Personalized Survival Prediction of Patients With Acute Myeloblastic Leukemia Using Gene Expression Profiling

Abstract

Acute Myeloid Leukemia (AML) is a heterogeneous neoplasm characterized by cytogenetic and molecular alterations that drive patient prognosis. Currently established risk stratification guidelines show a moderate predictive accuracy, and newer tools that integrate multiple molecular variables have proven to provide better results. In this report, we aimed to create a new machine learning model of AML survival using gene expression data. We used gene expression data from two publicly available cohorts in order to create and validate a random forest predictor of survival, which we named ST-123. The most important variables in the model were age and the expression of KDM5B and LAPTM4B, two genes previously associated with the biology and prognostication of myeloid neoplasms. This classifier achieved high concordance indexes in the training and validation sets (0.7228 and 0.6988, respectively), and predictions were particularly accurate in patients at the highest risk of death. Additionally, ST-123 provided significant prognostic improvements in patients with high-risk mutations. Our results indicate that survival of patients with AML can be predicted to a great extent by applying machine learning tools to transcriptomic data, and that such predictions are particularly precise among patients with high-risk mutations.

The Cross Marks the Spot: The Emerging Role of JmjC Domain-Containing Proteins in Myeloid Malignancies

“…In AML, Wong et al demonstrated that KDM5B negatively regulates leukemogenesis in both mouse and human MLL-rearranged AML cells [ 47 ] through H3K4 demethylation, which leads to cell differentiation. Orgueira and colleagues used a computer learning algorithm termed ST-123 to predict survival of AML patients [ 48 ]. Their results suggest that, aside from age, expression of KDM5B and LAPTM4B are the strongest predictors of overall survival using multivariate cox regression analyses.…”

HERVs characterize normal and leukemia stem cells and represent a source of shared epitopes for cancer immunotherapy

“…Several studies have evaluated the possibility to predict survival or response to intensive therapy using gene‐expression 18,48,60–63 . However, most of these studies do not account for major cofounding factors (such as treatment type and stem cell transplantation) or do not contain a validation cohort.…”

Survival prediction in acute myeloid leukemia using gene expression profiling

“…Compared to the two previously published machine learning methods [ 12 , 13 ], our random forest model showed three main advantages. First, our random forest model was trained in the TCGA dataset and independently validated in the OHSU dataset, indicating a high reproducibility of survival prediction.…”

“…However, the established model lacks independent validation [ 12 ]. Orgueira et al created a new machine learning model of AML survival using gene expression data and showed that the classifier achieved reasonable accuracy in predicting the survival rates of AML patients [ 13 ]. However, the accuracy of the classifier needs to be improved.…”