Acute myeloid leukaemia (AML) is haematologic malignancy with high heterogeneity, characterized by uncontrolled proliferation of myeloid progenitor cells gradually replacing the normal haematopoietic function of bone marrow. With the continuous exploration and research at the cellular and molecular level on the pathogenesis of AML, the choice of novel treatment modalities has surged over the past few years, including targeted small-molecule inhibitors, antibody-drug conjugate, tumour-targeted immunotherapy and so on. 1,2 The prognosis of majority of young AML patients has improved, and most patients have access to complete remission. However, more than half of young adult patients and approximately 90% of older patients still die of their diseases. 3 Hence, a reliable prognostic Abstract Acute myeloid leukaemia (AML) is the most common type of adult acute leukaemia and has a poor prognosis. Thus, optimal risk stratification is of greatest importance for reasonable choice of treatment and prognostic evaluation. For our study, a total of 1707 samples of AML patients from three public databases were divided into meta-training, meta-testing and validation sets. The meta-training set was used to build risk prediction model, and the other four data sets were employed for validation. By log-rank test and univariate COX regression analysis as well as LASSO-COX, AML patients were divided into high-risk and low-risk groups based on AML risk score (AMLRS) which was constituted by 10 survival-related genes. In meta-training, meta-testing and validation sets, the patient in the low-risk group all had a significantly longer OS (overall survival) than those in the high-risk group (P < .001), and the area under ROC curve (AUC) by time-dependent ROC was 0.5854-0.7905 for 1 year, 0.6652-0.8066 for 3 years and 0.6622-0.8034 for 5 years. Multivariate COX regression analysis indicated that AMLRS was an independent prognostic factor in four data sets. Nomogram combining the AMLRS and two clinical parameters performed well in predicting 1-year, 3-year and 5-year OS. Finally, we created a webbased prognostic model to predict the prognosis of AML patients (https://tcgi.shiny apps.io/amlrs_nomog ram/).
K E Y W O R D Sacute myeloid leukaemia, gene expression profiling, nomogram, prognosis, signature | 4511 YANG et Al.stratification system which can be applied to clinical risk evaluation is of high importance for the choice of therapy and follow-up in AML patients.Whether it is an established classification system, such as the
French-American-British (FAB) classification system in 1976, 4 WorldHealth Organization (WHO) classification in 2008 5 and 2016 6 incorporating genetic information, or prognostic factors, for instance, clinical factors including mounting age and poor performance status, 7 cytogenetic changes 8 and gene mutation, 9 all have their downsides for risk stratification, such as the insufficiency of generalization capacity, the uncertainty in the accuracy of prediction. Hence, recently increasing sight has turned to studies o...