Aggregation of Multimodal ICE-MS Data into Joint Classifier Increases Quality of Brain Cancer Tissue Classification

Anatoly A. Sorokin, Denis S. Bormotov, Denis S. Zavorotnyuk, Vasily A. Eliferov, Konstantin V. Bocharov, Stanislav I. Pekov (), Evgeny N. Nikolaev () and Igor A. Popov ()
Additional contact information
Anatoly A. Sorokin: The Moscow Institute of Physics and Technology, National Research University, 141701 Dolgoprudny, Russia
Denis S. Bormotov: The Moscow Institute of Physics and Technology, National Research University, 141701 Dolgoprudny, Russia
Denis S. Zavorotnyuk: The Moscow Institute of Physics and Technology, National Research University, 141701 Dolgoprudny, Russia
Vasily A. Eliferov: The Moscow Institute of Physics and Technology, National Research University, 141701 Dolgoprudny, Russia
Konstantin V. Bocharov: V. L. Talrose Institute for Energy Problems of Chemical Physics, N. N. Semenov Federal Research Center for Chemical Physics Russian Academy of Science, 119334 Moscow, Russia
Stanislav I. Pekov: Skolkovo Institute of Science and Technology, 121205 Moscow, Russia
Evgeny N. Nikolaev: Skolkovo Institute of Science and Technology, 121205 Moscow, Russia
Igor A. Popov: The Moscow Institute of Physics and Technology, National Research University, 141701 Dolgoprudny, Russia

Data, 2022, vol. 8, issue 1, 1-8

Abstract: Mass spectrometry fingerprinting combined with multidimensional data analysis has been proposed in surgery to determine if a biopsy sample is a tumor. In the specific case of brain tumors, it is complicated to obtain control samples, leading to model overfitting due to unbalanced sample cohorts. Usually, classifiers are trained using a single measurement regime, most notably single ion polarity, but mass range and spectral resolution could also be varied. It is known that lipid groups differ significantly in their ability to produce positive or negative ions; hence, using only one polarity significantly restricts the chemical space available for sample discrimination purposes. In this work, we have developed an approach employing mass spectrometry data obtained by eight different regimes of measurement simultaneously. Regime-specific classifiers are trained, then a mixture of experts techniques based on voting or mean probability is used to aggregate predictions of all trained classifiers and assign a class to the whole sample. The aggregated classifiers have shown a much better performance than any of the single-regime classifiers and help significantly reduce the effect of an unbalanced dataset without any augmentation.

Keywords: mass spectrometry; ensemble learners; mixture of experts; brain tumor; ambient ionization; inline cartridge extraction (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/8/1/8/pdf (application/pdf)
https://www.mdpi.com/2306-5729/8/1/8/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:8:y:2022:i:1:p:8-:d:1016335

Access Statistics for this article

Data is currently edited by Ms. Cecilia Yang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().