Machine-learning algorithms for dental caries detection vs Different machine-learning algorithms compared with one another / against the reference caries diagnosis: Diagnostic accuracy for root caries detection
One study reported machine-learning accuracy for root caries detection (97.1%, support vector machine); not pooled and not graded.
What each review found
Include earlier review versions| Finding | Effect | Studies | GRADE certainty |
|---|---|---|---|
Machine-learning algorithms (deep learning: CNN/FCNN, ANN, backpropagation neural network, SVM, ADA-NN, Mask R-CNN) applied as an index test to detect dental caries vs Different machine-learning algorithms compared with one another / against the reference caries diagnosis Diagnostic accuracy for root caries detection · Dental radiographic/intraoral images of human teeth (X-ray and photographic) · Dental image datasets (X-ray/intraoral photographs), multiple countries, 2008-2022, Root caries One study reported machine-learning accuracy for root caries detection (97.1%, support vector machine); not pooled and not graded. Uses of Different Machine Learning Algorithms for Diagnosis of Dental Caries. (2022) All outcomes | Accuracy 97.1 | 1 study | GRADE not reported |
Findings are shown side by side, never pooled across reviews.
The reviews
| Review | Searched up to | Included studies | AMSTAR 2 |
|---|---|---|---|
| Uses of Different Machine Learning Algorithms for Diagnosis of Dental Caries. 2022 All outcomes | Not specified | 17 | Not applicable |
Studies behind the findings
None of these reviews ties its included studies to this outcome in the data here. Cochrane reviews and reviews with headline outcomes only do not list their studies yet.
How reviews are matched to this question
Reviews word the same question differently. Four decision models (TypeSafe's Jev, Liquid AI's d1-ultra, SubQ Snap and Baseten's Elephant) judged each wording of the population, intervention, comparator and outcome against the others; two wordings count as the same when at least three of them agree and none clearly disagrees, and findings count as this question only when all four elements match. Timing, setting and subgroup never split a question: they are shown on each finding.