Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
Ontology highlight
ABSTRACT:
SUBMITTER: Karami K
PROVIDER: S-EPMC8294525 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveUnsupervised machine learning approaches hold promise for large-scale clinical data. However, the heterogeneity of clinical data raises new methodological challenges in feature selection, choosing a distance metric that captures biological meaning, and visualization. We hypothesized that clustering could discover prognostic groups from patients with chronic lymphocytic leukemia, a disease that provides biological validation through well-understood outcomes.MethodsTo address this challenge, we applied k-medoids clustering with 10 distance metrics to 2 experiments ("A" and "B") with mixed clinical features collapsed to binary vectors and visualized with both multidimensional scaling and t-stochastic neighbor embedding. To assess prognostic utility, we performed survival analysis using a Cox proportional hazard model, log-rank test, and Kaplan-Meier curves.ResultsIn both experiments, survival analysis revealed a statistically significant association between clusters and survival outcomes (A: overall survival, P = .0164; B: time from diagnosis to treatment, P = .0039). Multidimensional scaling separated clusters along a gradient mirroring the order of overall survival. Longer survival was associated with mutated immunoglobulin heavy-chain variable region gene (IGHV) status, absent Zap 70 expression, female sex, and younger age.ConclusionsThis approach to mixed-type data handling and selection of distance metric captured well-understood, binary, prognostic markers in chronic lymphocytic leukemia (sex, IGHV mutation status, ZAP70 expression status) with high fidelity.
| S-EPMC7647286 | biostudies-literature
Project description:Our objective is to develop a prognostic model focused on cuproptosis, aimed at predicting overall survival (OS) outcomes among Acute myeloid leukemia (AML) patients. The model utilized machine learning algorithms incorporating stacking. The GSE37642 dataset was used as the training data, and the GSE12417 and TCGA-LAML cohorts were used as the validation data. Stacking was used to merge the three prediction models, subsequently using a random survival forests algorithm to refit the final model using the stacking linear predictor and clinical factors. The prediction model, featuring stacking linear predictor and clinical factors, achieved AUC values of 0.840, 0.876 and 0.892 at 1, 2 and 3 years within the GSE37642 dataset. In external validation dataset, the corresponding AUCs were 0.741, 0.754 and 0.783. The predictive performance of the model in the external dataset surpasses that of the model simply incorporates all predictors. Additionally, the final model exhibited good calibration accuracy. In conclusion, our findings indicate that the novel prediction model refines the prognostic prediction for AML patients, while the stacking strategy displays potential for model integration.
| S-EPMC10837443 | biostudies-literature
Project description:Acute myeloid leukemia (AML) is a severe, mostly fatal hematopoietic malignancy. We were interested in whether transcriptomic-based machine learning could predict AML status without requiring expert input. Using 12,029 samples from 105 different studies, we present a large-scale study of machine learning-based prediction of AML in which we address key questions relating to the combination of machine learning and transcriptomics and their practical use. We find data-driven, high-dimensional approaches-in which multivariate signatures are learned directly from genome-wide data with no prior knowledge-to be accurate and robust. Importantly, these approaches are highly scalable with low marginal cost, essentially matching human expert annotation in a near-automated workflow. Our results support the notion that transcriptomics combined with machine learning could be used as part of an integrated -omics approach wherein risk prediction, differential diagnosis, and subclassification of AML are achieved by genomics while diagnosis could be assisted by transcriptomic-based machine learning.
| S-EPMC6992905 | biostudies-literature
Project description:Chromosomal abnormalities are detected in 50-60% of patients with acute myeloid leukemia (AML) and are important predictors of prognosis and risk of relapse. The remaining patients, those with cytogenetically normal AML, are a seemingly homogeneous group that in fact consists of subsets of patients with distinct clinical outcomes. This heterogeneity is likely related to acquired gene mutations, as well as altered miRNA and gene-expression profiles, which occur within the group. The identification of recurrent molecular abnormalities has improved prognostication and provided insight into mechanisms of leukemogenesis for patients with cytogenetically normal AML, as well as led to the discovery of novel therapeutic targets. As the number of mutations continues to expand, bioinformatic algorithms that allow for integration of multiple markers will be necessary to provide optimal care for patients with this disease.
