Uyarlanabilir Sinirsel Bulanık Çıkarım Sistemini (ANFIS) Kullanarak Prostat Kanseri Tanısının Değerlendirilmesi: Tanısal Doğruluğun Karşılaştırmalı Analizi

Abstract

Bu çalışma, prostat kanseri teşhis sonuçlarını değerlendirmede Adaptive Neural Fuzzy Inference System’in (ANFIS) uygulamasını araştırmaktadır. Prostat kanseri, erken ve doğru tespitin etkili tedavi için kritik öneme sahip olduğu, küresel olarak erkekler arasında en yaygın kanserlerden biri olmaya devam etmektedir. İlerlemelere rağmen, prostat kanseri teşhisi klinik verilerdeki değişkenlik ve kesin yorumlama ihtiyacı nedeniyle doğası gereği karmaşıktır. Bu araştırmada, bulanık mantık ve sinir ağlarını entegre eden bir hibrit metodoloji olan ANFIS, bir klinik veri setini analiz etmek ve bir teşhis modeli geliştirmek için kullanılmıştır. ANFIS çerçevesi, belirsizlik ve doğrusal olmayan ilişkileri ele almada mükemmeldir ve bu da onu özellikle tıbbi teşhisler için uygun hale getirir. Modelin performansı, doğruluk, duyarlılık ve özgüllük dahil olmak üzere birden fazla değerlendirme metriği kullanılarak titizlikle değerlendirilmiştir. Sonuçlar, ANFIS’in yüksek teşhis doğruluğuna ulaştığını ve geleneksel yöntemlere kıyasla gereksiz biyopsileri %45,45 oranında önemli ölçüde azalttığını göstermektedir. Bu, klinik ortamlarda güvenilir bir karar destek aracı olarak potansiyelini vurgulamaktadır. ANFIS’ten yararlanarak, klinisyenler tanısal hassasiyeti artırabilir, kaynak tahsisini optimize edebilir ve hasta sonuçlarını iyileştirebilir. Çalışma, prostat kanseri yönetimini ilerletmede akıllı sistemlerin dönüştürücü rolünü vurgulamaktadır.

Keywords

• Bulanık mantık
• prostat kanser
• ANFIS

Evaluating Prostate Cancer Diagnosis Using the Adaptive Neural Fuzzy Inference System (ANFIS): A Comparative Analysis of Diagnostic Accuracy

Abstract

This study explores the application of the Adaptive Neural Fuzzy Inference System (ANFIS) in evaluating prostate cancer diagnosis outcomes. Prostate cancer remains one of the most prevalent cancers among men globally, where early and accurate detection is critical for effective treatment. Despite advancements, diagnosing prostate cancer is inherently complex due to the variability in clinical data and the need for precise interpretation. In this research, ANFIS—a hybrid methodology integrating fuzzy logic and neural networks—was employed to analyze a clinical dataset and develop a diagnostic model. The ANFIS framework excels in handling uncertainty and nonlinear relationships, making it particularly suited for medical diagnostics. The model’s performance was rigorously assessed using multiple evaluation metrics, including accuracy, sensitivity, and specificity. The results demonstrate that ANFIS achieves high diagnostic accuracy, significantly reducing unnecessary biopsies by 45.45% compared to traditional methods. This highlights its potential as a reliable decision-support tool in clinical settings. By leveraging ANFIS, clinicians can enhance diagnostic precision, optimize resource allocation, and improve patient outcomes. The study underscores the transformative role of intelligent systems in advancing prostate cancer management.

Keywords

• Fuzzy logic
• prostate cancer
• ANFIS

References

1. Zadeh LA. Fuzzy sets. Inf Control 1965; 8: 338–353.
2. Dalkılıç O, Demirtaş N. Algebraic operations of virtual fuzzy parameterized soft sets and their application in decision-making. Cumhuriyet Sci J 2021; 42(4): 878–889.
3. Zhang F, Ma W, Ma H. Dynamic chaotic multi-attribute group decision making under weighted T-spherical fuzzy soft rough sets. Symmetry 2023; 15(2): 307.
4. Gwak J, Garg H, Jan N. Hybrid integrated decision-making algorithm for clustering analysis based on a bipolar complex fuzzy and soft sets. Alex Eng J 2023; 67: 473–487.
5. Nawaz HS, Akram M. Granulation of protein–protein interaction networks in Pythagorean fuzzy soft environment. J Appl Math Comput 2023; 69(1): 293–320.
6. Akram M, Martino A. Multi-attribute group decision making based on T-spherical fuzzy soft rough average aggregation operators. Granul Comput 2023; 8(1): 171–207.
7. Khalil AM, Zahran AM, Basheer R. A novel diagnosis system for detection of kidney disease by a fuzzy soft decision-making problem. Math Comput Simul 2023; 203: 271–305.
8. Hu H, Xu J, Liu M, Lim MK. Vaccine supply chain management: An intelligent system utilizing blockchain, IoT and machine learning. J Bus Res 2023; 156: 113480.

