The Effects of Age and Some Vital Signs on Prostate-Specific Antigen Concerning Early Diagnosis of Prostate Cancer: A Multinomial Logistic Regression Approach
Keywords:
Risk groups, prostate cancer, pulse rate, age, significantAbstract
Prostate cancer, regarded as a health anomaly frequently experienced by males over the age of 45, has gained prominence among cancer disorders experienced by the entire human species in recent years. Discussions about the anomaly's management, treatment, and early diagnosis have also gained attention. There is a paucity of literature on the application of multinomial logistic regression (MLR) to model prostate-specific antigen (PSA) for early diagnosis of prostate cancer through the effects of age and some vital signs associated with fluctuations in PSA. In this study, multinomial logistic regression was applied to model changes in PSA under two different classifications of the PSA levels (four categories and five categories) with age, pulse rate, systolic blood pressure, and diastolic blood pressure as the predictor variables. In each classification, the procedure begins by only grouping the age predictor variable and finding the effects of the predictor variables on the categories of the PSA. The procedure is then repeated with age and pulse rate grouped. The MLR for the two classifications were then compared based on prediction accuracy, no information rate, and kappa value. The results show that the model with the first classification of PSA was better than the second classification especially when the pulse rate is also grouped.
Age and pulse rate significantly affect prostate-specific antigen (PSA) categories. The 45-55 age group is the most significant, while no-risk individuals have no significant difference in PSA levels. Increased pulse rates may reduce prostate cancer risk in males with PSA levels greater than 50.
References
. E.N. Afogu, I. Sunday-Adeoye, K.C. Ekwedigwe, M.E. Isikhuemen, S.C. Okenwa, S.A. Popoola, M.O.Eliboh, and I.C. Amamilo. Prostate Specific Antigen Screening among Men in Abakaliki, South East Nigeria. Open Jour. of Urology, 7(2017),79–85. https://doi.org/10.4236/oju.2017.75011
. L.L. Galvão, S. Tribess, T.G. Silva, C.G. Santa Rosa, C. G. Pereira, C. G., R.R. Silva, J.E. Sasaki, J.S. Virtuoso Junior, C.A.B. de Lira, and D.A.T. Santos. (2020). Prevalence and Factors Associated with High Concentration of Prostate-Specific Antigen: ELSIA Study.9(2020). Biology. https://doi.org/10.3390/biology9100329
. C.M. Bishop. Pattern Recognition and Machine Learning, (2006) https://doi.org/10.1007/b9479810.1007/978-0-387-45528-0
. E.N. Afogu, I. Sunday-Adeoye, K.C. Ekwedigwe, M.E. Isikhuemen, S.C. Okenwa, S.A. Popoola, M.O. Eliboh, and I.C. Amamilo. Prostate Specific Antigen Screening among Men in Abakaliki, South East Nigeria. Open Jour. of Urology, 7(2017),79–85. https://doi.org/10.4236/oju.2017.75011
. L. Nogueira, Prostate-specific antigen for prostate cancer detection, Int. Brazil Jour. of Urology, 35(2009), 521-531.
. N. Karunasinghe,T.Z. Minas, B.Y. Bao, A. Lee, A. Wang, S. Zhu, J. Masters, M. Goudie, S.P. Huang, F.J. Jenkins, and L.R. Ferguson, L. R. Assessment of factors associated with PSA level in prostate cancer cases and controls from three geographical regions, Scie. Reports. 12 (2022). https://doi.org/10.1038/s41598-021-04116-8
. R.S.L. Yii, J. Lim, S.Sothilingam, W.S. Yeoh, A.N.Fadzli, T.A. Ong, S. Kuppusamy, and A.H. Abdul Razack.Predictive factors of prostate cancer diagnosis with PSA 4.0–10.0 ng/ml in a multi-ethnic Asian population, Malaysia, Asian Jour. of Sur., 43(2020), pp. 87–94. https://doi.org/10.1016/j.asjsur.2019.02.014
. H. Wang, S. Tai, L. Zhang, and C. Liang. Integrated formulas to forecast prostate cancer: the parameters of influencing the prostate-specific antigen level as an adjunct to prostate-specific antigen and multi-parametric MRI to predict prostate cancer before biopsy.6(2017), Translational Cancer Research,1180–1187. https://doi.org/10.21037/tcr.2017.11.17
. U.C. Orumie and D.C. Bartholomew. Respiratory Syncytial Virus Infection in Infants: A comparative study using Discriminant, Probit and Logistic Regression Analysis”, Asian Journal of Probability and Statistics, 18(2022), 18-31.
. U.C. Orumie, D.C. Bartholomew, C.P. Obite and L.C. Kiwu. 2021). Likelihood of Insurance Coverage on Damages Due To Level of Insecurity In Nigeria: Logistic Modeling Approach, 7(2021), Financial Risk and Management Reviews, pp. 50-59.
. D.C. Bartholomew, E.O. Biu, and D. Enegesele. Impact of Maternal Education and Age on Weight of Child at Birth: Use of Multinomial Logistic Model, Asian Journal of Probability and Statistics, 18(2022), 46-59. Article no.AJPAS.88848
. C.C. Nwaigwe, A.C.OnyekaandS.N. Nwanneako. Comparison of Logit and Probit Models in the Analysis of Severity of Diabetes”, EC Diabetes and Metabolic Research, 4(2020), 1 – 11.
. G.U. Ugwuanyim, C.O. Osuchukwu, D.C. Bartholomew and C.P. Obite. Medical Choices for a Wealthy Nation – A Multinomial Logistic Regression Model, Asian Journal of Probability and Statistics, 6(2020),1-12. Article no.AJPAS.54245.
. C.M. Bishop. Pattern Recognition and Machine Learning, (2006) https://doi.org/10.1007/b9479810.1007/978-0-387-45528-0
. H.F. Yu and F.L. Huang (2011). Dual coordinate descent methods for logistic regression and maximum entropy models, Machine Learning. 85(2011), 41–75. doi:10.1007/s10994-010-5221-8.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 International Journal of Applied Sciences: Current and Future Research Trends
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who submit papers with this journal agree to the following terms.