| S-EPMC3582378 | biostudies-literature
Project description:BackgroundAlthough it is well-known that adult and pediatric acute myeloid leukemias (AMLs) are genetically distinct diseases, they still share certain gene expression profiles. The age-related genetic heterogeneities of AMLs have been well-studied, but the common prognostic signatures and molecular mechanisms of adult and pediatric AMLs are less investigated.AimTo identify genes and pathways that are associated with both pediatric and adult AMLs and discover a gene signature for overall survival (OS) prediction.MethodsThrough mining the transcriptome profiles of The Cancer Genome Atlas (TCGA) data sets of adult cancers and The Therapeutically Applicable Research to Generate Effective Treatments (TARGET) data of pediatric cancers, we identified genes that are commonly dysregulated in both pediatric and adult AMLs, further discovered a common gene signature, and built two risk score models for TCGA and TARGET cohorts, respectively with L 0 regularized global AUC (area under the receiver operating characteristic curve) summary maximization.ResultsWe identified 57 genes that are differentially expressed and prognostically significant in both adult and childhood AMLs. The top 4 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways enriched with those 57 genes include transcriptional misregulation, focal adhesion, PI3K-Akt signaling pathway, and signaling pathways regulating pluripotency of stem cells. We further identified a 6-gene signature including genes of ADAMTS3, DNMT3B, NYNRIN, SORT1, ZFHX3, and ZG16B for risk prediction. We constructed a risk score model with one dataset (either TCGA or TARGET) and evaluated its performance with the other. The test AUCs for the risk prediction of TCGA data with a 2-year and 5-year OS cutoffs are 0.762 (P = 2.33e-13, 95% CI: 0.69-0.83) and 0.759 (P = 7.26e-08, 95% CI: 0.66-0.85), respectively, while the test AUCs of TARGET data with the same cutoffs are 0.71 (P = 3.3e-07, 95% CI: 0.62-0.79) and 0.72 (P= 5.25e-09, 95% CI: 0.65-0.80), respectively. We further stratified patients into 3 equal sized prognostic subtypes with the 6-gene risk scores. The P-values of the tertile partitions are 1.74e-07 and 3.28e-08 for the TARGET and TCGA cohorts, respectively, which are significantly better than the standard cytogenetic risk stratification of both cohorts (TARGET: P = 1.64e-06; TCGA: P = 1.79e-05). When validated with two other independent cohorts, the 6-gene risk score models remain a significant predictor for OS. Investigating the common gene expression program is significant in that we may extrapolate the findings from adults to children and avoid unnecessary pediatric clinical trials.
| S-EPMC9556437 | biostudies-literature
Project description:In this study, we utilized data from the Surveillance, Epidemiology, and End Results (SEER) database to predict the glioblastoma patients' survival outcomes. To assess dataset skewness and detect feature importance, we applied Pearson's second coefficient test of skewness and the Ordinary Least Squares method, respectively. Using two sampling strategies, holdout and five-fold cross-validation, we developed five machine learning (ML) models alongside a feed-forward deep neural network (DNN) for the multiclass classification and regression prediction of glioblastoma patient survival. After balancing the classification and regression datasets, we obtained 46,340 and 28,573 samples, respectively. Shapley additive explanations (SHAP) were then used to explain the decision-making process of the best model. In both classification and regression tasks, as well as across holdout and cross-validation sampling strategies, the DNN consistently outperformed the ML models. Notably, the accuracy were 90.25% and 90.22% for holdout and five-fold cross-validation, respectively, while the corresponding R2 values were 0.6565 and 0.6622. SHAP analysis revealed the importance of age at diagnosis as the most influential feature in the DNN's survival predictions. These findings suggest that the DNN holds promise as a practical auxiliary tool for clinicians, aiding them in optimal decision-making concerning the treatment and care trajectories for glioblastoma patients.
| S-EPMC10824760 | biostudies-literature
Project description:Dysregulation of cytokines and growth factors is a general feature of tumor microenvironment, and unraveling the expression spectrum of cytokine and growth factor in niche is of utmost importance. Here, we evaluated cytokine profiling of bone marrow serum samples in AML patients and healthy controls. Protein expression profiling of serum from nine AML patients and five healthy controls was obtained using a biotinylated antibody chip. A total of 507 cytokines and growth factors were analyzed. Compared with healthy people, AML patients expressed 31 signature proteins, among which, 27 were significantly higher expressed and 4 proteins were lower. When patients were divided into favorable and poor prognosis, 12 signature proteins were significantly differentially expressed between these two groups. Furthermore, in order to identify the accuracy of cytokine expression profiles, we verified and analyzed the expression of THBS1 (Thrombospondin 1) in 116 patients and 9 healthy people. We found that THBS1 was lowly expressed in AML patients, which might be induced by promoter methylation, and patients with low THBS1 possessed shorter survivor time. Our data indicated that we successfully unveil differentially expressed proteins in AML patients using a biotinylated antibody chip; among them, THBS1 may be a potential therapeutic target for AML patients' treatment.
