Machine learning‐assisted prediction of clinical responses to periodontal treatment
Journal of Periodontology · 2025-11 · 96 (11) · 1199-1212
DOI: 10.1002/jper.24-0737 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Periodontology, online erschienen am 20.04.2025. Verfasst von Balazs Feher und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral Medicine, Infection, and Immunity, Harvard School of Dental Medicine, Boston, Massachusetts, USA. Hauptthemen laut MEDLINE: Machine Learning, Periodontitis. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação de Amparo à Pesquisa do Estado de São Paulo, NCRR NIH HHS, NIH | National Institute of Dental and Craniofacial Research.
Abstract (Originalsprache)
Background
Periodontitis is among the most prevalent chronic inflammatory conditions globally, and is associated with bone resorption, tooth loss, and systemic complications. While its treatment is largely standardized, individual outcomes vary, with some patients experiencing further disease progression despite adherence.
Methods
We developed a machine learning (ML) approach to predict individual outcomes 1 year post‐treatment using retrospectively assessed baseline parameters. We trained a Random Forest model on 18 demographic, clinical, microbiological, and treatment‐related features of 414 patients from randomized clinical trials (RCTs) in South America. We subsequently performed internal testing, interpretability analysis, and external testing on a second dataset of 78 patients from previous RCTs in North America and Europe exhibiting less severe disease.
Results
In internal testing, the ML model achieved an area under the receiver operator characteristics curve (AUROC) of 0.93, an area under the precision‐recall curve (AUPRC) of 0.90, an F 1 ‐score of 0.82, and an out‐of‐bag score of 0.71. Relative importances were 0.42 for clinical, 0.33 for treatment‐related, 0.21 for microbiological, and 0.04 for demographic features. In external testing, the ML model achieved an AUROC of 0.76, an AUPRC of 0.69, and an F 1 ‐score of 0.71.
Conclusions
Our study indicates that an ML‐based approach can assist in predicting individual responses to periodontal treatment. Prospective validation is needed for clinical application. Plain language summary Using comprehensive data from patients with periodontitis, an inflammatory condition of the tooth‐supporting tissues, a machine learning model was trained to predict how well patients might respond to different treatments after 1 year. The model was externally tested in patient populations from 2 continents different from the training dataset. The results suggest that with further research and refinement, this tool could eventually become a valuable asset in personalizing treatment plans for improved patient outcomes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oral Medicine, Infection, and Immunity, Harvard School of Dental Medicine, Boston, Massachusetts, USA.
- Department of Oral Surgery, University Clinic of Dentistry, Medical University of Vienna, Vienna, Austria.
- Department of Oral Biology, University Clinic of Dentistry, Medical University of Vienna, Vienna, Austria.
- Topic Group Dental Diagnostics and Digital Dentistry, International Telecommunication Union-World Health Organization-World Intellectual Property Organization Global Initiative on Artificial Intelligence for Health, Gen…
- Department of Periodontology, University of Florida, Gainesville, Florida, USA.
- Core for Computational Biomedicine, Department for Biomedical Informatics, Blavatnik Institute, Harvard Medical School, Boston, Massachusetts, USA.
ORCID-Profile: Balazs Feher, Eduardo H de Souza Oliveira, Poliana Mendes Duarte, Andreas A Werdich, William V Giannobile, Magda Feres
Förderung
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- NCRR NIH HHS
- NIH | National Institute of Dental and Craniofacial Research
- NIDCR NIH HHS
- Harvard Medical School Dean's Innovation Award
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- World Health Organization
- Osteology Foundation
Zitieren
APA
Feher, B., de Souza Oliveira, E. H., Mendes Duarte, P., Werdich, A. A., Giannobile, W. V., & Feres, M. (2025). Machine learning‐assisted prediction of clinical responses to periodontal treatment. Journal of Periodontology, 96(11), 1199-1212. https://doi.org/10.1002/jper.24-0737
Vancouver
Feher B, de Souza Oliveira EH, Mendes Duarte P, Werdich AA, Giannobile WV, Feres M. Machine learning‐assisted prediction of clinical responses to periodontal treatment. Journal of Periodontology. 2025;96(11):1199-1212. doi:10.1002/jper.24-0737
BibTeX
@article{Feher2025,
author = {Feher, Balazs and de Souza Oliveira, Eduardo H and Mendes Duarte, Poliana and Werdich, Andreas A and Giannobile, William V and Feres, Magda},
title = {Machine learning‐assisted prediction of clinical responses to periodontal treatment},
journal = {Journal of Periodontology},
year = {2025},
volume = {96},
number = {11},
pages = {1199--1212},
doi = {10.1002/jper.24-0737}
}
EUVIMED