Machine learning reveals microbiome differences by periodontitis severity
PLOS One · 21.05.2026 · 21 (5) · e0349686
DOI: 10.1371/journal.pone.0349686 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 21.05.2026. Verfasst von Soo Hyun Seo und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea. Hauptthemen laut MEDLINE: Microbiota, Machine Learning, Periodontitis. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Accugene Inc., Korea Health Industry Development Institute.
Abstract (Originalsprache)
Periodontitis is a chronic inflammatory disease driven by microbial dysbiosis, yet the microbial signatures associated with severity remain incompletely understood. This study investigated changes in subgingival microbial composition across clinically defined severity groups and evaluated the performance of microbiome-based machine-learning models for classifying periodontitis severity. Subgingival plaque samples from 84 patients were analyzed using 16S rRNA gene sequencing. Microbial diversity showed a modest decreasing trend with increasing severity, although differences were not statistically significant. Five machine learning models were applied to classify periodontitis. Random Forest and XGBoost achieved AUC values of 0.98, indicating statistically significant classification performance (p < 0.05) after feature selection. Validation using three external cohorts demonstrated substantial performance variability across populations, reflecting differences in oral microbiome composition, sample type, and periodontal status definitions. Feature importance analysis identified Fusobacterium , Campylobacter , Stomatobaculum , Leptotrichia and Segatella as key contributors to periodontitis severity classification, consistent with their established roles in periodontal dysbiosis. These findings highlight the potential of microbiome-based models for classifying periodontitis severity while underscoring the need to incorporate diverse populations and robust feature-selection strategies to enhance generalizability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Laboratory Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
- Department of Laboratory Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
- Department of Genomic Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
- Accugene Inc., Incheon, Republic of Korea.
- Department of Periodontology, Section of Dentistry, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
- Department of Periodontology, Korea University Anam Hospital, Seoul, Republic of Korea.
ORCID-Profile: Soo Hyun Seo, Jin-Sil Hong, Kyoung Un Park
Förderung
- National Research Foundation of Korea
- Accugene Inc.
- Korea Health Industry Development Institute
Zitieren
APA
Seo, S. H., Lee, J. W., Oh, S., Hong, J. S., Lee, B. S., Kwon, S. J., Kim, K. S., Park, J. S., Heo, J. S., Ahn, K. H., Lee, H. J., & Park, K. U. (2026). Machine learning reveals microbiome differences by periodontitis severity. PLOS One, 21(5), e0349686. https://doi.org/10.1371/journal.pone.0349686
Vancouver
Seo SH, Lee JW, Oh S, Hong JS, Lee BS, Kwon SJ, et al. Machine learning reveals microbiome differences by periodontitis severity. PLOS One. 2026;21(5):e0349686. doi:10.1371/journal.pone.0349686
BibTeX
@article{Seo2026,
author = {Seo, Soo Hyun and Lee, Jae Won and Oh, Sujin and Hong, Jin-Sil and Lee, Ban Seok and Kwon, Sun Jae and Kim, Keun-Suh and Park, Jung Soo and Heo, Ju Sun and Ahn, Ki Hoon and Lee, Hyo-Jung and Park, Kyoung Un},
title = {Machine learning reveals microbiome differences by periodontitis severity},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {5},
pages = {e0349686},
doi = {10.1371/journal.pone.0349686}
}
EUVIMED