Type-2 Fuzzy Logic Systems for Robust Medical Diagnosis Under Deep Clinical Uncertainty: A Comparative Study with Type-1 Models
Keywords:
Clinical uncertainty, Fuzzy decision support systems, Medical diagnosis, Robustness analysis, Type-1 fuzzy systems, Type-2 fuzzy logicAbstract
Medical diagnosis as a problem of uncertainty is caused by subjectivity in the description of symptoms, noisy clinical measurements and non-uniformity in the interpretation by experts. The widely studied imprecision has traditionally been modelled using fuzzy logic systems, although conventional Type-1 fuzzy systems assume strictly defined membership functions, which do not accommodate high levels of uncertainty in clinical environments. The paper is indicative of a comparative analysis of Type-1 and Type-2 fuzzy logic framework in medical diagnostic decision support under the presence of profound clinical uncertainty in a systematic fashion. The two models use an integrated rule base with the aim that a clinically motivated diagnostic problem is formulated in a manner that both models are given a fair comparison. It has a Type-2 system, the representation of membership functions in the form of interval-valued representations directly involves uncertainty, providing an explicit representation of clinician disagreement and population heterogeneity. Massive experiments are performed on a carefully designed synthetic data that emulates diagnostic uncertainty within the real world, an example of which includes measurement randomness, missing data, and perturbations to membership. The results have shown that Type-2 fuzzy logic system is more sensitive, specific, and larger AUC than Type-1 counterpart when the uncertainty is larger. The findings have provided practical and theoretical evidence on the application of Type-2 fuzzy logic to provide sound medical diagnosis under deep and protracted uncertainty.
References
K. Jacob, “The challenge of medical diagnosis: A primer on principles, probability, process and pitfalls,” The National Medical Journal of India, vol. 28, no. 1, 2015.
J. Sooknanan and T. Seemungal, “Not so elementary – the reasoning behind a medical diagnosis,” MedEdPublish, vol. 8, no. 3, 2019.
P. Croskerry, S. G. Campbell, and D. A. Petrie, “The challenge of cognitive science for medical diagnosis,” Cognitive Research: Principles and Implications, vol. 8, no. 1, Feb. 2023.
G. Improta, V. Mazzella, D. Vecchione, S. Santini, and M. Triassi, “Fuzzy logic–based clinical decision support system for the evaluation of renal function in post‐Transplant Patients,” Journal of Evaluation in Clinical Practice, vol. 26, no. 4, pp. 1224–1234, Nov. 2019.
G. G. Devarajan, D. Arockiam, S. M. Nagarajan, and R. Agrawal, Healthcare 5.0 with Fuzzy Logic. Walter de Gruyter GmbH & Co KG, 2026.
E. Ontiveros-Robles, O. Castillo, and P. Melin, “Towards asymmetric uncertainty modeling in designing General Type-2 Fuzzy classifiers for medical diagnosis,” Expert Systems with Applications, vol. 183, p. 115370, Nov. 2021.
E. Ontiveros, P. Melin, and O. Castillo, “Comparative study of interval Type-2 and general Type-2 fuzzy systems in medical diagnosis,” Information Sciences, vol. 525, pp. 37–53, Jul. 2020.
I. Ullah, H. Y. Youn, and Y.-H. Han, “Integration of type-2 fuzzy logic and Dempster–Shafer Theory for accurate inference of IoT-based health-care system,” Future Generation Computer Systems, vol. 124, pp. 369–380, Nov. 2021.
J. B. Awotunde, O. Folorunsho, I. O. Mustapha, O. Olufunmilayo Olusanya, and M. B. Akanbi, “An Enhanced Internet of Things Enabled Type-2 Fuzzy Logic for Healthcare System Applications,” Studies in fuzziness and soft computing, vol. 425, pp. 133–151, Jan. 2023.
P. Nagaraj and P. Deepalakshmi, “An intelligent fuzzy inference rule‐based expert recommendation system for predictive diabetes diagnosis,” International Journal of Imaging Systems and Technology, Feb. 2022.
J. Cao et al., “Fuzzy Inference System with Interpretable Fuzzy Rules: Advancing Explainable Artificial Intelligence for Disease Diagnosis A Comprehensive Review,” Information Sciences, vol. 662, pp. 120212–120212, Jan. 2024.
U. Abubakar, M. L. Jibril, A. Musa Yola, M. Usman, and S. Ali Jijji, “A Fuzzy Expert System for Early Diagnosis of Diabetes Mellitus Using an Atkinson Index-Based Algorithm,” Science World Journal, vol. 20, no. 2, pp. 672–680, 2025.
A. K. Shukla, P. Mehra, and P. K. Muhuri, “Fuzzy Sets-Based Approaches for Improved Medical Diagnosis: An Analysis and Overview of Major Research Directions,” ACM Computing Surveys, Jul. 2025.
J. M. Mendel, Uncertain Rule-Based Fuzzy Systems. Cham: Springer International Publishing, 2017.
P. Melin and O. Castillo, “A review on type-2 fuzzy logic applications in clustering, classification and pattern recognition,” Applied Soft Computing, vol. 21, pp. 568–577, Aug. 2014.
K. Mittal, A. Jain, K. S. Vaisla, O. Castillo, and J. Kacprzyk, “A comprehensive review on type 2 fuzzy logic applications: Past, present and future,” Engineering Applications of Artificial Intelligence, vol. 95, p. 103916, Oct. 2020.
İ. Atacak, O. Çıtlak, and İ. Alper Doğru, “Application of interval type-2 fuzzy logic and type-1 fuzzy logic-based approaches to social networks for spam detection with combined feature capabilities,” PeerJ Computer Science, vol. 9, pp. e1316–e1316, Apr. 2023.
E. Bernal, M. L. Lagunes, O. Castillo, J. Soria, and F. Valdez, “Optimization of Type-2 Fuzzy Logic Controller Design Using the GSO and FA Algorithms,” International Journal of Fuzzy Systems, vol. 23, no. 1, Nov. 2020.
N. M. Yahya, N. Elias, and M. H. M. Nordin, “A Comparison of Type 1 and Type 2 Fuzzy Logic Controller for DC Motor System,” Lecture Notes in Electrical Engineering, vol. 900, pp. 125–133, 2022.
A. Mashhadany, S. Jassam, and E. H. Yahia, “Design and Simulation of Modified Type-2 Fuzzy Logic Controller for Power System,” International Journal of Electrical and Electronics Research, vol. 10, no. 3, pp. 731–736, Sep. 2022.
