Artificial Intelligence Models for Diagnosis of Periodontitis Using Non-Invasive Biological Markers: A Systematic Review and Meta-Analysis of Patient-Based Studies
Künstliche-Intelligenz-Modelle zur Diagnose von Parodontitis mit nicht-invasiven biologischen Markern: systematische Übersichtsarbeit und Metaanalyse patientenbasierter Studien
Medical Sciences · 01.09.2025 · 13 (3) · 159
DOI: 10.3390/medsci13030159 ↗Auf einen Blick
Sieben Studien untersuchten AI-Modelle zur Diagnose von Parodontitis mit Biomarkern aus Speichel, GCF und immunologischen Profilen. Die zusammengefasste diagnostische Genauigkeit war hoch.
Fragestellung
Wie genau diagnostizieren AI-Modelle mit nicht-invasiven oder minimal-invasiven Biomarkern Parodontitis beim Menschen?
Methode
Systematische Übersichtsarbeit und Metaanalyse; Suche in PubMed/MEDLINE, Scopus, Web of Science, EMBASE und Cochrane CENTRAL bis Juni 2025.
Ergebnisse
7 Studien. Gepoolte Sensitivität 0,89 (95 %-KI 0,84–0,93), Spezifität 0,87 (95 %-KI 0,80–0,92), Summary-AUC 0,92. Saliväre Marker: AUC 0,94; GCF/immunologische Marker: AUC 0,89.
Einschränkungen
Einschränkungen in Studiendesign und Validierung; Studien mit unklarem Bias wurden in Sensitivitätsanalysen ausgeschlossen.
Schlussfolgerung der Autor:innen
AI-basierte diagnostische Modelle mit salivären, mikrobiellen oder immunologischen Biomarkern zeigten quantitativ hohe Genauigkeit; die Evidenz war insgesamt moderat bis hoch.
Kernaussagen
- Gepoolte Sensitivität 0,89 und Spezifität 0,87
- Summary-AUC 0,92
- Saliväre Biomarker schnitten mit AUC 0,94 besser ab als GCF/immunologische Marker
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Medical Sciences, online erschienen am 01.09.2025. Verfasst von Carlos M Ardila und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Periodontics, Saveetha Dental College, and Hospitals, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Saveet…. Hauptthemen laut MEDLINE: Biomarkers, Artificial Intelligence, Periodontitis. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Early diagnosis of periodontitis remains challenging using traditional clinical methods. This systematic review and meta-analysis evaluated the diagnostic accuracy of artificial intelligence (AI) models trained on non-invasive or minimally invasive biomarkers—including saliva, gingival crevicular fluid (GCF), and immunologic profiles—for diagnosing and classifying periodontitis in human subjects.
Methods
A comprehensive search of PubMed/MEDLINE, Scopus, Web of Science, EMBASE, and Cochrane CENTRAL was conducted from database inception to June 2025. Eligible studies used AI or machine learning models with patient-derived biomarker data and reported diagnostic performance metrics.
Results
Seven studies were included, employing various AI models such as random forest, artificial neural networks, and gradient boosting. Biomarkers were derived from saliva (n = 4), saliva-derived biomarkers from oral rinse (n = 1), immunologic profiles (n = 1), and tissue-based gene expression (n = 1). Reported area under the receiver operating characteristic (ROC) curve (AUC) ranged from 0.83 to 0.96. Meta-analysis of studies with comparable outcomes showed a pooled sensitivity of 0.89 (95% CI: 0.84–0.93), a specificity of 0.87 (95% CI: 0.80–0.92), and a summary AUC of 0.92. Subgroup analysis revealed that models using salivary biomarkers achieved a higher pooled AUC (0.94) than those using GCF or immunologic markers (AUC: 0.89). Sensitivity analyses excluding studies with unclear bias did not significantly alter pooled estimates, affirming robustness. The overall certainty of evidence was rated as moderate to high.
Conclusions
AI-based diagnostic models utilizing salivary, microbiome, or immunologic biomarkers demonstrated quantitatively high accuracy; however, the overall certainty of evidence was rated as moderate to high due to limitations in study design and validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Periodontics, Saveetha Dental College, and Hospitals, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Saveetha 600077, India.
- Biomedical Stomatology Research Group, Basic Sciences Department, Faculty of Dentistry, Universidad de Antioquia U de A, Medellín 050010, Colombia.
- Institución Universitaria Visión de las Américas, Faculty of Dentistry, Medellín 050040, Colombia.
ORCID-Profile: Carlos M Ardila, Anny M Vivares-Builes, Pradeep Kumar Yadalam
Zitieren
APA
Ardila, C. M., Vivares-Builes, A. M., & Yadalam, P. K. (2025). Artificial Intelligence Models for Diagnosis of Periodontitis Using Non-Invasive Biological Markers: A Systematic Review and Meta-Analysis of Patient-Based Studies. Medical Sciences, 13(3), 159. https://doi.org/10.3390/medsci13030159
Vancouver
Ardila CM, Vivares-Builes AM, Yadalam PK. Artificial Intelligence Models for Diagnosis of Periodontitis Using Non-Invasive Biological Markers: A Systematic Review and Meta-Analysis of Patient-Based Studies. Medical Sciences. 2025;13(3):159. doi:10.3390/medsci13030159
BibTeX
@article{Ardila2025,
author = {Ardila, Carlos M and Vivares-Builes, Anny M and Yadalam, Pradeep Kumar},
title = {Artificial Intelligence Models for Diagnosis of Periodontitis Using Non-Invasive Biological Markers: A Systematic Review and Meta-Analysis of Patient-Based Studies},
journal = {Medical Sciences},
year = {2025},
volume = {13},
number = {3},
pages = {159},
doi = {10.3390/medsci13030159}
}
EUVIMED