Timelines of Prostate Cancer Biomarkers
Prostate cancer is a deadly disease which affects men, yet there are few specific and sensitive biomarkers that can be used to diagnose and provide prognosis for the disease. Prostate specific antigen (PSA) is a serum protein that is one of the most well-established biomarkers in prostate cancer, but it lacks specificity and sensitivity. As a result, researchers are in search of other biomarkers such as genes or proteins that can be used for prostate cancer diagnostic test. In order to save effort, qualitative reviews based on primary studies are manually performed to characterize genes and proteins as emerging biomarkers. However, one problem is that less effective biomarkers might not be explicitly addressed as poor biomarkers in primary studies due to publication bias. We use text mining to provide a tool to examine whether biomarkers are emerging or decreasing in terms of publication popularity. In addition, we provide a tool to examine the increasing or decreasing popularity of gene families with respect to prostate cancer research. Selected biomarkers which have been labelled as emerging in qualitative reviews are evaluated using our approach. We also provide public access to our web portal to allow users to explore genes or gene families that they are interested in.
KeywordsProstate cancer Text mining Data mining
- 2.Diamandis, E.P., Yousef, G.M.: Human tissue kallikreins: a family of new cancer biomarkers. Clin. Chem. 48(8), 1198–1205 (2002)Google Scholar
- 3.Draisma, G., Boer, R., Otto, S.J., van der Cruijsen, I.W., Damhuis, R.A., Schröder, F.H., de Koning, H.J.: Lead times and overdetection due to prostate-specific antigen screening: estimates from the European randomized study of screening for prostate cancer. J. Natl. Cancer Inst. 95(12), 868–878 (2003)CrossRefGoogle Scholar
- 4.Economist: Time’s up. Economist 422(9033), 69–71 (2017)Google Scholar
- 16.Wang, M., Valenzuela, L., Murphy, G., Chu, T.: Purification of a human prostate specific antigen. Investig. Urol. 17(2), 159–163 (1979)Google Scholar
- 17.Xylogiannopoulos, K., Karampelas, P., Alhajj, R.: Discretization method for the detection of local extrema and trends in non-discrete time series. In: ICEIS 2015 - 17th International Conference on Enterprise Information Systems (2015)Google Scholar