Differential Diagnosis of Crimean Congo Fever from Diseases with Almost Identical Symptoms Using Fuzzy Analytic Hierarchy Process

Abstract

Background: Accurate and timely diagnosis is vital, particularly when different diseases present with overlapping symptoms. Misdiagnosis or diagnostic delays can lead to severe consequences. Early differentiation based on clinical signs — prior to laboratory confirmation — plays a key role in guiding initial treatment decisions. Objectives: The present study proposes a fuzzy-based diagnostic support system aimed at improving early differential diagnosis and minimizing errors in cases where symptoms are shared across diseases. Methods: Three infectious diseases — Crimean-Congo hemorrhagic fever (CCHF), bacterial meningitis, and severe influenza — were selected due to their similar clinical presentations. Sixteen key symptoms were identified through medical literature and verified by an infectious disease specialist. The fuzzy analytic hierarchy process (FAHP), using Chang’s method, was employed to prioritize disease likelihood based on symptom weighting. Results: The FAHP model facilitated disease prioritization through a structured analysis of symptom weights. It enabled identification of the most likely diagnosis for hypothetical patient scenarios and demonstrated potential to support clinical decision-making. Conclusions: The proposed fuzzy-based system offers a structured and transparent approach to differential diagnosis in settings where diseases exhibit nearly identical symptoms. It may assist healthcare professionals in making faster and more informed decisions ahead of confirmatory testing.