Purpose: Prediction models for acute myeloid leukemia (AML) are useful, but have considerable inaccuracy and imprecision. No current model includes covariates related to immune cells in the AML microenvironment. Here, an immune risk score was explored to predict the survival of patients with AML.
Experimental design: We evaluated the predictive accuracy of several in silico algorithms for immune composition in AML based on a reference of multi-parameter flow cytometry. CIBERSORTx was chosen to enumerate immune cells from public datasets and develop an immune risk score for survival in a training cohort using least absolute shrinkage and selection operator Cox regression model.
Results: Six flow cytometry-validated immune cell features were informative. The model had high predictive accuracy in the training and four external validation cohorts. Subjects in the training cohort with low scores had prolonged survival compared with subjects with high scores, with 5-year survival rates of 46% versus 19% (P < 0.001). Parallel survival rates in validation cohorts-1, -2, -3, and -4 were 46% versus 6% (P < 0.001), 44% versus 18% (P = 0.041), 44% versus 24% (P = 0.004), and 62% versus 32% (P < 0.001). Gene set enrichment analysis indicated significant enrichment of immune relation pathways in the low-score cohort. In multivariable analyses, high-risk score independently predicted shorter survival with HRs of 1.45 (P = 0.005), 2.12 (P = 0.004), 2.02 (P = 0.034), 1.66 (P = 0.019), and 1.59 (P = 0.001) in the training and validation cohorts, respectively.
Conclusions: Our immune risk score complements current AML prediction models.
©2020 American Association for Cancer Research.