Data Mining Techniques Applied to Hydrogen Lactose Breath Test

PLoS One. 2017 Jan 26;12(1):e0170385. doi: 10.1371/journal.pone.0170385. eCollection 2017.

Abstract

Objectives: Analyze a set of data of hydrogen breath tests by use of data mining tools. Identify new patterns of H2 production.

Methods: Hydrogen breath tests data sets as well as k-means clustering as the data mining technique to a dataset of 2571 patients.

Results: Six different patterns have been extracted upon analysis of the hydrogen breath test data. We have also shown the relevance of each of the samples taken throughout the test.

Conclusions: Analysis of the hydrogen breath test data sets using data mining techniques has identified new patterns of hydrogen generation upon lactose absorption. We can see the potential of application of data mining techniques to clinical data sets. These results offer promising data for future research on the relations between gut microbiota produced hydrogen and its link to clinical symptoms.

MeSH terms

  • Adolescent
  • Breath Tests / methods*
  • Child
  • Child, Preschool
  • Data Mining
  • Female
  • Gastrointestinal Microbiome*
  • Humans
  • Infant
  • Lactose Intolerance / diagnosis*
  • Male

Grants and funding

The authors want to thank the financial support given by the Spanish Ministry of Science and Technology project TIN2014-55894- C2-1-R. This work has also been funded by Junta de Andalucía's project TIC-7528. The authors want to thank technical support from System’s Department of Instituto Hispalense de Pediatria. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.