Clinical audit of an artificial intelligence (AI) empowered smile simulation system: a prospective clinical trial
Bibliographic record
Abstract
Smile aesthetics is an important factor to consider during orthodontic treatment planning. The aim of the present study is to assess the predictability of Invisalign SmileView for digital AI smile simulation in comparison to actual smile treatment outcomes, using various smile assessment parameters. A total of 24 adult subjects (12 females and 12 males; mean age 22 ± 5.2 years) who chose to be treated using Invisalign were prospectively recruited to have their pretreatment smiles captured using the Invisalign SmileView to simulate their new smiles before treatment was started. Patients were then treated using upper and lower Invisalign aligners with average treatment time of 18 ± 6 months. Full post-treatment records were obtained and full smile frame images of simulated smile and actual final smile of each subject were evaluated by an independent examiner using an objective assessment sheet. Ten smile variants were used to assess the characteristics of the full smile images. Significance level was set at P < 0.05. The ICC for the quantitative parameters showed that there was an overall excellent & good internal consistency (alpha value > 0.7 & > 0.9). The Independent t test was performed amongst the quantitative variables. The P value was not significant for all except maxillary inter canine width (P = 0.05), stating that for the five variables namely; philtrum height, commissure height, smile width, buccal corridor and smile index, actual mean values were similar to the simulation mean values. For the qualitative variables, the Kappa value ranged between 0.66 and - 0.75 which showed a substantial level of agreement between the examiners. Additionally, the Chi square test for the qualitative variables, revealed that the P value was found to be significant in all except lip line. This implies that only the lip line values are comparable. More optimal lip lines, straighter smile arcs and more ideal tooth display were achieved in actual post treatment results in comparison to the initially predicted smiles. Five quantitative smile assessment parameters i.e., philtrum height, commissure height, smile width, buccal corridor, and smile index, could be used as reliable predictors of smile simulation. Maxillary inter canine width cannot be considered to be a reliable parameter for smile simulation prediction. A single qualitative parameter, namely the lip line, can be used as a reliable predictor for smile simulation. Three qualitative parameters i.e., most posterior tooth display, smile arc, and amount of lower incisor exposure cannot be considered as reliable parameters for smile prediction.Trial Registration number and date: NCT06123585, (09/11/2023).
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 | 0.007 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".