Published Paper Details:

This project focuses on developing a machine learning framework to offer personalized spinach intake recommendations for cancer patients. Spinach, a very nutritious food, is an important component in the diet of cancer patients. Nevertheless, it is necessary to take into account the peculiar condition of every patient when to establish the best consumption. For this purpose we make use of K-Means Clustering to partition the patients according to health predictors such as body mass index (BMI), cancer type and metabolic rate. Grouping patients with similar profiles, we develop clusters that characterize shared dietary needs and treatment responses. After these clusters are defined, Gaussian Mixture Models (GMMs) are used to provide personalized spinach consumption recommendations. The GMMs offer a probabilistic solution to dietary recommendations, taking into account individual variability among the clusters. This guarantee that the intake query applied to each patient is specific, sensitive and personalized to their unique physiological requirement, nutritional deficiencies and treatment-related issue. By selecting those variables, the system can be geared to maximize the antioxidant, vitamin, and mineral content of spinach, a vegetable that has been associated with improvement in cancer treatment outcomes. This machine learning-based strategy improves the personalization of nutrition in cancer management by using patient health information to deliver targeted dietary guidance (that is, personalized dietary guidance). Combined with K-Means Clustering and GMMs, the project can not only enhance dietary recommendation accuracy, but also make contribution to the rapidly developing personalized nutrition. In conclusion, this framework seeks to assist cancer patients by tailoring their nutrition, improving health outcomes and quality of life during treatment.