Development trend of Artificial Intelligence (AI) in dentistry: exploring FDA-cleared dental devices
Bibliographic record
Abstract
INTRODUCTION: Artificial Intelligence (AI) and Machine Learning (ML) are increasingly being incorporated into dentistry to enhance diagnostics, treatment planning, and clinical outcomes. However, their translation into routine practice is contingent upon regulatory approval to ensure safety and effectiveness. In the United States, the Food and Drug Administration (FDA) typically evaluates moderate-risk AI/ML-based dental devices under the 510(k) Premarket Notification pathway. Understanding the approval trends and characteristics of these devices is crucial for assessing the clinical integration of AI in dentistry. MATERIALS AND METHODS: A manual search of the FDA's 510(k) Premarket Notification Database was conducted in December 2024 using the terms "AI/ML devices" and "dentistry." Devices were screened for relevance, and data were extracted regarding applicant name, device type, predicate device, year of approval, AI algorithm employed, clinical indication, country of origin, and status of real-world deployment. RESULTS: Fifty-two AI/ML dental devices were identified. The year 2022 saw the highest number of approvals (n = 8, 15.38%). Nearly half (n = 25, 48%) of the devices were indicated for oral radiology, followed by applications in implantology and regenerative procedures (n = 18, 32%). Overjet, Inc. received four approvals for diagnostic tools targeting caries, calculus, and charting. Ewoosoft Co., Ltd. accounted for six approvals, primarily versions of its Ez3D-i imaging platform. Most devices originated from the United States (n = 24, 46.15%), followed by South Korea (n = 5, 9.61%) and Canada (n = 3, 5.76%). Notably, 60% of devices did not disclose the type of AI/ML algorithm used (n = 31), and 50% lacked public documentation on clinical deployment (n = 26). CONCLUSION: Most FDA-cleared AI/ML dental devices in the 510(k) database are imaging-based diagnostics; greater transparency, real-world validation, and attention to equity are needed for safe adoption.
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 | 0.008 | 0.024 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.012 | 0.014 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".