Application of Statistical Analysis and Machine Learning Methods for Analysing Blood Metabolites
Name
Mihkel Ilisson
Abstract
In this research, blood metabolite data from 31 pediatric subjects were analysed using statistical and machine learning methods to find relations between metabolic profiles and clinically diagnosed conditions. The study revealed statistically significant metabolites for several clinical features, most prominently for epilepsy, where metabolites from some lipid subpathways were clearly overrepresented. Also, the applied machine learning methods produced models that could be used for screening purposes for early epilepsy discovery. The findings of this study can lead to a better mechanistic understanding of epilepsy, which in turn might improve the diagnosis and treatment of this severe condition.
Graduation Thesis language
English
Graduation Thesis type
Master - Conversion Master in IT
Supervisor(s)
Dmytro Fishman
Defence year
2021