Machine Learning Model for Predicting Human Health Implications of Genetically Modified Foods

The safety of genetically modified foods (GMFs) remains a major public health and regulatory concern due to potential short- and long-term health implications. This study proposes a machine learning–based framework for predicting human health risks associated with genetically modified foods by leveraging artificial intelligence techniques. The system integrates genetic, proteomic, toxicological, and nutritional datasets to enable comprehensive risk assessment. Machine learning algorithms, including Random Forest, Support Vector Machines, and Gradient Boosting, were implemented to classify GM foods into low, moderate, and high health risk categories. Experimental results indicate that ensemble learning approaches outperform single-model methods, with Gradient Boosting achieving the highest predictive accuracy of approximately 94%, an F1-score of 0.93, and improved sensitivity to complex biological interactions. Feature importance analysis revealed that protein sequence similarity to known allergens, presence of toxic metabolites, and nutritional composition variations are the most significant predictors of potential health risks. The findings demonstrate that artificial intelligence can enhance the efficiency, accuracy, and interpretability of GM food safety assessments. The proposed framework provides a scalable decision-support tool for researchers and regulatory agencies, supporting evidence-based evaluation and continuous monitoring of genetically modified foods.