9. Shimizu R, Saito Y, Matsutani M, Goto M. Fashion intelligence system: An outfit interpretation utilizing images and rich abstract tags. Expert Syst Appl 2023; 213: 119167.
10. Njoku JN, Nwakanma CI, Amaizu GC, Kim DS. Prospects and challenges of Metaverse application in data-driven intelligent transportation systems. IET Intell Transp Syst 2023; 17(1): 1–21.
11. Chesnokov AM. Pattern regions as a basis for logical inference in columns-based intelligent systems. J Pharm Negat Results 2023; 407–422.
12. Rabin MRI, Hussain A, Alipour MA, Hellendoorn VJ. Memorization and generalization in neural code intelligence models. Inf Softw Technol 2023; 153: 107066.
13. Olayode IO, Tartibu LK, Alex FJ. Comparative study analysis of ANFIS and ANFIS-GA models on flow of vehicles at road intersections. Appl Sci 2023; 13(2): 744.
14. Yu H, Dai Q. AE-DIL: A double incremental learning algorithm for non-stationary time series prediction via adaptive ensemble. Inf Sci 2023; 636: 118916.
15. Ahmed IE, Mehdi R, Mohamed EA. The role of artificial intelligence in developing a banking risk index: An application of adaptive neural network-based fuzzy inference system (ANFIS). Artif Intell Rev 2023; 1–23.
16. Zardkoohi M, Molaeezadeh SF. Long-term prediction of blood pressure time series using ANFIS system based on DKFCM clustering. Biomed Signal Process Control 2022; 74: 103480.
17. Salehi S. Employing a time series forecasting model for tourism demand using ANFIS. J Inf Organ Sci 2022; 46(1): 157–172.
18. Southwick PC, Catalona WJ, Partin AW, Slawin KM, Brawer MK, Flanigan RC, Loveland KG. Prediction of post-radical prostatectomy pathological outcome for stage T1c prostate cancer with percent free prostate specific antigen: A prospective multicenter clinical trial. J Urol 1999; 162(4): 1346–1351.
19. Van Cangh PJ, De Nayer P, Sauvage P, Tombal B, Elsen M, Lorge F, Wese FX. Free to total prostate-specific antigen (PSA) ratio is superior to total-PSA in differentiating benign prostate hypertrophy from prostate cancer. Prostate 1996; 29(S7): 30–34.
20. Egawa S, Soh S, Ohori M, Uchida T, Gohji K, Fujii A, Koshiba K. The ratio of free to total serum prostate specific antigen and its use in differential diagnosis of prostate carcinoma in Japan. Cancer 1997; 79(1): 90–98.
21. Perincheri S, Levi AW, Celli R, Gershkovich P, Rimm D, Morrow JS, Sinard J. An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy. Mod Pathol 2021; 34(8): 1588–1595.
22. Raciti P, Sue J, Ceballos R, Godrich R, Kunz JD, Kapur S, Fuchs TJ. Novel artificial intelligence system increases the detection of prostate cancer in whole slide images of core needle biopsies. Mod Pathol 2020; 33(10): 2058–2066.
23. Rouvière O, Souchon R, Lartizien C, Mansuy A, Magaud L, Colom M, Crouzet S. Detection of ISUP ≥ 2 prostate cancers using multiparametric MRI: Prospective multicentre assessment of the non-inferiority of an artificial intelligence system as compared to the PI-RADS V2.1 score (CHANGE study). BMJ Open 2022; 12(2): e051274.
24. Parwani AV. Commentary: Automated diagnosis and Gleason grading of prostate cancer – are artificial intelligence systems ready for prime time? J Pathol Inform 2019; 10.
25. Van Booven DJ, Kuchakulla M, Pai R, Frech FS, Ramasahayam R, Reddy P, Arora H. A systematic review of artificial intelligence in prostate cancer. Res Rep Urol 2021; 31–39.
26. Jang JS. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 1993; 23(3): 665–685.
27. Karaboga D, Kaya E. Training ANFIS using artificial bee colony algorithm for nonlinear dynamic systems identification. In: Proc 22nd Signal Process Commun Appl Conf (SIU). IEEE 2014; 493–496.
28. Jang JS, Sun CT. Neuro-fuzzy modeling and control. Proc IEEE 1995; 83(3): 378–406.
29. Cobbinah M, Abdulrahman UFI, Emmanuel AK. Adaptive neuro-fuzzy inferential approach for the diagnosis of prostate diseases. Int J Intell Syst Appl 2022; 14(1).
30. Zekri M. A review of medical image classification using adaptive neuro-fuzzy inference system (ANFIS). J Med Signals Sens 2012; 2(1): 49–60.
31. Haznedar B, Arslan MT, Kalinli A. Optimizing ANFIS using simulated annealing algorithm for classification of microarray gene expression cancer data. Med Biol Eng Comput 2021; 59: 497–509.
32. Ramana PV, Rosalina KM. Optimizing weak grid integrated wind energy systems using ANFIS-SRF controlled DSTATCOM. Sci Rep 2025; 15(1): 13662.
33. Awasthi D, Khare P, Srivastava VK. ANFISmark: ANFIS-based secure watermarking approach for telemedicine applications. Neural Comput Appl 2025; 37(14): 8677–8693.
34. Mirzaaghabeik H, Mashaan NS, Shukla SK. A predictive model for the shear capacity of ultra-high-performance concrete deep beams reinforced with fibers using a hybrid ANN-ANFIS algorithm. Appl Mech 2025; 6(2): 27.