Background: This Consensus Workshop dealt with diagnostic methodologies in the context of surveillance, screening, assessment of stage and grade, prognosis, monitoring and prediction of periodontal status. Several elements provided the impetus for the workshop, including the limited quality of available research on diagnostic tests, the rapid development of new technologies, the implementation of the 2018 classification and the declarations of the World Health Organisation on diagnosis and oral health. Aim: To update and evaluate the evidence on diagnostic methods, considering recent advances in knowledge and the implementation of the 2018 classification. Methods: The European Workshop Committee of the European Federation of Periodontology guided the development of a consensus report after commissioning eight systematic reviews within three working groups. The reviews were discussed during the in‐person consensus meeting involving 70 participants from 21 different countries. Results: Working Group 1 discussed innovations in traditional diagnostic approaches, justified manual probing as the reference standard and assessed the value of image‐based methods. Working Group 2 analysed diagnostic tests based on microbial and host biomarkers and genetic diagnostic tests. Working Group 3 covered emerging technologies to be used within dental and non‐dental clinical settings, focusing principally on the impact of questionnaire‐based assessments and artificial intelligence systems (AIS) in interpreting different data modalities. Conclusion: Although manual periodontal probing is firmly established as the reference standard, additional approaches based on imaging, biomarkers, host genetics, questionnaires and the development of emerging applied data science methods (e.g., AIS) are increasingly integrated in periodontal diagnostics.

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.

Objectives: Risk prediction in implant dentistry presents specific challenges including the dependence of observations from patients with multiple implants and rare outcome events. The aim of this study was to use advanced statistical methods based on penalized regression to assess risk factors in implant dentistry.Material and methods: We conducted a retrospective study from January 2016 to November 2018 recording postoperative complications including bleeding, hematoma, local infection, and nerve damage, as well as early implant failure. We further assessed patient‐ and implant‐related risk factors including smoking and diabetes, as well as treatment parameters including types of gaps and surgical procedures. Univariable and multivariable generalized estimating equation (GEE) models were estimated to assess predictor effects, and a prediction model was fitted using L1 penalized estimation (lasso).Results: In a total of 1,132 patients (mean age: 50.6 ± 16.5 years, 55.4% female) and 2,413 implants, postoperative complications occurred in 71 patients. Sixteen implants were lost prior to loading. Multivariable GEE models showed a higher risk of any complication for diabetes mellitus (p = .006) and bone augmentation (p = .039). The models further revealed a higher risk of local infection for bone augmentation (p = .003), and a higher risk of hematoma formation for diabetes mellitus (p = .007) and edentulous jaws (p = .024). The lasso model did not select any risk factors into the prediction model.Conclusions: Using novel methodology well‐suited to tackle the specific challenges of risk prediction in implant dentistry, we were able to reliably estimate associations of risk factors with outcomes.

The detection and classification of cystic lesions of the jaw is of high clinical relevance and represents a topic of interest in medical artificial intelligence research. The human clinical diagnostic reasoning process uses contextual information, including the spatial relation of the detected lesion to other anatomical structures, to establish a preliminary classification. Here, we aimed to emulate clinical diagnostic reasoning step by step by using a combined object detection and image segmentation approach on panoramic radiographs (OPGs). We used a multicenter training dataset of 855 OPGs (all positives) and an evaluation set of 384 OPGs (240 negatives). We further compared our models to an international human control group of ten dental professionals from seven countries. The object detection model achieved an average precision of 0.42 (intersection over union (IoU): 0.50, maximal detections: 100) and an average recall of 0.394 (IoU: 0.50–0.95, maximal detections: 100). The classification model achieved a sensitivity of 0.84 for odontogenic cysts and 0.56 for non-odontogenic cysts as well as a specificity of 0.59 for odontogenic cysts and 0.84 for non-odontogenic cysts (IoU: 0.30). The human control group achieved a sensitivity of 0.70 for odontogenic cysts, 0.44 for non-odontogenic cysts, and 0.56 for OPGs without cysts as well as a specificity of 0.62 for odontogenic cysts, 0.95 for non-odontogenic cysts, and 0.76 for OPGs without cysts. Taken together, our results show that a combined object detection and image segmentation approach is feasible in emulating the human clinical diagnostic reasoning process in classifying cystic lesions of the jaw.

Objectives Resonance frequency analysis (RFA) is used to monitor implant stability. Its output, the Implant Stability Quotient (ISQ), supposedly correlates with insertion torque, a common measurement of primary stability. However, the reliability of RFA in condensed bone remains unclear. Material and methods In this human cadaver study in edentulous jaws and fresh extraction sockets, implants were inserted using a split-mouth approach into condensed or untreated bone. Mean ISQ, peak insertion torque, and pre- and postoperative bone volume fractions (BV/TV) were assessed. Results In edentulous jaws, insertion torque and ISQ correlated both in untreated (r = 0.63, p = 0.02) and in condensed (r = 0.82, p < 0.01) bone. In extraction sockets, insertion torque and ISQ only correlated in untreated (r = 0.78, p 0.01), but not in condensed bone (r = 0.15, p = 0.58). In all edentulous jaws, preoperative BV/TV correlated with insertion torque (r = 0.90, p 0.0001), ISQ (r = 0.64, p 0.001), and changes in BV/TV (r = -0.71, p 0.01). In all extraction sockets, preoperative BV/TV did not correlate with either insertion torque (r = 0.33, p = 0.15), ISQ (r = 0.38, p = 0.09), or changes in BV/TV (r = -0.41, p = 0.09). Joint analysis identified preoperative BV/TV as a predictor of postoperative BV/TV (p 0.001), insertion torque (p 0.001), and ISQ (p 0.001). Conclusions RFA is feasible for monitoring stability after late implant placement into condensed bone, but not after immediate placement into condensed fresh extraction sites.

Periodontitis is a severe infection affecting oral and systemic health and is traditionally diagnosed through clinical probing—a process that is time-consuming, uncomfortable for patients, and subject to variability based on the operator’s skill. We hypothesized that computer vision can be used to estimate periodontal stability from radiographs alone. At the tooth level, we used intraoral radiographs to detect and categorize individual teeth according to their periodontal stability and corresponding treatment needs: healthy (prevention), stable (maintenance), and unstable (active treatment). At the patient level, we assessed full-mouth series and classified patients as stable or unstable by the presence of at least 1 unstable tooth. Our 3-way tooth classification model achieved an area under the receiver operating characteristic curve of 0.71 for healthy teeth, 0.56 for stable, and 0.67 for unstable. The model achieved an F ₁ score of 0.45 for healthy teeth, 0.57 for stable, and 0.54 for unstable (recall, 0.70). Saliency maps generated by gradient-weighted class activation mapping primarily showed highly activated areas corresponding to clinically probed regions around teeth. Our binary patient classifier achieved an area under the receiver operating characteristic curve of 0.68 and an F ₁ score of 0.74 (recall, 0.70). Taken together, our results suggest that it is feasible to estimate periodontal stability, which traditionally requires clinical and radiographic examination, from radiographic signal alone using computer vision. Variations in model performance across different classes at the tooth level indicate the necessity of further refinement.