Abstarct: Health data are associated with varying degrees of uncertainty and indistinct boundaries due to the overlap among different patient groups and the gradual nature of many mextabolic disorders. Therefore, crisp classification methods cannot always provide an accurate representation of transitional states and borderline patients. Identifying hidden health patterns and distinguishing different levels of mextabolic risk can play an important role in improving preventive and therapeutic decision-making. Accordingly, the present study was conducted to evaluate the capability of fuzzy clustering in identifying health groups and borderline patients. To this end, after preprocessing the clinical data, including normalization and outlier control, the optimal number of clusters was determined using validation indices, and the fuzzy clustering algorithm was implemented. Subsequently, by analyzing the membership matrix, the clinical profiles of the clusters were extracted and patients with mixed memberships were identified. The results indicate that four distinct clusters can be differentiated in terms of age, body mass index, blood pressure, blood glucose, and blood lipid levels. The mean systolic blood pressure across the clusters ranges from 118.4 to 146.2 mmHg, while the mean fasting blood glucose varies from 96.7 to 148.5 mg/dL, representing a spectrum from low-risk to high-risk mextabolic conditions. Furthermore, 78 patients (15.6% of the samples) were identified as borderline patients, with the highest degree of membership overlap observed between the second and third clusters. The mean difference between their two highest membership degrees was 0.12. Comparative results also indicate that the fuzzy approach is more effective than crisp methods in modeling transitional states and clinical uncertainties. Overall, the findings demonstrate that fuzzy clustering can realistically model the heterogeneity present in health data and provide a basis for more accurate patient classification and the design of targeted interventions within healthcare systems.