Improving Prostate Cancer Risk Diagnosis Using a Modified Fuzzy Medical Expert System Based on Mamdani Logic
DOI:
https://doi.org/10.22399/ijcesen.3110Keywords:
Expert System, Fuzzy, Mamdani, Prostate Cancer, Medical DiagnosisAbstract
Timely identification of prostate cancer significantly enhances the likelihood of successful treatment; however, diagnostic uncertainty remains a common challenge. This study introduces a Fuzzy Medical Expert System (F-MES) based on Mamdani inference, aiming to improve the accuracy of risk estimation for prostate cancer. The system incorporates four clinically validated input parameters: patient age, prostate-specific antigen (PSA), prostate volume (PV), and the percentage of free PSA (%FPSA) to produce a quantitative output representing Prostate Cancer Risk (PCR) in percentage. Designed for use in clinical environments such as hospitals and urology clinics, the F-MES provides risk interpretation and biopsy recommendations aligned with medical guidelines. A total of 500 fuzzy rules, adapted from standard clinical criteria, were implemented on this system within the Mamdani framework. We have implemented the FMES by using MATLAB and had several intensive numerical experiments, based on an evaluation of 90 benchmark patient records. We also compared the results to those of the previous research. It is shown that the FMES has a better performance that the other previous approach. It gives an accuracy of 81.11%, surpassing previous fuzzy models, which ranged from 60% to 77.5%. Performance metrics indicate a precision of 76.47%, recall of 88.64%, specificity of 73.91%, and an F1-score of 82.11%.,
References
[1] M. F. Leitzmann and S. Rohrmann, (2012). Risk factors for the onset of prostatic cancer: Age, location, and behavioral correlates, Clin. Epidemiol., vol. 4(1), 1–11, doi: 10.2147/CLEP.S16747.
[2] R. L. Siegel, K. D. Miller, H. E. Fuchs, and A. Jemal, (2022). Cancer Statistic, CA Cancer J Clin, vol. 72(1), 7–33, doi: 10.3322/caac.21708.
[3] O. S. Tătaru et al., (2021). Artificial intelligence and machine learning in prostate cancer patient management—current trends and future perspectives, doi: 10.3390/diagnostics11020354.
[4] Abdillah, S. Syaharuddin, V. Mandailina, and S. Mehmood, (2024). The Role of Mathematics in Machine Learning for Disease Prediction: An In-Depth Review in the Healthcare Domain, Adv. Sustain. Sci. Eng. Technol., vol. 6,(4), 02404010, doi: 10.26877/asset.v6i4.845.
[5] G. K. Thakur, A. Thakur, S. Kulkarni, N. Khan, and S. Khan, (2024). Deep Learning Approaches for Medical Image Analysis and Diagnosis, Cureus, vol. 16(5), doi: 10.7759/cureus.59507.
[6] J. Mahanta and S. Panda, (2020). Fuzzy Expert System for Prediction of Prostate Cancer, New Math. Nat. Comput., vol. 16(1), 163–176, doi: 10.1142/S1793005720500106.
[7] M. Rawat, P. Pathak, and P. Vats, (2024). An approach to diagnosis of prostate cancer using fuzzy logic, Int. J. Reconfigurable Embed. Syst., vol. 13(1), 192–200, doi: 10.11591/ijres.v13.i1.pp192-200.
[8] L. Wynants et al., (2020). Prediction models for diagnosis and prognosis of covid-19: Systematic review and critical appraisal, BMJ, vol. 369, doi: 10.1136/bmj.m1328.
[9] S. Loeb et al., (2013). Systematic review of complications of prostate biopsy, Eur. Urol., vol. 64(6), 876–892, doi: 10.1016/j.eururo.2013.05.049.
[10] Van den B. N. Mottet et al., (2019). EAU - EANM - ESTRO - ESUR - SIOG Guidelines on Prostate Cancer 2019, Eur. Assoc. Urol. Guidel. 2019, vol. 53, 1–161, [Online]. https://uroweb.org/guideline/prostate-cancer
[11] A. Heidenreich et al., (2014). EAU guidelines on prostate cancer. Part 1: Screening, diagnosis, and local treatment with curative intent - Update 2013, Eur. Urol., vol. 65(1), 124–137, doi: 10.1016/j.eururo.2013.09.046.
[12] G. Improta, V. Mazzella, D. Vecchione, S. Santini, and M. Triassi, (2020). Fuzzy logic–based clinical decision support system for the evaluation of renal function in post-Transplant Patients, J. Eval. Clin. Pract., vol. 26(4), 1224–1234, doi: 10.1111/jep.13302.
[13] Q. Sun, A. Akman, and B. W. Schuller, (2024). Explainable Artificial Intelligence for Medical Applications : A Review, Proc. ACM Meas. Anal. Comput. Syst., vol. 37(4).
[14] M. Abdar et al., A Review of Uncertainty Quantification in Deep Learning : Techniques , Applications and Challenges.
[15] I. Saritas, N. Allahverdi, and I. U. Sert, (2003). A fuzzy expert system design for diagnosis of prostate cancer, no. January, 345–351, doi: 10.1145/973620.973677.
