Data sharing for responsible artificial intelligence in dentistry: a narrative review of legal frameworks and privacy-preserving techniques
Bibliographic record
Abstract
OBJECTIVES: Data sharing is essential for ensuring research reproducibility and for developing generalizable artificial intelligence (AI) systems, but it demands robust safeguards for patient privacy. This narrative review aims to guide dental clinicians and researchers in sharing patient data responsibly while preserving confidentiality. DATA: Dental patient data include radiographs, (cone beam) CTs, photographs, intraoral scans, tabular data, and electronic health records. These datasets are often heterogeneous, distributed across institutions, and subject to strict privacy regulations. Handling and sharing such sensitive data requires secure, privacy-preserving techniques to ensure compliance with legal and ethical standards. SOURCES: PubMed, Embase, Scopus, arXiv and Google Scholar were searched using keywords related to dentistry, data sharing, AI, and privacy-preserving techniques. Given the limited number of results relevant to dentistry, the search was extended to medicine. In parallel, we reviewed applicable regulatory frameworks such as the European Union (EU) General Data Protection Regulation (GDPR), Health Insurance Portability and Accountability Act (HIPAA), EU AI Act, and European Health Data Space (EHDS). STUDY SELECTION: We selected studies addressing data sharing in dentistry/medicine, de-identification, privacy-preserving techniques, and/or federated learning, as well as applicable regulatory frameworks. Most of the articles were peer-reviewed, but authoritative grey literature was included as well. CONCLUSIONS: This review summarized legal and technical aspects of dental data sharing to enable compliant multi-institutional collaboration. Beyond AI in dentistry, which was primarily emphasized, responsible data sharing is integral to FAIR practice and strengthens transparency and reproducibility across dental and medical research. CLINICAL SIGNIFICANCE: This review provides regulation-aligned guidance on de-identifying and sharing dental data, enabling compliant multi-institutional collaboration while protecting privacy. By promoting responsible AI development and reproducible research, it translates into more reliable care and greater patient trust in everyday clinical practice.
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 | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".