| S-EPMC7020255 | biostudies-literature
Project description:ObjectiveWe conducted a meticulous bioinformatics analysis leveraging expression data of 226 PANRGs obtained from previous studies, as well as clinical data from AML patients derived from the HOVON database.MethodsThrough meticulous data analysis and manipulation, we were able to categorize AML cases into two distinct PANRG clusters and subsequently identify differentially expressed genes (PRDEGs) with prognostic significance. Furthermore, we organized the patient data into two corresponding gene clusters, allowing us to investigate the intricate relationship between the risk score, patient prognosis, and the immune landscape.ResultsOur findings disclosed significant associations between the identified PANRGs, gene clusters, patient survival, immune system, and cancer-related biological processes and pathways. Importantly, we successfully constructed a prognostic signature comprising nineteen genes, enabling the stratification of patients into high-risk and low-risk groups based on individually calculated risk scores. Furthermore, we developed a robust and practical nomogram model, integrating the risk score and other pertinent clinical features, to facilitate accurate patient survival prediction. Our comprehensive analysis demonstrated that the high-risk group exhibited notably worse prognosis, with the risk score proving to be significantly correlated with infiltration of most immune cells. The qRT-PCR results revealed significant differential expression patterns of LGR5 and VSIG4 in normal and human leukemia cell lines (HL-60 and MV-4-11).ConclusionsOur findings underscore the potential utility of PANoptosis-based molecular clustering and prognostic signatures as predictive tools for assessing patient survival in AML.
| S-EPMC10846924 | biostudies-literature
Project description:Background: Acute myeloid leukemia (AML) is a heterogeneous malignant disease. SLC25A1, the gene encoding mitochondrial carrier subfamily of solute carrier proteins, was reported to be overexpressed in certain solid tumors. However, its expression and value as prognostic marker has not been assessed in AML. Methods: We retrieved RNA profile and corresponding clinical data of AML patients from the Beat AML, TCGA, and TARGET databases (TARGET_AML). Patients in the TCGA cohort were well-grouped into two group based on SLC25A1 and differentially expressed genes were determined between the SLC25A1 high and low group. The expression of SLC25A1 was validated with clinical samples. The survival and apoptosis of two AML cell lines were analyzed with SLC25A1 inhibitor (CTPI-2) treatment. Cox and the least absolute shrinkage and selection operator (LASSO) regression analyses were applied to Beat AML database to identify SLC25A1-associated genes for the construction of a prognostic risk-scoring model. Survival analysis was performed by Kaplan-Meier and receiver operator characteristic curves. Results: Our analysis revealed that high expressed level of SLC25A1 in AML patients correlates with unfavorable prognosis. Moreover, SLC25A1 expression was positively associated with metabolism activity. We further demonstrated that the inhibition of SLC25A1 could inhibit the proliferation and increase the apoptosis of AML cells. In addition, a panel of SLC25A1-associated genes, was identified to construct a prognostic risk-scoring model. This SLC25A1-associated prognostic signature (SPS) is an independent risk factor with high area under curve (AUC) values of receiver operating characteristic (ROC) curves. A high SPS in leukemia patients is associated with poor survival. A Prognostic nomogram including the SPS and other clinical parameters, was constructed and its predictive efficiency was confirmed. Conclusion: We have successfully established a SPS prognostic model that predict outcome and risk stratification in AML. This risk model can be used as an independent biomarker to assess prognosis of AML.
| S-EPMC9852877 | biostudies-literature
Project description:BackgroundAcute myeloid leukemia (AML) is a genetically heterogeneous blood disorder. AML patients are associated with a relatively poor overall survival. The objective of this study was to establish a machine learning model to accurately perform the prognosis prediction in AML patients.MethodsWe first screened for prognosis-related genes using Kaplan-Meier survival analysis in The Cancer Genome Atlas dataset and validated the results in the Oregon Health & Science University dataset. With a random forest model, we built a prognostic risk score using patient's age, TP53 mutation, ELN classification and normalized 197 gene expression as predictor variable. Gene set enrichment analysis was implemented to determine the dysregulated gene sets between the high-risk and low-risk groups. Similarity Network Fusion (SNF)-based integrative clustering was performed to identify subgroups of AML patients with different clinical features.ResultsThe random forest model was deemed the best model (area under curve value, 0.75). The random forest-derived risk score exhibited significant association with shorter overall survival in AML patients. The gene sets of pantothenate and coa biosynthesis, glycerolipid metabolism, biosynthesis of unsaturated fatty acids were significantly enriched in phenotype high risk score. SNF-based integrative clustering indicated three distinct subsets of AML patients in the TCGA cohort. The cluster3 AML patients were characterized by older age, higher risk score, more frequent TP53 mutations, higher cytogenetics risk, shorter overall survival.ConclusionsThe random forest-based risk score offers an effective method to perform prognosis prediction for AML patients.
| S-EPMC8892720 | biostudies-literature