One of the most important tasks of modern medicine is the timely and accurate assessment of the state of the body's defense systems at various levels of its functioning. However, due to the diversity, complexity and dynamism of the functioning of these body systems, there are significant difficulties in constructing appropriate analytical models, which complicates the use of modern information and intelligent technologies to improve the quality of decisions made about the state of the studied class of systems. The aim of the study is to develop methods for quantitative assessment of the protective functions of the antioxidant system and its use in forecasting and medical diagnostics to improve the quality of decisions made. Taking into account the structure of the data describing the state of the body's defense systems, the soft computing technology implemented using the methodology of synthesis of hybrid fuzzy decision rules was chosen as the basic mathematical apparatus. The characteristics of lipid peroxidation and antioxidant activity were chosen as indicators characterizing the state of the antioxidant system. Using these characteristics, a fuzzy model of the level of body protection by the antioxidant system was obtained in the work. The effectiveness of the resulting model was tested on the tasks of predicting recurrent myocardial infarction, assessing the degree of complications after kidney injury, and assessing the severity of endogenous intoxication of the body after nephrolithotripsy. During the statistical tests, it was shown that the use of the indicator of the level of protection of the body by the antioxidant system in the decision rules increases the quality of decisions made by 10–15%. The work was carried out within the framework of the implementation of the development program of the Federal State Budgetary Educational Institution of Higher Education "Southwestern State University" of the "Priority 2030" project.