Developing an Improved Survival Prediction Model for Disease Prognosis
Machine learning has become an important research field in genetics and molecular biology. Survival analysis using machine learning can provide an important computed-aid clinical research scheme for evaluating tumor treatment options. However, the genomic features are high-dimensional, which limits...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/12/12/1751 |
| _version_ | 1797461223352041472 |
|---|---|
| author | Zhanbo Chen Qiufeng Wei |
| author_facet | Zhanbo Chen Qiufeng Wei |
| author_sort | Zhanbo Chen |
| collection | DOAJ |
| description | Machine learning has become an important research field in genetics and molecular biology. Survival analysis using machine learning can provide an important computed-aid clinical research scheme for evaluating tumor treatment options. However, the genomic features are high-dimensional, which limits the prediction performance of the survival learning model. Therefore, in this paper, we propose an improved survival prediction model using a deep forest and self-supervised learning. It uses a deep survival forest to perform adaptive learning of high-dimensional genomic data and ensure robustness. In addition, self-supervised learning, as a semi-supervised learning style, is designed to utilize unlabeled samples to improve model performance. Based on four cancer datasets from The Cancer Genome Atlas (TCGA), the experimental results show that our proposed method outperforms four advanced survival analysis methods in terms of the C-index and brier score. The developed prediction model will help doctors rethink patient characteristics’ relevance to survival time and personalize treatment decisions. |
| first_indexed | 2024-03-09T17:17:23Z |
| format | Article |
| id | doaj.art-8caad312f7d844d18dd83c2e310ea42f |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-09T17:17:23Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-8caad312f7d844d18dd83c2e310ea42f2023-11-24T13:32:41ZengMDPI AGBiomolecules2218-273X2022-11-011212175110.3390/biom12121751Developing an Improved Survival Prediction Model for Disease PrognosisZhanbo Chen0Qiufeng Wei1China-ASEAN Institutes of Statistics & Guangxi Key Laboratory of Big Data in Finance and Economics, Guangxi University of Finance and Economics, Nanning 530003, ChinaChina-ASEAN Institutes of Statistics & Guangxi Key Laboratory of Big Data in Finance and Economics, Guangxi University of Finance and Economics, Nanning 530003, ChinaMachine learning has become an important research field in genetics and molecular biology. Survival analysis using machine learning can provide an important computed-aid clinical research scheme for evaluating tumor treatment options. However, the genomic features are high-dimensional, which limits the prediction performance of the survival learning model. Therefore, in this paper, we propose an improved survival prediction model using a deep forest and self-supervised learning. It uses a deep survival forest to perform adaptive learning of high-dimensional genomic data and ensure robustness. In addition, self-supervised learning, as a semi-supervised learning style, is designed to utilize unlabeled samples to improve model performance. Based on four cancer datasets from The Cancer Genome Atlas (TCGA), the experimental results show that our proposed method outperforms four advanced survival analysis methods in terms of the C-index and brier score. The developed prediction model will help doctors rethink patient characteristics’ relevance to survival time and personalize treatment decisions.https://www.mdpi.com/2218-273X/12/12/1751survival predictionmachine learningdeep forestself-supervised learning |
| spellingShingle | Zhanbo Chen Qiufeng Wei Developing an Improved Survival Prediction Model for Disease Prognosis Biomolecules survival prediction machine learning deep forest self-supervised learning |
| title | Developing an Improved Survival Prediction Model for Disease Prognosis |
| title_full | Developing an Improved Survival Prediction Model for Disease Prognosis |
| title_fullStr | Developing an Improved Survival Prediction Model for Disease Prognosis |
| title_full_unstemmed | Developing an Improved Survival Prediction Model for Disease Prognosis |
| title_short | Developing an Improved Survival Prediction Model for Disease Prognosis |
| title_sort | developing an improved survival prediction model for disease prognosis |
| topic | survival prediction machine learning deep forest self-supervised learning |
| url | https://www.mdpi.com/2218-273X/12/12/1751 |
| work_keys_str_mv | AT zhanbochen developinganimprovedsurvivalpredictionmodelfordiseaseprognosis AT qiufengwei developinganimprovedsurvivalpredictionmodelfordiseaseprognosis |