Background: Iron Deficiency Anemia (IDA) is one of the most prevalent nutritional disorders globally and a leading cause of Disability Adjusted Life Years (DALYs). Conventional diagnostic methods fail to detect deficiencies at an early stage and rarely account for individual genetic5 predisposition. Methods: This study proposes an end-to-end AI-driven precision nutrition pipeline integrating public Genome-Wide Association Study (GWAS) data and NHANES phenotypic data encompassing demographics, dietary intake, anthropometrics, and hematology. A synthetic genotype matrix was simulated for 400 GWAS-filtered SNPs using Hardy-Weinberg Equilibrium. Data preprocessing included missing value imputation, feature engineering, and SMOTE class balancing. Four machine learning models namely, Logistic Regression, Random Forest, Artificial Neural Network (ANN), and XGBoost were implemented and evaluated for both IDA classification and haemoglobin regression tasks. Results: XGBoost achieved state-of-the-art performance with ROC-AUC = 0.9981 for classification and R2 = 0.9903 for haemoglobin prediction. Polygenic Risk Score (PRS) stratification classified participants into low (73%), moderate (18%), and high (9%) risk tiers. Pathway burden analysis identified the Hepcidin Regulation pathway as the highest burden pathway in high-risk individuals. Conclusion: The integration of genomics, machine learning, and nutritional science through a Pathway-Burden Precision Nutrition Engine produced gene-specific, evidence-graded dietary recommendations, demonstrating significant potential for early and personalised IDA prevention.