Cross-Disease Breathomics by PTR-TOF-MS: Multiclass Machine Learning and Network Remodeling Across Asthma, COPD, Cystic Fibrosis, and Lymphangioleiomyomatosis
International Journal of Molecular Sciences · 2026
DOI: 10.3390/ijms27083483 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2026. Verfasst von Malika Mustafina und 16 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, Functional and Ultrasound Diagnostics, I.M. Sechenov First Moscow State Medical University (Sechenov University), 119048 Mo…. Hauptthemen laut MEDLINE: Lymphangioleiomyomatosis, Asthma, Volatile Organic Compounds, Cystic Fibrosis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Philipp Kopylov, Artemiy Silantyev, Russian Science Foundation.
Themen: Künstliche Intelligenz in der Pflege, COPD
Abstract (Originalsprache)
Chronic obstructive and inflammatory lung diseases share overlapping clinical manifestations and spirometric features, complicating differential diagnosis and monitoring. In this study, we performed an integrative real-time proton-transfer-reaction time-of-flight mass spectrometry (PTR-TOF-MS) breathomics analysis to assess whether exhaled volatile organic compound (VOC) profiles enable multiclass discrimination among bronchial asthma (BA), chronic obstructive pulmonary disease (COPD), cystic fibrosis (CF), and lymphangioleiomyomatosis (LAM), with healthy individuals as controls. Breath VOC data from 843 subjects were analyzed using a stratified 70/30 train/test split. An ensemble feature selection strategy based on gradient boosting (XGBoost with SMOTE within cross-validation) identified stable VOC panels (top 25% selection probability), yielding 29 VOCs and 31 features including clinical covariates. On the independent test set, the VOC-only model achieved a macro-averaged one-vs-one (OvO) AUC of 0.866 (95% CI 0.829–0.903), while the combined model improved to 0.888 (95% CI 0.853–0.919), indicating modest value of clinical variables. Pairwise analysis demonstrated highest discrimination for CF (AUC up to 0.988), whereas BA and LAM showed lower sensitivity (
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Cardiology, Functional and Ultrasound Diagnostics, I.M. Sechenov First Moscow State Medical University (Sechenov University), 119048 Moscow, Russia.
- Pulmonology Research Institute under the Federal Medical and Biological Agency of Russia, 115682 Moscow, Russia.
- Research Institute for Systemic Analysis of the Russian Academy of Sciences, 117218 Moscow, Russia.
- World-Class Research Center "Digital Biodesign and Personalized Healthcare", I.M. Sechenov First Moscow State Medical University (Sechenov University), 119048 Moscow, Russia.
- Federal State Autonomous Educational Institution of Higher Education, N.I. Pirogov Russian National Research Medical University, 1 Ostrovityanova str., Bldg. 6, 117513 Moscow, Russia.
- Pulmonology Department, I.M. Sechenov First Moscow State Medical University (Sechenov University), 119048 Moscow, Russia.
ORCID-Profile: Malika Mustafina, Aleksandr Suvorov, Marina Makarova, Alexander Chernyak, Olga Suvorova, Anna Shmidt, Aleksandra Bykova, Nana Gogiberidze, Andrei Akselrod, Abram Syrkin
Förderung
- Philipp Kopylov
- Artemiy Silantyev
- Russian Science Foundation
- government assignment
Zitieren
APA
Mustafina, M., Silantyev, A., Suvorov, A., Krasovskiy, S., Makarova, M., Chernyak, A., Suvorova, O., Shmidt, A., Gognieva, D., Bykova, A., Gogiberidze, N., Akselrod, A., Belevskiy, A., Avdeev, S., Betelin, V., Syrkin, A., & Kopylov, P. (2026). Cross-Disease Breathomics by PTR-TOF-MS: Multiclass Machine Learning and Network Remodeling Across Asthma, COPD, Cystic Fibrosis, and Lymphangioleiomyomatosis. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms27083483
Vancouver
Mustafina M, Silantyev A, Suvorov A, Krasovskiy S, Makarova M, Chernyak A, et al. Cross-Disease Breathomics by PTR-TOF-MS: Multiclass Machine Learning and Network Remodeling Across Asthma, COPD, Cystic Fibrosis, and Lymphangioleiomyomatosis. International Journal of Molecular Sciences. 2026. doi:10.3390/ijms27083483
BibTeX
@article{Mustafina2026,
author = {Mustafina, Malika and Silantyev, Artemiy and Suvorov, Aleksandr and Krasovskiy, Stanislav and Makarova, Marina and Chernyak, Alexander and Suvorova, Olga and Shmidt, Anna and Gognieva, Daria and Bykova, Aleksandra and Gogiberidze, Nana and Akselrod, Andrei and Belevskiy, Andrey and Avdeev, Sergey and Betelin, Vladimir and Syrkin, Abram and Kopylov, Philipp},
title = {Cross-Disease Breathomics by PTR-TOF-MS: Multiclass Machine Learning and Network Remodeling Across Asthma, COPD, Cystic Fibrosis, and Lymphangioleiomyomatosis},
journal = {International Journal of Molecular Sciences},
year = {2026},
doi = {10.3390/ijms27083483}
}
EUVIMED