Otimização multiobjetivo aplicada ao planejamento de dietas para portadores de diabetes

Abstract

Diabetes mellitus (DM) is a chronic disease characterized by lack or malabsorption of hormonal insulin. Its treatment includes, among other strategies, adopting a balanced diet low in glucose. In this sense, this work aims to automatically generate optimized diets for individuals with DM, focusing on minimizing critical nutrients such as carbohydrates and lipids. To address conflicting goals of reducing carbohydrates and limiting lipids, a multi-objective integer linear programming model has been developed. This model has demonstrated effectiveness in meeting specific nutritional needs of patients while maintaining a balance between reducing carbohydrates and incorporating foods with lower fat content. This approach provides a practical and viable solution in clinical dietetics and nutrition for diabetes management, ensuring dietary variety throughout the week.