Building Biomarker Combinations for Korean Ovarian Cancer Screening Using Statistics and Machine Learning

Abstract:

Early screening using appropriate biomarkers is helpful for the effective treatment of ovarian cancer. CA-125, the most widely used biomarker for the diagnosis of ovarian cancer, has high false positive and false negative rates. We introduce an approach for determining an appropriate combination of biomarkers known to be highly related to ovarian cancer among 21 predetermined biomarkers. Sera representing 27 cases and 31 controls from women undergoing surgery were examined using high-throughput, multiplexed bead-based immunoassays. Student’s t-test and a genetic algorithm (GA) were employed and compared for building the proper combination of two to four biomarkers. The combinations selected by both methods were compared with a 5-fold cross validation of the LDA classifier. The combination of four markers chosen by the GA had the best performance in regards to accuracy, with sensitivity and specificity of 81% and 100%, respectively.

• Periodical: Applied Mechanics and Materials (Volume 145)
• Pages: 229-233
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.145.229
• Online since: December 2011
• Authors: Hey Jeong Song, Yu Seop Kim, Kwang Won Choi, Jong Dae Kim, Chan Young Park, Erika Lee, Jong Won Kim
• Keywords: Biomarker Combination, Genetic Algorithm (GA), Ovarian Cancer Screening, T-Test

References

[1] Time site: http: /www. time. com/time/health/article/0, 8599, 1990534, 00. html.

[2] Seoul National University Hospital site : http: /cancer. snuh. org/center. GCCenter. cancerDefaultView. snuh?selectedCancerId= CAT_20110127000139.

[3] Asan Medical Center site : http: /uouapn. amc. seoul. kr/healthinfo/disease/detail. do?icdt=HD00000226.

[4] Z, Zhang, R.C. Bast Jr., Y. Yu, J. Li, L.J. Sokoll, A.J. Rai, J.M. Rosenzweig, B. Cameron, Y.Y. Wang, X. Meng, A. Berchuck, C. can Haaften-Day, N.F. Hacker, H.W.A. de Bruijn, A.G.J. van der Zee, I.J. Jacobs, E.T. Fung, and D.W. Chan, Cancer Research. Vol. 64 (2004).

DOI: 10.1158/0008-5472.can-04-0746

[5] Z. Yurkovetsky, S. Skates, A. Lomakin, B. Nolen, T. Pulsipher, F. Modugno, J. Marks, A. Godwin, E. Gorelik, I. Kacobs, U. Menon, K. Lu, D. Badgwell, R.C. Bast Jr. and A.E. Lokshin, Journal of Clinical Oncology. Vol. 28 (2010).

DOI: 10.1200/jco.2008.19.2484

[6] L.J. Havrilesky, C.M. Whitehead, J.M. Rubatt, R.L. Cheek, J. Groelke, Q. He, D.P. Malinowski, T.J. Fischer and A. Berchuck, Gynecologic Oncology. Vol. 110 (2008).

DOI: 10.1016/j.ygyno.2008.04.041

[7] Y.M. Kim, D.H. Whang, J. Park, S.H. Kim, S.W. Lee, H.A. Park, M. Ha and K. Choi, Clinical Chemical Laboratory Medicine. Vol. 49 (2011).

[8] S. Jung, E. Oh, C. Yang, W. Ahn, Y. Kim, Y. Park and K Han, Korean Journal of Laboratory Medicine. Vol. 29 (2009).

[9] N. El-Awar, J. Lee and P. Terasaki, Hum Immunol. Vol. 66 (2005).

[10] B. Nolen, A. Marrangoni, L. Velikokohatnaya, D. Prosser, M. Winans, E. Gorelik and A. Lokshin, Gynecologic Oncology. Vol. 112 (2009).

DOI: 10.1016/j.ygyno.2008.09.043

[11] S.D. Amonkar, G.P. Bertenshaw, T. Chen, K.J. Bergstrom, J. Zhao, P. Seshaiah, P. Yip and B.C. Mansfield, PLos ONE. Vol. 4 (2009).

DOI: 10.1371/journal.pone.0004599

[12] University of Pittsburgh Cancer Institute site : http: /www. upci. upmc. edu/facilities/luminex/sources. html.

[13] D.E. Goldberg, Genetic Algorithms in Search Optimization & Machine Learning, Addison-Wesley (1989).

[14] MathWorks. inc site : http: /www. mathworks. com/matlabcentral/fileexchange/5051.