Efficacy of Artificial Intelligence–Assisted Appliances in the Selection of Tooth Shade: Protocol for an Observational Study
Bibliographic record
Abstract
BACKGROUND: Accurate shade matching in dentistry is crucial for achieving aesthetic outcomes, with increasing patient expectations driving advancements in shade selection technologies. Color perception is influenced by multiple factors such as incident light, reflection, absorption, observer variability, and environmental conditions. The evolution of shade-matching tools now includes digital and artificial intelligence (Al)-assisted appliances aimed at improving accuracy and ease of use. OBJECTIVE: This study aims to compare and evaluate the efficacy of AI-assisted appliances, namely, smartphone cameras, digital single-lens reflex (DSLR) cameras, and intraoral scanners in selecting tooth shades in clinical practice. METHODS: This observational study conducted at the Department of Prosthodontics and Crown & Bridge aims to evaluate shade selection methods in 221 participants recruited from the outpatient department based on specific inclusion and exclusion criteria, including age, oral health status, and informed consent. Three devices will be used for shade selection: a smartphone camera (iPhone 12, iOS 12.5.2) for quick, noninvasive, and accessible image capture; a DSLR camera (Canon EOS 200D) to obtain high-resolution images under standardized lighting for enhanced color accuracy; and an intraoral scanner (CEREC Primescan, Dentsply Sirona) offering precise 3D mapping and digital shade analysis. This multidevice approach allows for a comparative evaluation of conventional and advanced digital tools in clinical shade matching. The primary objective is to assess the effectiveness of commonly available digital teeth in accurately selecting tooth shades. Our study anticipates the following outcomes: validation of smartphone cameras as simple, economical, and efficient tools for basic shade matching; demonstration of DSLR cameras' superiority in resolution and lighting control for improved accuracy; and confirmation of intraoral scanners as precise, customizable devices that offer a high level of digital integration. Statistical analyses will include sensitivity, specificity, and subgroup evaluations to compare the performance of each device. The findings are expected to show that both DSLR and smartphone cameras can match the effectiveness of intraoral scanners, offering viable alternatives for clinical use. RESULTS: This study was intramurally funded in December 2024. Data collection is scheduled to commence following the publication of this study protocol. As of submission, no participants have been recruited, and data analysis is yet to begin. Results are expected to be completed and published in early January 2026. CONCLUSIONS: This study aims to establish a standard protocol for the use of Al-assisted, easily accessible tools such as smartphones and DSLRs for dental shade selection. These devices, being user-friendly and nontechnical, could democratize the process of shade matching, benefiting both clinicians and patients by improving restoration outcomes while reducing costs and complexity. Our results will contribute to the growing body of digital dentistry literature and support the integration of practical Al tools in everyday clinical practice. TRIAL REGISTRATION: Clinical Trials Registry-India CTRI/2024/07/070002; https://tinyurl.com/4pt5eutb. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/68160.
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 | 0.025 | 0.014 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.003 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.019 | 0.004 |
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".