Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics
Determining the aggressiveness of gliomas, termed grading, is a critical step toward treatment optimization to increase the survival rate and decrease treatment toxicity for patients. Streamlined grading using molecular information has the potential to facilitate decision making in the clinic and ai...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/22/14155 |
| _version_ | 1797465087088263168 |
|---|---|
| author | Erdal Tasci Ying Zhuge Harpreet Kaur Kevin Camphausen Andra Valentina Krauze |
| author_facet | Erdal Tasci Ying Zhuge Harpreet Kaur Kevin Camphausen Andra Valentina Krauze |
| author_sort | Erdal Tasci |
| collection | DOAJ |
| description | Determining the aggressiveness of gliomas, termed grading, is a critical step toward treatment optimization to increase the survival rate and decrease treatment toxicity for patients. Streamlined grading using molecular information has the potential to facilitate decision making in the clinic and aid in treatment planning. In recent years, molecular markers have increasingly gained importance in the classification of tumors. In this study, we propose a novel hierarchical voting-based methodology for improving the performance results of the feature selection stage and machine learning models for glioma grading with clinical and molecular predictors. To identify the best scheme for the given soft-voting-based ensemble learning model selections, we utilized publicly available TCGA and CGGA datasets and employed four dimensionality reduction methods to carry out a voting-based ensemble feature selection and five supervised models, with a total of sixteen combination sets. We also compared our proposed feature selection method with the LASSO feature selection method in isolation. The computational results indicate that the proposed method achieves 87.606% and 79.668% accuracy rates on TCGA and CGGA datasets, respectively, outperforming the LASSO feature selection method. |
| first_indexed | 2024-03-09T18:16:26Z |
| format | Article |
| id | doaj.art-285dc3740f85492085b1ca3f2d0d56bc |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T18:16:26Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-285dc3740f85492085b1ca3f2d0d56bc2023-11-24T08:39:28ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-11-0123221415510.3390/ijms232214155Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular CharacteristicsErdal Tasci0Ying Zhuge1Harpreet Kaur2Kevin Camphausen3Andra Valentina Krauze4Radiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Building 10, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Building 10, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Building 10, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Building 10, Bethesda, MD 20892, USARadiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, Building 10, Bethesda, MD 20892, USADetermining the aggressiveness of gliomas, termed grading, is a critical step toward treatment optimization to increase the survival rate and decrease treatment toxicity for patients. Streamlined grading using molecular information has the potential to facilitate decision making in the clinic and aid in treatment planning. In recent years, molecular markers have increasingly gained importance in the classification of tumors. In this study, we propose a novel hierarchical voting-based methodology for improving the performance results of the feature selection stage and machine learning models for glioma grading with clinical and molecular predictors. To identify the best scheme for the given soft-voting-based ensemble learning model selections, we utilized publicly available TCGA and CGGA datasets and employed four dimensionality reduction methods to carry out a voting-based ensemble feature selection and five supervised models, with a total of sixteen combination sets. We also compared our proposed feature selection method with the LASSO feature selection method in isolation. The computational results indicate that the proposed method achieves 87.606% and 79.668% accuracy rates on TCGA and CGGA datasets, respectively, outperforming the LASSO feature selection method.https://www.mdpi.com/1422-0067/23/22/14155diagnosticbrain tumorgliomagradingmolecular dataoncology |
| spellingShingle | Erdal Tasci Ying Zhuge Harpreet Kaur Kevin Camphausen Andra Valentina Krauze Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics International Journal of Molecular Sciences diagnostic brain tumor glioma grading molecular data oncology |
| title | Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics |
| title_full | Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics |
| title_fullStr | Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics |
| title_full_unstemmed | Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics |
| title_short | Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics |
| title_sort | hierarchical voting based feature selection and ensemble learning model scheme for glioma grading with clinical and molecular characteristics |
| topic | diagnostic brain tumor glioma grading molecular data oncology |
| url | https://www.mdpi.com/1422-0067/23/22/14155 |
| work_keys_str_mv | AT erdaltasci hierarchicalvotingbasedfeatureselectionandensemblelearningmodelschemeforgliomagradingwithclinicalandmolecularcharacteristics AT yingzhuge hierarchicalvotingbasedfeatureselectionandensemblelearningmodelschemeforgliomagradingwithclinicalandmolecularcharacteristics AT harpreetkaur hierarchicalvotingbasedfeatureselectionandensemblelearningmodelschemeforgliomagradingwithclinicalandmolecularcharacteristics AT kevincamphausen hierarchicalvotingbasedfeatureselectionandensemblelearningmodelschemeforgliomagradingwithclinicalandmolecularcharacteristics AT andravalentinakrauze hierarchicalvotingbasedfeatureselectionandensemblelearningmodelschemeforgliomagradingwithclinicalandmolecularcharacteristics |