Although recent work has characterized the microbiome in solid tumors, microbial content in hematological malignancies is not well-characterized. Here we analyzed existing deep DNA sequence data from the blood and bone marrow of 1,870 patients with myeloid malignancies, along with healthy controls, for bacterial, fungal, and viral content. After strict quality filtering, we find evidence for dysbiosis in disease cases, and distinct microbial signatures among diagnoses. In patients with low-risk myelodysplastic syndrome, we provide evidence that Epstein-Barr infection status refines risk stratification into more precise categories than the current standard. Motivated by these observations, we construct machine-learning classifiers that can discriminate among disease subtypes based solely on bacterial content. Our study highlights the potential of the circulating microbiome as a diagnostic and prognostic tool.