Abstract
The data from independent gene expression sources may be integrated for the purpose of molecular diagnostics of cancer. So far, multiple approaches were described. Here, we investigated the impacts of different data fusion strategies on classification accuracy and feature selection stability, which allow the costs of diagnostic tests to be reduced. We used molecular features (gene expression) combined with a feature extracted from the independent clinical data describing a patient’s sample. We considered the dependencies between selected features in two data fusion strategies (early fusion and late fusion) compared to classification models based on molecular features only. We compared the best accuracy classification models in terms of the number of features, which is connected to the potential cost reduction of the diagnostic classifier. We show that for thyroid cancer, the extracted clinical feature is correlated with (but not redundant to) the molecular data. The usage of data fusion allows a model to be obtained with similar or even higher classification quality (with a statistically significant accuracy improvement, a p-value below 0.05) and with a reduction in molecular dimensionality of the feature space from 15 to 3–8 (depending on the feature selection method). Both strategies give comparable quality results, but the early fusion method provides better feature selection stability.
Funder
Silesian University of Technology
Polish Ministry of Science and Higher Education
National Center for Research and Development project MILE-STONE
Subject
Inorganic Chemistry,Organic Chemistry,Physical and Theoretical Chemistry,Computer Science Applications,Spectroscopy,Molecular Biology,General Medicine,Catalysis
Reference44 articles.
1. Artificial Intelligence and Machine Learning in Clinical Development: A Translational Perspective;NPJ Digit. Med.,2019
2. Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data;Front. Genet.,2019
3. Hira, Z.M., and Gillies, D.F. (2020, April 05). A Review of Feature Selection and Feature Extraction Methods Applied on Microarray Data. Available online: https://www.hindawi.com/journals/abi/2015/198363/.
4. Li, G.-Z., Bu, H.-L., Yang, M.Q., Zeng, X.-Q., and Yang, J.Y. (2008). Selecting Subsets of Newly Extracted Features from PCA and PLS in Microarray Data Analysis. BMC Genom., 9.
5. Wee, L.J., Simarmata, D., Kam, Y.-W., Ng, L.F., and Tong, J.C. (2010). SVM-Based Prediction of Linear B-Cell Epitopes Using Bayes Feature Extraction. BMC Genom., 11.
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献