Periodontitis is a common inflammatory disease of the tissues surrounding the teeth and can lead to tooth loss if left untreated. To detect it, the dentist uses a fine probe to measure, at six points around each tooth, how far the gum has detached from the tooth. This so-called probing pocket depth is the key clinical measurement in diagnosing periodontitis. However, the measurement is time consuming, depends on the examiner's experience, and can be uncomfortable for patients. In dental practice, a panoramic radiograph showing all teeth in a single image is frequently taken. It is often the only image available at the first examination. Until now it has only allowed assessment of bone loss, not of clinical probing pocket depth. This study investigates whether a computer program based on artificial intelligence can estimate, from such a panoramic radiograph, how deep the gum pockets are between the teeth. For each tooth, the program is intended to indicate separately for the side facing the front neighbouring tooth and the side facing the back neighbouring tooth whether the pocket is shallow (up to 3 mm), moderate (4 to 5 mm) or deep (6 mm or more). The quality of these estimates is assessed by comparing them with the values actually measured during the dental examination. The study analyses only data that were already collected as part of routine dental care at the department. All patients for whom periodontal treatment was approved by the statutory health insurer since 1 July 2021 and for whom a panoramic radiograph from the twelve months preceding the examination is available are included (approximately 1,770 people). No additional examinations, no additional radiographs and no treatment take place as part of the study. Participants are therefore not exposed to any risks or burdens. All data are irreversibly altered before analysis so that individuals can no longer be identified. The aim is to improve the early detection of periodontitis in general den
Patients of the Department of Conservative Dentistry, Periodontology and Digital Dentistry, LMU Munich. Statutory periodontal treatment plan (BEMA) submitted and approved by the responsible health insurer since 1 July 2021. Complete documented six-point clinical periodontal chart including diagnosis according to the 2018 classification (staging and grading). Availability of a digital panoramic radiograph obtained no more than 12 months before the date of clinical charting. Adequate diagnostic image quality of the panoramic radiograph. All criteria refer exclusively to pre-existing data collected during medically indicated diagnostics and treatment. The analysis is performed at tooth level; implant sites are excluded from analysis.
Missing or incompletely documented six-point clinical periodontal chart. No digital panoramic radiograph available, or an interval of more than 12 months between the radiograph and clinical charting. Panoramic radiograph of insufficient diagnostic image quality, for example due to positioning or motion artefacts, over- or underexposure, or incomplete depiction of the jaws. Documented objection to the further use of treatment data for research purposes. Edentulous jaw or no evaluable tooth remaining after application of the tooth-level criteria.
Diagnostic performance of the deep learning model in categorically estimating the maximum mesial and maximum distal periodontal probing pocket depth per tooth (shallow 3 mm or less, moderate 4 to 5 mm, deep 6 mm or more) from the panoramic radiograph, measured as the area under the receiver operating characteristic curve (AUROC), reported class-wise (one-vs-rest) and as macro-average. The reference standard is the documented six-point clinical periodontal chart. Performance is reported exclusively on the previously unused, patient-stratified hold-out test set. Confidence intervals are obtained by bootstrapping. Time of assessment: single analysis of retrospectively available data from 1 January 2021 to 1 May 2026; there is no follow-up. Radiograph and clinical reference examination are separated by no more than 12 months.