Diagnostic Accuracy of Oral Images, OPGs, Biomarkers and Questionnaires vs. Clinical Assessment for Periodontal Disease (PostNCT07164573)

Gingivitis, Periodontal Disease, Periodontitis

Diagnosis, ArtiLcial Intelligence, Periodontal Diseases, Radiography, Machine Learning, Photography

This multi-center, cross-sectional diagnostic trial evaluates the accuracy of multiple non-invasive screening tools-including self-reported questionnaires, intra-oral photographs, orthopantomographs (OPGs), intraoral scans (IOS), and salivary/microbial biomarkers-for detecting periodontal health and diseases (gingivitis and periodontitis Stages I-IV), using full-mouth clinical periodontal examination as the reference standard. A total of 2,000 participants will be recruited across five international centers. Diagnostic performance (sensitivity, specificity, AUROC) of individual and combined methods will be assessed using logistic regression and machine learning algorithms to establish an optimized multi-modal screening algorithm.

This study is an extension of NCT07164573, with the addition of salivary and microbial biomarker analysis as index tests. While NCT07164573 focuses on questionnaires, oral images, and OPGs, this study incorporates biomarker-based classifiers to evaluate a comprehensive multi-modal diagnostic approach for periodontal disease detection.This is a multi-center, cross-sectional diagnostic accuracy study. The study aims to validate and compare the performance of multiple index tests against a clinical reference standard for the detection of periodontal health and disease. The reference standard for periodontal diagnosis will be a comprehensive full-mouth periodontal examination conducted by trained and calibrated examiners at five international clinical centers. Diagnoses (periodontal health, gingivitis, periodontitis Stages I-IV) will be assigned based on the integration of clinical, radiographic, and demographic data according to the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. The decision-making algorithms proposed by Tonetti and Sanz (2019) will be applied. The index tests under investigation include: 1. A set of self-reported questionnaires, including a modified CDC-AAP questionnaire, OHIP-14, and a dietary survey. 2. Intra-oral clinical photographs captured with a professional camera and a smartphone. 3. A self-performed intra-oral photograph ("selfie"), with and without cheek retractors. 4. Digital orthopantomographs (OPGs). 5. Intraoral scans (IOS). 6. Biomarker analysis of specific proteins and microbial signatures obtained from unstimulated saliva, oral rinse, and subgingival plaque (collected at the Shanghai center only). Data from the index tests will be analyzed using previously developed and validated machine learning models (e.g., HC-Net+ for OPG analysis, a deep learning model for single frontal-view images, and biomarker-based classifiers for periodontal disease detection). The data collected in this study will also be used to further refine these models, particularly to improve the differentiation between gingivitis/Stage I periodontitis and health/Stage II-IV periodontitis. The primary analytical method will involve assessing the diagnostic accuracy of each index test, both individually and in combination, by calculating sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) against the clinical reference standard. Logistic regression and machine learning algorithms will be employed to identify the most predictive variables and optimal diagnostic sequences. A total of 2,000 participants will be recruited across the five centers. The study will be conducted in compliance with the Declaration of Helsinki, ICH-GCP guidelines, and relevant STARD and AI-specific reporting guidelines.

No related papers found yet.

None listed

China, Italy, United Kingdom