[16] Y. Gong, G. Liu, Y. Xue, R. Li, and L. Meng, (2023). A survey on dataset quality in machine learning, Inf. Softw. Technol., vol. 162(September 2022), 107268, doi: 10.1016/j.infsof.2023.107268.
[17] I. T. R. Yanto, A. Apriani, R. Wahyudi, C. Waishiang, Suprihatin, and R. Hidayat, (2024). Fuzzy Soft Set Clustering for Categorical Data, Int. J. Informatics Vis., vol. 8(1), 542–547, doi: 10.62527/joiv.8.1.2364.
[18] Y. F. Hernández-Julio, M. J. Prieto-Guevara, W. Nieto-Bernal, I. Meriño-Fuentes, and A. Guerrero-Avendaño, (2019). Framework for the development of data-driven mamdani-type fuzzy clinical decision support systems, Diagnostics, vol. 9(2), doi: 10.3390/diagnostics9020052.
[19] A. Dyussenbayev, (2017). Age Periods of Human Life, Adv. Soc. Sci. Res. J., vol. 4(6), 258–263, doi: 10.14738/assrj.46.2924.
[20] M. K. Favid and S. W. Leslie, (2022). Prostate specific antigen, Aust. Fam. Physician, vol. 40(10), 755.
[21] J. F. Tyloch and A. P. Wieczorek, (2017). Standardy badania ultrasonograficznego gruczołu krokowego. Część 2, J. Ultrason., vol. 17(68), 43–58, doi: 10.15557/jou.2017.0007.
[22] A. Bezinque, A. Moriarity, C. Farrell, H. Peabody, S. L. Noyes, and B. R. Lane, (2018). Determination of Prostate Volume: A Comparison of Contemporary Methods, Acad. Radiol., vol. 25(12), 1582–1587, doi: 10.1016/j.acra.2018.03.014.
[23] S. Aprikian et al., (2019). Improving ultrasound-based prostate volume estimation, BMC Urol., vol. 19(1), 68, doi: 10.1186/s12894-019-0492-2.
[24] Y. Huang, Z. Z. Li, Y. L. Huang, H. J. Song, and Y. J. Wang, (2018). Value of free/total prostate-specific antigen (f/t PSA) ratios for prostate cancer detection in patients with total serum prostate-specific antigen between 4 and 10 ng/mL, Med. (United States), vol. 97(13), doi: 10.1097/MD.0000000000010249.
[25] M. Perera et al., (2020). PSA-based machine learning model improves prostate cancer risk stratification in a screening population, World J. Urol., doi: 10.1007/s00345-020-03392-9.
[26] J. T. Wei et al., (2023). Early Detection of Prostate Cancer: AUA/SUO Guideline Part I: Prostate Cancer Screening, J. Urol., vol. 210(1), 46–53, doi: 10.1097/JU.0000000000003491.
[27] S. K. Dewi and H. Purnomo, (2010). Aplikasi Logika Fuzzy untuk Pendukung Keputusan, Kedua., vol. Kedua. Yogyakarta: Graha Ilmu.
[28] A. M. Alqudah, (2017). Fuzzy expert system for coronary heart disease diagnosis in Jordan, Health Technol. (Berl)., vol. 7(2–3), 215–222, doi: 10.1007/s12553-017-0178-2.
[29] B. M. Gayathri and C. P. Sumathi, (2016). Mamdani fuzzy inference system for breast cancer risk detection, 2015 IEEE Int. Conf. Comput. Intell. Comput. Res. ICCIC 2015, doi: 10.1109/ICCIC.2015.7435670.
[30] K. S. Gilda and S. L. Satarkar, (2020). Analytical overview of defuzzification methods, Int. J. Adv. Res. Ideas Innov. Technol., vol. 6(2), 359–365, [Online]. www.IJARIIT.com
[31] H. Ouifak and A. Idri, (2023). On the performance and interpretability of Mamdani and Takagi-Sugeno-Kang based neuro-fuzzy systems for medical diagnosis, Sci. African, vol. 20(April, 2023), doi: 10.1016/j.sciaf.2023.e01610.
[32] J. F. Lima, A. Patiño-León, M. Orellana, and J. L. Zambrano-Martinez, (2025). Evaluating the Impact of Membership Functions and Defuzzification Methods in a Fuzzy System: Case of Air Quality Levels, Appl. Sci., vol. 15(4), 1–16, doi: 10.3390/app15041934.
[33] A. K. Mallick and A. Das, (2021). An Analytical Survey of Defuzzification Techniques, in 2021 IEEE 4th International Conference on Computing, Power and Communication Technologies, GUCON 2021, doi: 10.1109/GUCON50781.2021.9573993.
[34] I. Saritas, N. Allahverdi, and U. Sert, (2013). Multi-phase semicrystalline microstructures drive exciton dissociation in neat plastic semiconductors, J. Mater. Chem. C, 3;10715–10722, 2013, doi: 10.1039/b000000x.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
