Publication detail

Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors

SCHWARZEROVÁ, J. OLEŠOVÁ, D. ŠABATOVÁ, K. KVASNIČKA, A. KOŠTOVAL, A. FRIEDECKÝ, D. SEKORA, J. DLUHÁ, J. PROVAZNÍK, V. POPELINSKY, L. WECKWERTH, W.

Original Title

Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors

Type

journal article in Web of Science

Language

English

Original Abstract

Motivation The increasing use of big data and optimized prediction methods in metabolomics requires techniques aligned with biological assumptions to improve early symptom diagnosis. One major challenge in predictive data analysis is handling confounding factors—variables influencing predictions but not directly included in the analysis. Results Detecting and correcting confounding factors enhances prediction accuracy, reducing false negatives that contribute to diagnostic errors. This study reviews concept drift detection methods in metabolomic predictions and selects the most appropriate ones. We introduce a new implementation of concept drift analysis in predictive classifiers using metabolomics data. Known confounding factors were confirmed, validating our approach and aligning it with conventional methods. Additionally, we identified potential confounding factors that may influence biomarker analysis, which could introduce bias and impact model performance. Availability and implementation Based on biological assumptions supported by detected concept drift, these confounding factors were incorporated into correction of prediction algorithms to enhance their accuracy. The proposed methodology has been implemented in Semi-Automated Pipeline using Concept Drift Analysis for improving Metabolomic Predictions (SAPCDAMP), an open-source workflow available at https://github.com/JanaSchwarzerova/SAPCDAMP.

Keywords

Metabolomics, Concept drift analysis, Confounding factors, Predictive modeling, Enhanced classi-fiers

Authors

SCHWARZEROVÁ, J.; OLEŠOVÁ, D.; ŠABATOVÁ, K.; KVASNIČKA, A.; KOŠTOVAL, A.; FRIEDECKÝ, D.; SEKORA, J.; DLUHÁ, J.; PROVAZNÍK, V.; POPELINSKY, L.; WECKWERTH, W.

Released

4. 4. 2025

Publisher

Oxford Academic

Location

Oxford

ISBN

2635-0041

Periodical

Bioinformatics Advances

Year of study

5

Number

1

State

United Kingdom of Great Britain and Northern Ireland

Pages from

1

Pages to

12

Pages count

12

URL

https://academic.oup.com/bioinformaticsadvances/article/5/1/vbaf073/8106474

Full text in the Digital Library

http://hdl.handle.net/11012/251062

BibTex

@article{BUT197854,
  author="Jana {Schwarzerová} and Dominika {Olešová} and Kateřina {Šabatová} and Aleš {Kvasnička} and Aleš {Koštoval} and David {Friedecký} and Jiří {Sekora} and Jitka {Dluhá} and Valentýna {Provazník} and Lubos {Popelinsky} and Wolfram {Weckwerth}",
  title="Enhanced metabolomic predictions using concept drift analysis: identification and correction of confounding factors 
",
  journal="Bioinformatics Advances",
  year="2025",
  volume="5",
  number="1",
  pages="1--12",
  doi="10.1093/bioadv/vbaf073",
  issn="2635-0041",
  url="https://academic.oup.com/bioinformaticsadvances/article/5/1/vbaf073/8106474"
}