Survival prediction in acute myeloid leukemia using gene expression profiling

Lai, Binbin; Lai, Yanli; Zhou, Miao; Ouyang, Guifang

doi:10.1186/s12911-022-01791-z

Cited by 4 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prognostic stratification needs to be improved by taking into account the complexity and the interaction between genomic drivers. Gene expression signatures have been proposed to be effective biomarkers and have promising potential for clinical applications ( 18 ). In this context, we have developed a new prognostic score based on gene expression analysis ( Stellae-123 ) which achieved high discriminative power in the prediction of survival among adult AML patients ( 7 ).…”

Section: Discussionmentioning

confidence: 99%

Evaluation of the Stellae-123 prognostic gene expression signature in acute myeloid leukemia

et al. 2022

View full text Add to dashboard Cite

Risk stratification in acute myeloid leukemia (AML) has been extensively improved thanks to the incorporation of recurrent cytogenomic alterations into risk stratification guidelines. However, mortality rates among fit patients assigned to low or intermediate risk groups are still high. Therefore, significant room exists for the improvement of AML prognostication. In a previous work, we presented the Stellae-123 gene expression signature, which achieved a high accuracy in the prognostication of adult patients with AML. Stellae-123 was particularly accurate to restratify patients bearing high-risk mutations, such as ASXL1, RUNX1 and TP53. The intention of the present work was to evaluate the prognostic performance of Stellae-123 in external cohorts using RNAseq technology. For this, we evaluated the signature in 3 different AML cohorts (2 adult and 1 pediatric). Our results indicate that the prognostic performance of the Stellae-123 signature is reproducible in the 3 cohorts of patients. Additionally, we evidenced that the signature was superior to the European LeukemiaNet 2017 and the pediatric clinical risk scores in the prediction of survival at most of the evaluated time points. Furthermore, integration with age substantially enhanced the accuracy of the model. In conclusion, Stellae-123 is a reproducible machine learning algorithm based on a gene expression signature with promising utility in the field of AML.

show abstract

Section: Discussionmentioning

confidence: 99%

Evaluation of the Stellae-123 prognostic gene expression signature in acute myeloid leukemia

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Nonetheless, in order to refine the prognosis factor, more and more genes enter the predictive models and require machine learning to be usefully analyzed. The analysis of the Oregon Health & Science University (OHSU) and of The Cancer Genome Atlas (TCGA) datasets allowed us to identify 197 common “protective” genes and 87 common “risk” genes between the two databases with a very potent predictive value [ 41 ].…”

Section: Discussionmentioning

confidence: 99%

Impact of Next-Generation Sequencing in Diagnosis, Prognosis and Therapeutic Management of Acute Myeloid Leukemia/Myelodysplastic Neoplasms

Madaci

Farnault

Abbou³

et al. 2023

Cancers

View full text Add to dashboard Cite

For decades, the diagnosis, prognosis and thus, the treatment of acute myeloblastic leukemias and myelodysplastic neoplasms has been mainly based on morphological aspects, as evidenced by the French-American-British classification. The morphological aspects correspond quite well, in a certain number of particular cases, to particular evolutionary properties, such as acute myelomonoblastic leukemias with eosinophils or acute promyelocytic leukemias. Advances in biology, particularly “classical” cytogenetics (karyotype) and molecular cytogenetics (in situ hybridization), have made it possible to associate certain morphological features with particular molecular abnormalities, such as the pericentric inversion of chromosome 16 and translocation t(15;17) in the two preceding examples. Polymerase chain reaction techniques have made it possible to go further in these analyses by associating these karyotype abnormalities with their molecular causes, CBFbeta fusion with MYH11 and PML-RAR fusion in the previous cases. In these two examples, the molecular abnormality allows us to better define the pathophysiology of leukemia, to adapt certain treatments (all-transretinoic acid, for example), and to follow up the residual disease of strong prognostic value beyond the simple threshold of less than 5% of marrow blasts, signaling the complete remission. However, the new sequencing techniques of the next generation open up broader perspectives by being able to analyze several dozens of molecular abnormalities, improving all levels of management, from diagnosis to prognosis and treatment, even if it means that morphological aspects are increasingly relegated to the background.

show abstract

“…The RF algorithm is a method of training and predicting samples by constructing a decision tree. The features with high importance scores are obtained by calculating and sorting the importance scores of features [ 12 ]. These machine algorithms can learn and train from data to achieve accurate predictions of future events [ 13 ].…”

Section: Backgroundsmentioning

confidence: 99%

Multiple machine-learning tools identifying prognostic biomarkers for acute Myeloid Leukemia

Cheng,

Yang,

Wang

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Acute Myeloid Leukemia (AML) generally has a relatively low survival rate after treatment. There is an urgent need to find new biomarkers that may improve the survival prognosis of patients. Machine-learning tools are more and more widely used in the screening of biomarkers. Methods Least Absolute Shrinkage and Selection Operator (LASSO), Support Vector Machine-Recursive Feature Elimination (SVM-RFE), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), lrFuncs, IdaProfile, caretFuncs, and nbFuncs models were used to screen key genes closely associated with AML. Then, based on the Cancer Genome Atlas (TCGA), pan-cancer analysis was performed to determine the correlation between important genes and AML or other cancers. Finally, the diagnostic value of important genes for AML was verified in different data sets. Results The survival analysis results of the training set showed 26 genes with survival differences. After the intersection of the results of each machine learning method, DNM1, MEIS1, and SUSD3 were selected as key genes for subsequent analysis. The results of the pan-cancer analysis showed that MEIS1 and DNM1 were significantly highly expressed in AML; MEIS1 and SUSD3 are potential risk factors for the prognosis of AML, and DNM1 is a potential protective factor. Three key genes were significantly associated with AML immune subtypes and multiple immune checkpoints in AML. The results of the verification analysis show that DNM1, MEIS1, and SUSD3 have potential diagnostic value for AML. Conclusion Multiple machine learning methods identified DNM1, MEIS1, and SUSD3 can be regarded as prognostic biomarkers for AML.

show abstract

Survival prediction in acute myeloid leukemia using gene expression profiling

Cited by 4 publications

References 42 publications

Evaluation of the Stellae-123 prognostic gene expression signature in acute myeloid leukemia

Evaluation of the Stellae-123 prognostic gene expression signature in acute myeloid leukemia

Impact of Next-Generation Sequencing in Diagnosis, Prognosis and Therapeutic Management of Acute Myeloid Leukemia/Myelodysplastic Neoplasms

Multiple machine-learning tools identifying prognostic biomarkers for acute Myeloid Leukemia

Contact Info

Product

Resources

About