the program showed a correct diagnosis (dis
ease group and subclassification) in 97% of the cases (n = 633) with s
light differences between the disease groups (e.g., B-NHL: 99%, B-cell
ALL:84%). (C) 1996 Wiley-Liss, Inc.