Ensemble Based Approach for Time Series Classification in Metabolomics.

Abstract

Machine learning is one important application in the area of health informatics, however classification methods for longitudinal data are still rare. The aim of this work is to analyze and classify differences in metabolite time series data between groups of individuals regarding their athletic activity. We propose a new ensemble-based 2-tier approach to classify metabolite time series data. The first tier uses polynomial fitting to generate a class prediction for each metabolite. An induced classifier (k-nearest-neighbor or naïve bayes) combines the results to produce a final prediction. Metabolite levels of 47 individuals undergoing a cycle ergometry test were measured using mass spectrometry. In accordance with our previous work the statistical results indicate strong changes over time. We found only small but systematic differences between the groups. However, our proposed stacking approach obtained a mean accuracy of 78% using 10-fold cross-validation. Our proposed classification approach allows a considerable classification performance for time series data with small differences between the groups.