Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.

This paper identifies prognosis factors for survival in patients with acute myeloid leukemia (AML) using machine learning techniques. We have integrated machine learning with feature selection methods and have compared their performances to identify the most suitable factors in assessing the surviva...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Keyvan Karami, Mahboubeh Akbari, Mohammad-Taher Moradi, Bijan Soleymani, Hossein Fallahi
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/fd77825e3e4741b6aa5d9b0b2418aa8a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:fd77825e3e4741b6aa5d9b0b2418aa8a
record_format dspace
spelling oai:doaj.org-article:fd77825e3e4741b6aa5d9b0b2418aa8a2021-12-02T20:06:42ZSurvival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.1932-620310.1371/journal.pone.0254976https://doaj.org/article/fd77825e3e4741b6aa5d9b0b2418aa8a2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254976https://doaj.org/toc/1932-6203This paper identifies prognosis factors for survival in patients with acute myeloid leukemia (AML) using machine learning techniques. We have integrated machine learning with feature selection methods and have compared their performances to identify the most suitable factors in assessing the survival of AML patients. Here, six data mining algorithms including Decision Tree, Random Forrest, Logistic Regression, Naive Bayes, W-Bayes Net, and Gradient Boosted Tree (GBT) are employed for the detection model and implemented using the common data mining tool RapidMiner and open-source R package. To improve the predictive ability of our model, a set of features were selected by employing multiple feature selection methods. The accuracy of classification was obtained using 10-fold cross-validation for the various combinations of the feature selection methods and machine learning algorithms. The performance of the models was assessed by various measurement indexes including accuracy, kappa, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC). Our results showed that GBT with an accuracy of 85.17%, AUC of 0.930, and the feature selection via the Relief algorithm has the best performance in predicting the survival rate of AML patients.Keyvan KaramiMahboubeh AkbariMohammad-Taher MoradiBijan SoleymaniHossein FallahiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254976 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Keyvan Karami
Mahboubeh Akbari
Mohammad-Taher Moradi
Bijan Soleymani
Hossein Fallahi
Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
description This paper identifies prognosis factors for survival in patients with acute myeloid leukemia (AML) using machine learning techniques. We have integrated machine learning with feature selection methods and have compared their performances to identify the most suitable factors in assessing the survival of AML patients. Here, six data mining algorithms including Decision Tree, Random Forrest, Logistic Regression, Naive Bayes, W-Bayes Net, and Gradient Boosted Tree (GBT) are employed for the detection model and implemented using the common data mining tool RapidMiner and open-source R package. To improve the predictive ability of our model, a set of features were selected by employing multiple feature selection methods. The accuracy of classification was obtained using 10-fold cross-validation for the various combinations of the feature selection methods and machine learning algorithms. The performance of the models was assessed by various measurement indexes including accuracy, kappa, sensitivity, specificity, positive predictive value, negative predictive value, and area under the ROC curve (AUC). Our results showed that GBT with an accuracy of 85.17%, AUC of 0.930, and the feature selection via the Relief algorithm has the best performance in predicting the survival rate of AML patients.
format article
author Keyvan Karami
Mahboubeh Akbari
Mohammad-Taher Moradi
Bijan Soleymani
Hossein Fallahi
author_facet Keyvan Karami
Mahboubeh Akbari
Mohammad-Taher Moradi
Bijan Soleymani
Hossein Fallahi
author_sort Keyvan Karami
title Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
title_short Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
title_full Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
title_fullStr Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
title_full_unstemmed Survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
title_sort survival prognostic factors in patients with acute myeloid leukemia using machine learning techniques.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/fd77825e3e4741b6aa5d9b0b2418aa8a
work_keys_str_mv AT keyvankarami survivalprognosticfactorsinpatientswithacutemyeloidleukemiausingmachinelearningtechniques
AT mahboubehakbari survivalprognosticfactorsinpatientswithacutemyeloidleukemiausingmachinelearningtechniques
AT mohammadtahermoradi survivalprognosticfactorsinpatientswithacutemyeloidleukemiausingmachinelearningtechniques
AT bijansoleymani survivalprognosticfactorsinpatientswithacutemyeloidleukemiausingmachinelearningtechniques
AT hosseinfallahi survivalprognosticfactorsinpatientswithacutemyeloidleukemiausingmachinelearningtechniques
_version_ 1718375400602599424