ARTIFICIAL INTELLIGENCE IN AUTOMATED INTERPRETATION OF DENTAL RADIOGRAPHS: A SYSTEMATIC REVIEW
Bibliographic record
Abstract
Background: Artificial intelligence (AI) is increasingly being integrated into dental diagnostics, particularly in the interpretation of radiographic images. Despite promising developments, current evidence on the diagnostic performance, error rates, and time-efficiency of AI algorithms in dental radiology remains fragmented. This creates uncertainty about the clinical utility and reliability of AI applications in real-world dental practice. Objective: This systematic review aimed to evaluate the diagnostic accuracy, error rate, and time-efficiency of AI algorithms in analyzing dental radiographs compared to traditional clinician-led interpretation. Methods: A systematic review was conducted following PRISMA guidelines. Databases searched included PubMed, Scopus, Web of Science, and the Cochrane Library from January 2019 to May 2024. Eligible studies included observational and experimental designs that compared AI-based radiographic interpretation with human performance, focusing on diagnostic accuracy, interpretation time, and error rates. Data extraction and risk of bias assessments were performed independently by two reviewers using standardized tools (Cochrane RoB 2.0 and Newcastle-Ottawa Scale). A narrative synthesis was conducted due to heterogeneity in study designs and outcomes. Results: Eight studies involving various AI models and a total of over 25,000 dental radiographic images were included. AI algorithms demonstrated high diagnostic accuracy (ranging from 80.2% to 96.5%), reduced error rates, and significantly improved time-efficiency in most studies (p < 0.05). The performance of AI systems was comparable to or better than experienced clinicians across multiple radiographic modalities, including bitewing, panoramic, and periapical images. Conclusion: AI shows strong potential in supporting dental professionals by enhancing diagnostic accuracy and efficiency in radiographic interpretation. However, variability in methodologies and limited external validation call for further large-scale, prospective studies to confirm its generalizability and clinical integration.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".