<p>Hypertension is a public health problem that affects millions of people worldwide, bringing with it a significant increase in the risk of developing cardiovascular diseases. Despite advances in medical research, its diagnosis and management remain a challenge due to uncertainty in clinical decision-making. Traditional diagnostic methods often rely on rigorous criteria, which is one of the reasons they do not accurately reflect the variability in patients' health conditions. For this reason, fuzzy inference systems have emerged as an effective tool in managing imprecision and uncertainty in medical data. This study explores the application of fuzzy inference systems, particularly Interval Type-3 Fuzzy Systems, to improve the classification and diagnosis of blood pressure. To analyze the performance and response time, Mamdani and Sugeno fuzzy models are experimented with and compared. In addition, tests are also conducted with different types of membership functions to analyze their impact on the results. By integrating Interval Type-3 Fuzzy Systems into blood pressure evaluation, the aim is to provide a more flexible and interpretable approach to medical diagnosis. The experimental results demonstrate that both models provide excellent results in classification. However, Sugeno-type fuzzy systems are significantly faster in response time, which is important in real-world applications.</p>