Clonal chromosomal abnormalities are the most important prognostic indicators in acute myeloid leukemia (AML). Two of the most prevalent cytogenetic subtypes of adult primary AML, t(8;21)(q22;q22) and inv(16)(p13q22)/t(16;16)(p13;q22), are characterized by disruption of the AML1(CBFA2, RUNX1) and CBFbeta genes, respectively, which encode subunits of core binding factor (CBF), a regulator of normal hematopoiesis. At the molecular level, t(8;21) and inv(16)/t(16;16) result in the creation of novel fusion genes, AML1/ETO and CBFbeta/MYH11, respectively, which encode fusion transcripts readily detectable by the reverse transcription-polymerase chain reaction (RT-PCR). Although the detection of t(8;21) or inv(16)/t(16;16) in adult patients with primary AML represents a favorable independent prognostic indicator for achievement of cure following intensive chemotherapy or stem cell transplantation, a substantial number of these patients (i.e. 40-50%) relapse and eventually die of their disease. Therefore, timely identification and therapeutic stratification of those patients deemed at high risk for disease relapse could ultimately result in a further improvement of clinical outcome within these cytogenetic subgroups of AML. As relapse is likely to occur as the result of failure of treatment to completely eradicate leukemic blasts, the detection of the AML1/ETO and CBFbeta/MYH11 fusion transcripts using sensitive RT-PCR assays has been utilized as a surrogate marker for resistant disease and, in turn, to predict disease recurrence during remission. The purpose of this paper is to review the applicability of this strategy to the clinical management of t(8;21) and inv(16)/t(16;16) primary AML, here collectively referred to as CBF AML.