Predicting Dietary B12 Deficiency in Vegetarians Using Interpretable Models

Rojas Badilla, Felipe Cristian (2025) Predicting Dietary B12 Deficiency in Vegetarians Using Interpretable Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The health risks of vitamin B12 deficiency include anemia and neurological damage which primarily affect vegetarians due to their restricted access to B12 sources. The research develops an interpretable machine learning system which uses NHANES data to forecast B12 deficiency through dietary consumption and personal characteristics. The model analyzes vegetarian participants by applying SMOTE to handle class imbalance and Random Forest classification on B12 intake and demographic and nutritional characteristics. The research utilized SHAP and LIME interpretability tools to generate both general and specific explanations for each case. The study reveals essential nutrient-risk connections while showing how dietary-based predictive models can perform scalable non-invasive screenings. The method enables the early detection of vulnerable people while providing a clear nutritional public health tool.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Onwuegbuche, Faithful UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > QP Physiology > Nutrition R Medicine > RA Public aspects of medicine > RA0421 Public health. Hygiene. Preventive Medicine > Personal Health and Hygiene
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	24 Aug 2026 11:06
Last Modified:	24 Aug 2026 11:06
URI:	https://norma.ncirl.ie/id/eprint/9594

Actions (login required)

View Item