A Neutrosophic Soft Set-Based Approach for Anemia Diagnosis: Managing Uncertainty in Medical Decision-Making

Fuzzy sets, introduced by Lotfi A. Zadeh in 1965, have been widely used to solve real world problems involving uncertainty and ambiguous situations. However, traditional fuzzy sets and interval-valued fuzzy sets are insufficient to fully capture uncertainty. To address this problem, intuitionistic fuzzy sets and neutrosophic sets have been proposed. Neutrosophic sets, especially neutrosophic soft sets, provide an effective framework for dealing with uncertain, conflicting, and incomplete information, especially in medical decision making. In this study, a model for the diagnosis of anemia is developed using the Neutrosophic Soft Set (NSS) method. The model scores female patients according to age groups (15-44, 45-59, 60+) and several hematological parameters such as hemoglobin level (Hb), hematocrit (Hct), mean corpuscular volume (MCV), serum iron level, ferritin, and total iron binding capacity (TIBC). A more robust and accurate decision-making process is created by assigning neutrosophic values to each parameter, including accuracy, uncertainty, and inaccuracy values. Data for the model were obtained from patients treated in the hematology clinic of a full-fledged hospital in Turkey. Smarandache stated that neutrosophic clusters have a superior ability to deal with uncertainty, inconsistency, and missing data. This approach offers significant advantages, especially in medical decision-making processes, where uncertainty and contradiction are intense. Maji's method, based on the theory of neutrosophic soft sets, has yielded effective results in increasing the accuracy and consistency of medical diagnoses. Used in the diagnosis of anemia and similar diseases, this approach is a valuable tool in the evaluation of uncertain data. This paper aims to provide a guide to the application of neutrosophic soft sets in medical decision-making. It also highlights the potential of these approaches to improve decision support systems in medical diagnostics and provides recommendations for future research.