Asian Pacific Journal of Cancer Prevention

Asian Pacific Journal of Cancer Prevention (아시아태평양암예방학회)
권호 표지
DOI QR코드

DOI QR Code

Evaluation of Machine Learning Algorithm Utilization for Lung Cancer Classification Based on Gene Expression Levels

  • Published : 2016.03.07
Download PDF
⟨ Previous Next ⟩

Abstract

Background: Lung cancer remains one of the most common cancers in the world, both in terms of new cases (about 13% of total per year) and deaths (nearly one cancer death in five), because of the high case fatality. Errors in lung cancer type or malignant growth determination lead to degraded treatment efficacy, because anticancer strategy depends on tumor morphology. Materials and Methods: We have made an attempt to evaluate effectiveness of machine learning algorithms in the task of lung cancer classification based on gene expression levels. We processed four publicly available data sets. The Dana-Farber Cancer Institute data set contains 203 samples and the task was to classify four cancer types and sound tissue samples. With the University of Michigan data set of 96 samples, the task was to execute a binary classification of adenocarcinoma and non-neoplastic tissues. The University of Toronto data set contains 39 samples and the task was to detect recurrence, while with the Brigham and Women's Hospital data set of 181 samples it was to make a binary classification of malignant pleural mesothelioma and adenocarcinoma. We used the k-nearest neighbor algorithm (k=1, k=5, k=10), naive Bayes classifier with assumption of both a normal distribution of attributes and a distribution through histograms, support vector machine and C4.5 decision tree. Effectiveness of machine learning algorithms was evaluated with the Matthews correlation coefficient. Results: The support vector machine method showed best results among data sets from the Dana-Farber Cancer Institute and Brigham and Women's Hospital. All algorithms with the exception of the C4.5 decision tree showed maximum potential effectiveness in the University of Michigan data set. However, the C4.5 decision tree showed best results for the University of Toronto data set. Conclusions: Machine learning algorithms can be used for lung cancer morphology classification and similar tasks based on gene expression level evaluation.

Keywords

References

  1. Baldi P, Brunak S, Chauvin Y, Andersen CAF, and Nielsen H (2000). Assessing the accuracy of prediction algorithms for classification: an overview. Bioinformatics, 16, 412-24. https://doi.org/10.1093/bioinformatics/16.5.412
  2. Beer DG, Kardia SLR, Huang CC, et al (2002). Geneexpression profiles predict survival of patients with lung adenocarcinoma. Nature Medicine. 8, 816-24. https://doi.org/10.1038/nm733
  3. Bhattacharjee A, Richards WG, Staunton J, et al (2001). Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses. Proceedings of the National Academy of Sciences, 98, 13790-5. https://doi.org/10.1073/pnas.191502998
  4. Cai Z, Xu D, Zhang Q, et al (2015). Classification of lung cancer using ensemble-based feature selection and machine learning methods. Mol BioSyst, 11, 791-800. https://doi.org/10.1039/C4MB00659C
  5. Cheng P, Cheng Y, Li Y, et al (2012). Comparison of the gene expression profiles between smokers with and without lung cancer using RNA-Seq. Asian Pac J Cancer Prev, 13, 3605-9. https://doi.org/10.7314/APJCP.2012.13.8.3605
  6. Cruz JA, and Wishart DS (2006). Applications of machine learning in cancer prediction and prognosis. Cancer Informatics, 2, 59-77.
  7. Ferlay J, Soerjomataram I, Dikshit R, et al (2015). Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. Intern J Cancer, 136, 359-86. https://doi.org/10.1002/ijc.29210
  8. Gordon GJ, Jensen RV, Hsiao LL, et al (2002). Translation of microarray data into clinically relevant cancer diagnostic tests using gene expression ratios in lung cancer and mesothelioma. Cancer Research, 62, 4963-7.
  9. Guo S, Yan F, Xu J, et al (2015). Identification and validation of the methylation biomarkers of non-small cell lung cancer (NSCLC). Clinical Epigenetics, 7, 3. https://doi.org/10.1186/s13148-014-0035-3
  10. Han Y, Wang XB, Xiao N, and Liu ZD (2013). mRNA Expression and Clinical Significance of ERCC1, BRCA1, RRM1, TYMS and TUBB3 in postoperative patients with non-small cell lung cancer. Asian Pac J Cancer Prev, 14, 2987-90. https://doi.org/10.7314/APJCP.2013.14.5.2987
  11. Hosseinzadeh F, Kayvan Joo AH, Ebrahimi M, Goliaei B (2013). Prediction of lung tumor types based on protein attributes by machine learning algorithms. Springer Plus, 2, 238. https://doi.org/10.1186/2193-1801-2-238
  12. Jung KW, Won YJ, Kong HJ, et al (2014). Cancer statistics in korea: incidence, mortality, survival, and prevalence in 2011. Cancer Res Treat, 46, 109-23. https://doi.org/10.4143/crt.2014.46.2.109
  13. Lei Win S, Htike ZZ, Yusof F, Noorbatcha AI (2014). Gene expression mining for predicting survivability of patients in earlystages of lung cancer. Int J Bioinformatics Biosciences, 4, 1-9.
  14. Li J, Li D, Wei X, Su Y (2014). In silico comparative genomic analysis of two non-small cell lung cancer subtypes and their potentials for cancer classification. Cancer Genomics Proteomics, 11, 303-10.
  15. Liu M, Pan H, Zhang F, et al (2013). Screening of differentially expressed genes among various TNM stages of lung adenocarcinoma by genomewide gene expression profile analysis. Asian Pac J Cancer Prev, 14, 6281-6. https://doi.org/10.7314/APJCP.2013.14.11.6281
  16. Pass HI (2001). Malignant pleural mesothelioma: surgical roles and novel therapies. Clinical Lung Cancer, 3, 102-7. https://doi.org/10.3816/CLC.2001.n.021
  17. Sun T, Wang J, Li X, et al (2013). Comparative evaluation of support vector machines for computer aided diagnosis of lung cancer in CT based on a multi-dimensional data set. Computer Methods Programs Biomedicine, 111, 519-24. https://doi.org/10.1016/j.cmpb.2013.04.016
  18. Wang JJ, Wu HF, Sun T, et al (2013). Prediction models for solitary pulmonary nodules based on curvelet textural features and clinical parameters. Asian Pac J Cancer Prev, 14, 6019-23. https://doi.org/10.7314/APJCP.2013.14.10.6019
  19. Wigle DA, Jurisica I, Radulovich N, et al (2002). Molecular profiling of non-small cell lung cancer and correlation with disease-free survival. Cancer Res, 62, 3005-8.
  20. Yu Z, Lu H, Si H, et al (2015). A highly efficient gene expression programming (GEP) model for auxiliary diagnosis of small cell lung cancer. PLoS ONE, 10, 125517.

Cited by

  1. Evaluating Various Lung Cancer Nodule Detection Techniques—A Comparative Study vol.46, pp.2, 2018, https://doi.org/10.1520/JTE20160410
  2. Role of artificial intelligence in the care of patients with nonsmall cell lung cancer vol.48, pp.4, 2018, https://doi.org/10.1111/eci.12901
  3. Artificial intelligence in cancer imaging: Clinical challenges and applications pp.1542-4863, 2019, https://doi.org/10.3322/caac.21552