Deep Learning Approach to Measure Alveolar Bone Loss After COVID-19
Bibliographic record
Abstract
Abstract Severity of periodontal disease may be determined by measurement of alveolar crestal height (ACH) on dental bitewing radiographs; however, the prevailing method of assessment is through visualization which is time consuming and not a direct measure. The primary objective of this manuscript is to create and validate a deep learning technique for precise evaluation of alveolar bone loss in bitewing radiographs. Additionally, surveys were conducted with dental professionals to determine accuracy of visualized measures of ACH for severe periodontal disease versus the deep learning program and to determine the acceptability of utility of the program among diverse dental professionals. Lastly, the deep learning program was utilized in research to evaluate the role of COVID on periodontal disease through longitudinal measures of bitewing radiograph ACH from patients during the: "pre-pandemic" (Feb 2017 - Feb 2020) and "post-pandemic" (Feb 2020 - Feb 2023) periods. The pre-pandemic group had a mean percentage loss of ACH of -1.74 + 16.5%, representing a gain in alveolar bone. In contrast, the post-pandemic group had a gain in ACH of 2.46 + 14.6%, representing a loss in alveolar bone. There remained a trend for greater annualized percent change in ACH in the post-pandemic vs pre-pandemic group (1.33 + 11.9% vs -0.94 + 12.5%, p=0.07), after accounting for differences in duration between xrays. Overall, this study demonstrates the successful training and validation of a deep learning program for ACH measurement as well as its utility and acceptability among dental professionals for clinical and research.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.000 | 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 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".