Abstract—This study developed and validated an intelligent expert system based on machine learning and clinical rules to optimize nutritional care for patients in the San Martín region of Peru. The approach specifically addresses challenges posed by limited access to specialized dietary guidance. A dataset consisting of 615 patient records, each with 45 clinical, anthropometric, and lifestyle variables, was used to train and implement a hybrid architecture that combined unsupervised clustering (K-means) with a rule-based inference engine. The model achieved optimal segmentation into five nutritional profiles, supported by dimensionality reduction through Principal Component Analysis (PCA) and validated using the Silhouette (0.1229), Davies-Bouldin (1.3238), and Calinski-Harabasz (47.8740) indices. The expert system’s dietary recommendations showed a global concordance of 77% with those of the clinical nutritionists, achieving up to 83% accuracy in standard metabolic clusters. These results confirm the system’s ability to generate personalized and clinically coherent dietary plans, thereby improving the efficiency of nutritional services. Overall, the findings highlight the potential of intelligent systems to enhance healthcare delivery in resource-limited settings and pave the way for broader applications of AI in public health and clinical decision support.
 
Keywords—clinical support, clustering algorithms, dietary recommendation, digital public health, nutritional profiling


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).