Plasma lipid levels predict chemotherapy response and survival in acute myeloid leukemia

Acute myeloid leukemia (AML) is characterized by a low five-year survival rate. Despite having many clinical metrics to assess patient prognosis, there remain opportunities to improve risk stratification. We hypothesized that an underexplored resource to examine AML patient prognosis is the plasma metabolome. Circulating metabolites are influenced by patients' clinical status and can serve as accessible cancer biomarkers. To establish a resource of circulating metabolites in genetically diverse AML patients, we performed an unbiased metabolomic and lipidomic analysis of 231 diagnostic AML plasma samples prior to treatment with intensive chemotherapy. Intriguingly, circulating metabolites were highly associated with the mutation status within the AML cells. Further, lipids were associated with refractory status. We established a machine learning algorithm trained on chemo-refractory associated lipids to predict patient survival. Cox regression and Kaplan-Meier analysis demonstrated that the high-risk lipid signature predicted overall survival in this patient cohort. Impressively, the top lipid in the high-risk lipid signature, sphingomyelin (d44:1), was sufficient to predict overall survival in the original and an independent validation dataset. Overall, this research underscores the potential of circulating metabolites to capture AML heterogeneity and lipids to be used as potential AML biomarkers.