Diagnosis of Brain Metastases from Lung Cancer Using a Modified Electromagnetism like Mechanism Algorithm

详细信息    查看全文

• 作者：Kun-Huang Chen ; Kung-Jeng Wang ; Angelia Melani Adrian…
• 关键词：Brain metastases ; Electromagnetism like mechanism ; Feature selection ; Lung cancer ; Support vector machine ; Synthetic minority over ; sampling technique
• 刊名：Journal of Medical Systems
• 出版年：2016
• 出版时间：January 2016
• 年：2016
• 卷：40
• 期：1
• 全文大小：1,381 KB
• 参考文献：1.Chi, A., and Komaki, R., Treatment of brain metastasis from lung cancer. Cancers 2(4):2100鈥?137, 2010.PubMed PubMedCentral CrossRef
  2.Schouten, L. J., Rutten, J., Huveneers, H. A., and Twijnstra, A., Incidence of brain metastases in a cohort of patients with carcinoma of the breast, colon, kidney, and lung and melanoma. Cancer 94(10):2698鈥?05, 2002.PubMed CrossRef
  3.Smedby, K. E., Brandt, L., B盲cklund, M. L., and Blomqvist, P., Brain metastases admissions in Sweden between 1987 and 2006. Br. J. Cancer 101(11):1919鈥?924, 2009.PubMed PubMedCentral CrossRef
  4.Karachaliou, N., and Rosell, R., Treatment of brain metastases in non-small cell lung cancer (NSCLC) patients with epidermal growth factor receptor (EGFR) mutations: the role of EGFR tyrosine kinase inhibitors. Ann. Palliat. Med. 2(3):114鈥?17, 2013.PubMed
  5.Tseng, WT., et al. The Application of Data Mining Techniques to Oral Cancer Prognosis. Journal of medical system. 39(5): 2015.
  6.Lu, HY., et al. Predicting Long-Term Outcome After Traumatic Brain Injury Using Repeated Measurements of Glasgow Coma Scale and Data Mining Methods. Journal of medical system, 39(2): 2015.
  7.Peker, M., et al. Rapid Automated Classification of Anesthetic Depth Levels using GPU Based Parallelization of Neural Networks. Journal of medical system, 39(2): 2015.
  8.Birbil, I., and Fang, S. C., An electromagnetism-like mechanism for global optimization. J. Glob. Optim. 25:263鈥?82, 2003.CrossRef
  9.Su, C. T., and Lin, H. C., Applying electromagnetism-like mechanism for feature selection. Inf. Sci. 181(5):972鈥?86, 2011.CrossRef
  10.Lin, H. C., and Su, C. T., A selective Bayes classifier with meta-heuristics for incomplete data. Neurocomputing 106:95鈥?02, 2013.CrossRef
  11.Chen, L. F., Su, C. T., and Chen, K. H., An improved particle swarm optimization for feature selection. Int. Data Anal. 16(2):167鈥?82, 2012.
  12.Lichman, M., UCI Machine Learning Repository [http://鈥媋rchive.鈥媔cs.鈥媢ci.鈥媏du/鈥媘l ]. Irvine, CA: University of California, School of Information and Computer Science, 2013.
  13.IDA Repository [http://鈥媔da.鈥媐irst.鈥媑md.鈥媎e/鈥媬raetsch/鈥媎ata/鈥媌enchmarks.鈥媓tm ], 2014.
  14.Broad Institute TCGA Genome Data Analysis Center. Cancer Program Data Sets [http://鈥媤ww.鈥媌roadinstitute.鈥媜rg/鈥媍gi-bin/鈥媍ancer/鈥媎atasets.鈥媍gi ]. Broad Institute of MIT and Harvard, 2013.
  15.Lung Cancer Microarray Dataset. [http://鈥媎atam.鈥媔2r.鈥媋-star.鈥媏du.鈥媠g/鈥媎atasets/鈥媖rbd/鈥媔ndex.鈥媓tml ], 2014.
  16.National Health Insurance Research Database, Taiwan. Bureau of National Health Insurance, Department of Health and managed by National Health Research Institute. [http://鈥媙hird.鈥媙hri.鈥媜rg.鈥媡w/鈥媏n/鈥媔ndex.鈥媓tm ], 2014.
  17.Bhattacharjee, A., et al., Classification of human lung carcinomas by mRNA expression profiling reveals Distinct adenocarcinoma subclasses. PNAS 98(24):13790鈥?3795, 2001.PubMed PubMedCentral CrossRef
  18.Gordon, G. J., et al., Translation of microarray data into clinically relevant cancer diagnostic tests using gege expression ratios in lung cancer and mesothelioma. Cancer Res. 62:4963鈥?967, 2002.PubMed
  19.Beer, D. G., et al., Gene-expression Profiles Predict Survival of Patients with Lung Adenocarcinoma. Nat. Med. 8(8):816鈥?23, 2002.PubMed
  20.Wigle, D. A., et al., Molecular profiling of Non-small cell lung cancer and correlation with disease-free survival. Cancer Res. 62:3005鈥?008, 2002.PubMed
  21.Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P., SMOTE: Synthetic Minority Over-sampling Technique. J. Artif. Intell. Res. 16:321鈥?57, 2002.
  22.Vapnik, V., Statistical learning theory. Wiley, New York, NY, 1998.
  23.Nguyen, M. H., and de la Torre, F., Optimal feature selection for support vector machines. Pattern Recogn. 43(3):584鈥?91, 2010.CrossRef
