A Comprehensive Evaluation of the Efficacy and Limitations of Nutrition Software Using Machine Learning

Arias Velásquez R.; Dreyfus B.D.; Rosendo E.G. · Lecture Notes in Networks and Systems (2025) · DOI: 10.1007/978-3-031-96798-6_19

Resumen

Currently, non-communicable chronic diseases such as diabetes, cardiovascular diseases, and cancer are leading causes of death and disability worldwide, accounting for 70% of global deaths. Technological solutions offering recommendation and/or suggestion systems for diets or nutritional plans have played a significant role in reducing the prevalence of these diseases due to their increased usage in recent years. This study presents a systematic literature review (SLR) using the PICO and PRISMA search methodologies, focusing on the usage and precision of algorithms and classification methods in software for the automatic creation of diets and nutritional plans, and how these compare to conventional diet creation techniques. A total of 32 documents from the Scopus and IEEE databases were analyzed. The results indicate considerable progress in the field of image recognition and in the precision of classification methods in recent years, highlighting significant advancements in global studies aimed at improving population health. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Instituciones: Universidad Tecnológica del Perú