Modelling and Classification of GC/IMS Breath Gas Measurements for Lozenges of Different Flavours

  • Claudia WigmannEmail author
  • Laura Lange
  • Wolfgang Vautz
  • Katja Ickstadt
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


The composition of exhaled breath contains information about diet, oral hygiene and other environmental influences as well as on the state of health and on medications. Therefore, rapid and sensitive breath analysis would be a helpful tool, for example, for medical diagnosis or therapy control. Ion mobility spectrometry coupled with gas-chromatographic pre-separation (GC/IMS) meet those requirements and can be used to distinguish between healthy and diseased persons or to detect drug usage, for example, based on characteristic exhaled metabolites. So far, the detection of peaks in IMS measurements and the assignment of compounds is done manually and an automated procedure is urgently needed. In this article, we analyse breath gas measurements by GC/IMS from a volunteer having consumed lozenges of 12 different flavours. The IMS measurements are modelled along drift time with an additive model of unimodal regressions to describe each peak. The regressions are afterwards combined across all spectra and all datasets to determine typical peak locations and the respective heights of the peaks in each measurement are inferred. The obtained matrix of peak intensities is then used to classify the measurements into the 12 flavour groups using support vector machines. Since the true class labels are known, we can assess the mis-classification rate using cross-validation.



The financial support of the Bundesministerium für Bildung und Forschung and the Ministerium für Innovation, Wissenschaft und Forschung des Landes Nordrhein-Westfalen is gratefully acknowledged. This work has also been supported by Deutsche Forschungsgemeinschaft (DFG) within the Collaborative Research Center SFB 876 ‘Providing Information by Resource-Constrained Analysis’, Project C4.


