Medical diagnosis is inherently complex, characterized by uncertainty, vagueness, and incomplete clinical data: symptom descriptions are vague, examination data is incomplete, disease manifestations are similar, and doctors often rely on imprecise verbal descriptions. Traditional binary logic struggles to handle this inherent ambiguity. Fuzzy set theory, proposed in 1965, allows elements to belong to a set with membership degrees between 0 and 1, making it ideal for simulating hierarchical and gradual reasoning processes in clinical practice. Fuzzy sets and systems provide a robust mathematical framework to model this ambiguity, enabling more accurate, flexible, and human-centric decision-making in healthcare. In recent years, the integration of fuzzy logic with emerging technologies—such as deep learning, cognitive computing, and big data analytics—has opened new frontiers in medical informatics. Fuzzy expert systems, reasoning systems, and hybrid models based on this theory have been successfully applied to the diagnosis of various diseases, including diabetes, heart disease, and COVID-19. In recent years, extended forms such as intuitionistic fuzzy sets, type 2 fuzzy sets, and image fuzzy sets have been developed to capture more complex fuzzy information such as hesitation and non-membership. Simultaneously, fuzzy logic is being combined with deep learning and medical image analysis to address high-dimensional medical data. Nevertheless, the field still faces challenges such as insufficient validation with real-world data, poor interpretability of fuzzy deep learning models, and difficulty in integrating them into routine clinical workflows.
This special issue, Fuzzy Sets and Systems in Medical Diagnosis, aims to address these challenges and present the latest research at the intersection of fuzzy logic and medical diagnosis. We invite original research articles, reviews, and methodological papers covering both theoretical developments and practical applications.
Topics of interest include (but are not limited to):
- Fuzzy inference and expert systems for disease detection
- Hybrid models combining fuzzy sets with machine learning or deep learning
- Advanced fuzzy set extensions (intuitionistic, picture, type‑2, neutrosophic, etc.) for diagnostic problems
- Fuzzy multi‑criteria decision‑making in clinical decision support
- Fuzzy similarity, distance, and entropy measures applied to medical data
- Fuzzy logic for biomedical signal processing (EEG, ECG, EMG) and medical image analysis (MRI, CT, X‑ray, ultrasound)
- Interpretable fuzzy AI and explainable diagnostic systems
- Real‑world case studies and clinical validation of fuzzy diagnostic tools
We welcome submissions addressing diagnosis of cardiovascular, neurological, metabolic, infectious, oncological, respiratory, and mental health disorders, among others.
By bringing together theoretical innovations and clinically relevant applications, this special issue aims to advance the development of accurate, interpretable, and reliable fuzzy diagnostic systems that can ultimately improve patient care.