Clinical Applications of Artificial Intelligence in Periodontology: A Systematic Review of the Literature
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Introduction Artificial intelligence (AI) is rapidly transforming various fields of medicine, including dentistry. AI applications in periodontology hold promise for improving diagnosis, treatment planning, and patient care. This protocol outlines a systematic review to evaluate the current evidence on clinical applications of AI in periodontology. Research Question What are the clinical applications of artificial intelligence in periodontology, and what is the evidence for their effectiveness and impact on patient outcomes? PICO Question Population: Patients with periodontal diseases Intervention: Artificial intelligence applications (e.g., diagnosis, risk assessment, treatment planning, outcome prediction) Comparison: Traditional methods or other AI applications Outcome: Diagnostic accuracy, treatment efficacy, patient-reported outcomes Inclusion Criteria Study Design: Clinical trials, cohort studies, case-control studies, cross-sectional studies Population: Patients with any type of periodontal disease (gingivitis, periodontitis) Intervention: Any AI application used for diagnosis, risk assessment, treatment planning, or outcome prediction in periodontology Outcomes: Diagnostic accuracy, treatment efficacy, patient-reported outcomes Language: English Exclusion Criteria Study Design: Case reports, case series, reviews, editorials, letters to the editor, conference papers/presentations Population: Animal studies, in vitro studies Intervention: AI applications not directly related to periodontology Outcomes: Not relevant to clinical practice or patient care Language: Non-English Search Strategy Databases: PubMed, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, Scopus, Web of Science™ Core Collection, ProQuest Dissertations and Theses Global Keywords: AI, Artificial Intelligence, machine learning, deep learning, neural network, convolutional network, Periodontology, periodontics, periodontal disease, periodontitis, periodontium, periodontal Boolean Operators: AND, OR Study Selection Title and Abstract Screening: Two reviewers will independently screen titles and abstracts for eligibility. Full-Text Review: Full texts of potentially eligible studies will be retrieved and reviewed independently by two reviewers. Disagreement Resolution: Any disagreements will be resolved through discussion or consultation with a third reviewer. Data Extraction Study Characteristics: Study design, population, intervention, comparison, outcomes, follow-up period AI Model Details: Type of AI algorithm, input data, training data, performance metrics Outcome Data: Diagnostic accuracy (sensitivity, specificity, AUC), treatment efficacy, patient-reported outcomes Quality Assessment Risk of Bias: The risk of bias in included studies will be assessed using appropriate tools (e.g., Cochrane Risk of Bias tool, Newcastle-Ottawa Scale). Data Synthesis Narrative Synthesis: A narrative synthesis will be conducted to summarize the findings of the included studies. Meta-Analysis: If appropriate, a meta-analysis will be performed to pool the results of studies with similar interventions and outcomes.
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.
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 | 0.008 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.010 |
| Science and technology studies | 0.000 | 0.003 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.010 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 it