  1. Bergen, I., Liedtke, S., Güssgen, S., Kayser, O., Hariharan, C., Drees, C., et al. (2018). Calibration of complex mixtures in one sweep. International Journal for Ion Mobility Spectrometry, 21(3), 55–64.CrossRefGoogle Scholar
  2. Bischl, B., Lang, M., Kotthoff, L., Schiffner, J., Richter, J., Studerus, E., et al. (2016). mlr: Machine learning in R. Journal of Machine Learning Research, 17(170), 1–5.MathSciNetzbMATHGoogle Scholar
  3. Bödeker, B., & Baumbach, J. I. (2009). Analytical description of IMS-signals. International Journal for Ion Mobility Spectrometry, 12(3), 103–108.CrossRefGoogle Scholar
  4. Bödeker, B., Vautz, W., & Baumbach, J. I. (2008). Peak finding and referencing in MCC/IMS-data. International Journal for Ion Mobility Spectrometry, 11(1–4), 83–87.CrossRefGoogle Scholar
  5. Bunkowski, A. (2012). MCC-IMS data analysis using automated spectra processing and explorative visualisation methods. Ph.D. thesis, Bielefeld University.Google Scholar
  6. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.zbMATHGoogle Scholar
  7. Eiceman, G., & Karpas, Z. (2005). Ion mobility spectrometry (2nd ed.). London: CRC Press.CrossRefGoogle Scholar
  8. Eilers, P. H. C., & Marx, B. D. (1996). Flexible smoothing with B-splines and penalties. Statistical Science, 11(2), 89–121.MathSciNetCrossRefGoogle Scholar
  9. Handa, H., Usuba, A., Maddula, S., Baumbach, J. I., Mineshita, M., & Miyazawa, T. (2014). Exhaled breath analysis for lung cancer detection using ion mobility spectrometry. PLoS ONE, 9(12), e114555.CrossRefGoogle Scholar
  10. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.)., Springer series in statistics. Berlin: Springer.Google Scholar
  11. Hauschild, A. C., Kopczynski, D., D’Addario, M., Baumbach, J. I., Rahmann, S., & Baumbach, J. (2013). Peak detection method evaluation for ion mobility spectrometry by using machine learning approaches. Metabolites, 3, 277–293.CrossRefGoogle Scholar
  12. Horsch, S., Kopczynski, D., Baumbach, J.I., Rahnenführer, J., & Rahmann, S. (2015). From raw ion mobility measurements to disease classification: A comparison of analysis processes. PeerJ PrePrints 3, e1294v1.Google Scholar
  13. Horsch, S., Kopczynski, D., Kuthe, E., Baumbach, J. I., Rahmann, S., & Rahnenführer, J. (2017). A detailed comparison of analysis processes for mcc-ims data in disease classification - automated methods can replace manual peak annotations. PLOS ONE, 12(9), 1–16.CrossRefGoogle Scholar
  14. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning—with applications in R (1st ed.). New York: Springer.CrossRefGoogle Scholar
  15. Karatzoglou, A., Smola, A., Hornik, K., & Zeileis, A. (2004). kernlab—an S4 package for kernel methods in R. Journal of Statistical Software, 11(9), 1–20.CrossRefGoogle Scholar
  16. Köllmann, C. (2016a). Unimodal spline regression and its use in various applications with single or multiple modes. Ph.D. thesis, TU Dortmund.
  17. Köllmann, C. (2016b). uniReg: Unimodal penalized spline regression using B-splines. R package version 1.1
  18. Köllmann, C., Bornkamp, B., & Ickstadt, K. (2014). Unimodal regression using Bernstein-Schoenberg-splines and penalties. Biometrics, 70, 783–793.MathSciNetCrossRefGoogle Scholar
  19. Kopczynski, D., & Rahmann, S. (2015). An online peak extraction algorithm for ion mobility spectrometry data. Algorithms for Molecular Biology, 10, 17.CrossRefGoogle Scholar
  20. Lange, L. (2015). Analyse von GC/IMS-Atemluftmessungen unter Berücksichtigung verschiedener Atemerfrischer. Master’s thesis, Faculty of Statistics, TU Dortmund University.Google Scholar
  21. Purkhart, R., Hillmann, A., Graupner, R., & Becher, G. (2012). Detection of characteristic clusters in IMS-spectrograms of exhaled air polluted with environmental contaminants. International Journal for Ion Mobility Spectrometry, 15(2), 1–6.CrossRefGoogle Scholar
  22. R Core Team. (2018). R: A language and environment for statistical computing. R foundation for statistical computing, Vienna, Austria.
  23. Vautz, W., & Baumbach, J. I. (2008). Exemplar application of multi-capillary column ion mobility spectrometry for biological and medical purpose. International Journal for Ion Mobility Spectrometry, 11, 35–41.CrossRefGoogle Scholar
  24. Vautz, W., Baumbach, J. I., & Westhoff, M. (2009a). An implementable approach to obtain reproducible reduced ion mobility. International Journal for Ion Mobility Spectrometry, 12, 47–57.CrossRefGoogle Scholar
  25. Vautz, W., Nolte, J., Fobbe, R., & Baumbach, J. I. (2009b). Breath analysis-performance and potential of ion mobility spectrometry. Journal of Breath Research, 3(3), 036004.CrossRefGoogle Scholar
  26. Vautz, W., Franzke, J., Zampolli, S., Elmi, I., & Liedtke, S. (2018a). On the potential of ion mobility spectrometry coupled to GC pre-separation—a tutorial. Analytica Chimica Acta, 1024, 52–64.CrossRefGoogle Scholar
  27. Vautz, W., Liedtke, S., Martin, B., & Drees, C. (2018b). Data interpretation in GC-ion mobility spectrometry: Pecunia non olet? International Journal for Ion Mobility Spectrometry, 21(3), 97–103.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Claudia Wigmann
    • 1
    Email author
  • Laura Lange
    • 2
  • Wolfgang Vautz
    • 3
    • 4
  • Katja Ickstadt
    • 5
  1. 1.IUF – Leibniz-Institut für umweltmedizinische Forschung gGmbHDüsseldorfGermany
  2. 2.OptiMedis AGHamburgGermany
  3. 3.ION-GAS GmbHDortmundGermany
  4. 4.Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V.DortmundGermany
  5. 5.Faculty of StatisticsTU Dortmund UniversityDortmundGermany

Personalised recommendations