Institutional Repository of Vilnius University
Kūno masės indekso prognozavimas remiantis epigenetiniais žymenimis /
Abstract
dc:descriptionThis paper examines the challenges of predicting body mass index using DNA methylation data. A new BMI predictor is created based on ensemble machine learning principles. The study reviews the significance of genetic and epigenetic data in determining phenotype, with a particular focus on DNA methylation mechanisms. The effectiveness of the existing McCartney and EpiScore BMI predictors is evaluated. In the practical part of the work, an ensemble machine learning model is implemented. Predictions from the Elastic Net algorithm, external McCartney and EpiScore estimates, and patient demographic indicators are integrated into a second-level Random Forest ensemble. The ability of this ensemble method to improve the accuracy of BMI prediction across various datasets is evaluated.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kušlevič, Albert,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308336720&prefLang=en_US