  24.Li, S., Wu, H., Wan, D., and Zuu, J., An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine. Knowl.-Based Syst. 24(1):40鈥?8, 2011.CrossRef
  25.Van Hulse, J., and Khoshgoftaar, J. T., Knowledge discovery from imbalanced and noisy data. Data Knowl. Eng. 68(12):1513鈥?542, 2009.CrossRef
  26.Vieira, S., Mendon莽a, L. F., Farinha, G. J., and Sousa, J. M. C., Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients. Appl. Soft Comput. 13(8):3494鈥?504, 2013.CrossRef
  27.Zi醛ba, M., Tomczak, J. M., Lubicz, M., and 艢wia抬tek, J., Boosted SVM for extracting rules from imbalanced data in application to prediction of the post-operative life expectancy in the lung cancer patients. Appl. Soft Comput. J. 14(A):99鈥?08, 2014.CrossRef
  28.Avci, E., A New expert system for diagnosis of lung cancer: GDA鈥擫S_SVM. J. Med. Syst. 36(3):2005鈥?009, 2012.PubMed CrossRef
  29.Jiang, X., R. El-Kareh, L. Ohno-Machado, Improving predictions in imbalanced datavusing pairwise expanded logistic regression. Annual Symposium on Biomedical and Health Informatics (AMIA鈥?1), 2001
  30.He, H., and Garcia, E., Learning for imbalanced data IEEE Trans. Data Knowl. Eng. 21(9):1263鈥?284, 2009.CrossRef
  31.Kang, P., and Cho, S., Eus svms: ensemble of under-sampled svms for data imbalance problems. Neural Inf. Process. 4232:837鈥?46, 2006.CrossRef
  32.Wang, K. J., Makond, B., and Wang, K. M., An improved survivability diagnosis of breast cancer by using sampling and feature selection technique to solve imbalanced patient classification data. BMC Med. Informat Decis Making 13(124):2鈥?4, 2013.
  33.Gao, M., Hong, X., Chen, S., Harris, C., J. On combination of SMOTE and particle swarm optimization based radial basis function classifier for imbalanced problems. Proceedings of the International Joint Conference on Neural Networks. 6033353: 1146鈥?153, 2011.
  34.Polat, K., Sahan, S., Kodaz, H., and G眉nes, S., Breast cancer and liver disorders classification using artificial immune recognition system (AIRS) with performance evaluation by fuzzy resource allocation mechanism. Expert Syst. Appl. 32(1):172鈥?83, 2007.CrossRef
  35.Saidi, M., Chikh, M., Settouti, N. Automatic identification of diabetes diseases using a Modified Artificial Immune Recognition System2 (MAIRS2). Proceedings of the International Conference on Computer Science and its Applications, 20, 2011.
  36.Werbos P., J. Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD thesis; Harvard University: 1974.
  37.Rumelhart, D. E., Hinton, G. E., and Williams, R. J., Learning representations by back-propagating errors. Nature 323(6088):533鈥?36, 1986.CrossRef
  38.Singer, E., Couper, M. P., Fagerlin, A., Van Hoewyk, J., and Zikmund-Fisher, B. J., The role of perceived benefits and costs in patients鈥?medical decisions. Health Expect. 17(1):4鈥?4, 2014.PubMed CrossRef
  39.Greenop, K. R., Blair, E. M., Bower, C., Armstrong, B. K., and Milne, E., Factors relating to pregnancy and birth and the risk of childhood brain tumors: Results from an Australian case鈥揷ontrol study. Pediatric Blood Cancer. 61(3):493鈥?98, 2014.PubMed CrossRef
  40.Yan, A. F., Voorhees, C. C., Beck, K. H., and Wang, M. Q., A social ecological assessment of physical activity among urban adolescents. Am. J. Health Behav. 38(3):379鈥?91, 2014.PubMed CrossRef
  41.Quinlan, J. R. C4.5: Programs for Machine Learning. Morgan Kaufmann. 1993.
  42.Razavi, A. R., Gill, H., Ahlfeldt, H., and Shahsavar, N., Predicting metastasis in breast cancer: comparing a decision tree with domain experts. J. Med. Syst. 31(4):263鈥?73, 2007.PubMed CrossRef
  43.Park, J., and Sandberg, J. W., Universal approximation using rasial basis function network. Neural Comput. 3:246鈥?57, 1991.CrossRef
  44.Poggio, T., and Girosi, F., Networks for approximation learning. Proc. IEEE. 78(9):1481鈥?497, 1990.CrossRef
  45.Kohonen, T., Self-organized formation of topologically correct feature maps. Biol. Cybern. 43:59鈥?9, 1982.CrossRef
  46.Saadatdoost, R., Alex, T., H., S., Jafarkarimi, H. Application of self organizing map for knowledge discovery based in higher education data. Proceeding of International Conference on IEEE Research and Innovation in Information Systems (ICRIIS), 1鈥?, 2011.
  47.Witten, I. H. and Frank, E. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann. 2005
  
