A lasso and random forest model using flow cytometry data identifies primary myelofibrosis

Thrombocythemia (ET), polycythemia vera (PV), primary myelofibrosis (PMF), prefibrotic/early (pre‐PMF), and overt fibrotic PMF (overt PMF) are classical Philadelphia‐Negative (Ph‐negative) myeloproliferative neoplasms (MPNs). Differentiating between these types based on morphology and molecular markers is challenging. This study aims to clarify the application of flow cytometry in the diagnosis and differential diagnosis of classical MPNs. This study retrospectively analyzed the immunophenotypes, clinical characteristics, and laboratory findings of 211 Ph‐negative MPN patients, including ET, PV, pre‐PMF, overt PMF, and 47 controls. Compared to ET and PV, PMF differed in white blood cells, hemoglobin, blast cells in the peripheral blood, abnormal karyotype, and WT1 gene expression. PMF also differed from controls in CD34+ cells, granulocyte phenotype, monocyte phenotype, percentage of plasma cells, and dendritic cells. Notably, the PMF group had a significantly lower plasma cell percentage compared with other groups. A lasso and random forest model select five variables (CD34+CD19+cells and CD34+CD38− cells on CD34+cells, CD13dim+CD11b− cells in granulocytes, CD38str+CD19+/−plasma, and CD123+HLA‐DR−basophils), which identify PMF with a sensitivity and specificity of 90%. Simultaneously, a classification and regression tree model was constructed using the percentage of CD34+CD38− on CD34+ cells and platelet counts to distinguish between ET and pre‐PMF, with accuracies of 94.3% and 83.9%, respectively. Flow immunophenotyping aids in diagnosing PMF and differentiating between ET and PV. It also helps distinguish pre‐PMF from ET and guides treatment decisions.