AI-driven analysis of jaw-bone alterations in CBCT images associated with systemic diseases: A systematic review
Bibliographic record
Abstract
This systematic review aims to evaluate the diagnostic performance of artificial intelligence (AI) algorithms in detecting jawbone alterations associated with systemic diseases, primarily osteoporosis (OP) and temporomandibular joint osteoarthritis (TMJ OA) using cone-beam computed tomography (CBCT) images. Following PRISMA guidelines, a comprehensive search was conducted across multiple databasesStudies were included if they applied AI techniques to CBCT scans for detecting jawbone changes related to systemic bone conditions. Data were extracted on study design, AI architecture, population, diagnostic performance, and risk of bias using QUADAS-2 and an AI-specific quality checklist. Seven studies published between 2018 and 2024 met the inclusion criteria. AI models such as convolutional neural networks (CNNs), you only look once (YOLO), artificial neural networks (ANNs), and ensemble methods were employed. These models demonstrated high diagnostic performance, with accuracies ranging from 76.78 % to 98.85 %, sensitivities up to 100 %, and specificities above 94 %. OP-related studies focused on mandibular bone density and cortical morphology, while TMJ OA studies targeted condylar changes such as flattening, erosion, and osteophytes. Most models were trained on single-center datasets with limited external validation. Risk-of-bias analysis revealed common concerns in patient selection and reference standard reporting. AI models, particularly DL-based architectures, show strong potential for identifying osseous changes associated with systemic diseases on CBCT images. These findings highlight AI's potential to support early detection of jawbone changes and enable screening for systemic diseases during routine dental imaging.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.066 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.008 | 0.009 |
| Bibliometrics | 0.010 | 0.007 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".