• 作者单位：Kun-Huang Chen (1)
  Kung-Jeng Wang (1)
  Angelia Melani Adrian (1)
  Kung-Min Wang (2)
  Nai-Chia Teng (3)
  
  1. Department of Industrial Management, National Taiwan University of Science and Technology, Daan District, Taipei 106, Taiwan, Republic of China
  2. Department of Surgery, Shin-Kong Wu Ho-Su Memorial Hospital, Shilin District, Taipei 111, Taiwan, Republic of China
  3. School of Dentistry, College of Oral Medicine, Taipei Medical University, Taipei 110, Taiwan, Republic of China
  
• 刊物类别：Mathematics and Statistics
• 刊物主题：Statistics
  Statistics for Life Sciences, Medicine and Health Sciences
  Health Informatics and Administration
  
• 出版者：Springer Netherlands
• ISSN：1573-689X

文摘

Brain metastases are commonly found in patients that are diagnosed with primary malignancy on their lung. Lung cancer patients with brain metastasis tend to have a poor survivability, which is less than 6 months in median. Therefore, an early and effective detection system for such disease is needed to help prolong the patients鈥?survivability and improved their quality of life. A modified electromagnetism-like mechanism (EM) algorithm, MEM-SVM, is proposed by combining EM algorithm with support vector machine (SVM) as the classifier and opposite sign test (OST) as the local search technique. The proposed method is applied to 44 UCI and IDA datasets, and 5 cancers microarray datasets as preliminary experiment. In addition, this method is tested on 4 lung cancer microarray public dataset. Further, we tested our method on a nationwide dataset of brain metastasis from lung cancer (BMLC) in Taiwan. Since the nature of real medical dataset to be highly imbalanced, the synthetic minority over-sampling technique (SMOTE) is utilized to handle this problem. The proposed method is compared against another 8 popular benchmark classifiers and feature selection methods. The performance evaluation is based on the accuracy and Kappa index. For the 44 UCI and IDA datasets and 5 cancer microarray datasets, a non-parametric statistical test confirmed that MEM-SVM outperformed the other methods. For the 4 lung cancer public microarray datasets, MEM-SVM still achieved the highest mean value for accuracy and Kappa index. Due to the imbalanced property on the real case of BMLC dataset, all methods achieve good accuracy without significance difference among the methods. However, on the balanced BMLC dataset, MEM-SVM appears to be the best method with higher accuracy and Kappa index. We successfully developed MEM-SVM to predict the occurrence of brain metastasis from lung cancer with the combination of SMOTE technique to handle the class imbalance properties. The results confirmed that MEM-SVM has good diagnosis power and can be applied as an alternative diagnosis tool in with other medical tests for the early detection of brain metastasis from lung cancer. Keywords Brain metastases Electromagnetism like mechanism Feature selection Lung cancer Support vector machine Synthetic minority over-sampling technique