Epigenomic studies, such as those that use DNA methylation (DNAm) data, make use of ML techniques to process extremely high-dimensional data obtained from high-throughput platforms. Such datasets suffer from the curse of dimensionality, increased computational complexity and are prone to overfitting. As such, feature reduction techniques become important considerations. The research evaluates the application of ML supervised prediction algorithms and feature reduction, using robust data-driven practices and methodologies, for the development of novel DNAm-based models of health and disease, specifically the DNAm-based prediction tasks of telomere length estimation, oesophageal cancer classification and inflammatory bowel disease course, subtype and activity prediction.