Question · asked by 1 review
AI systems for caries detection/segmentation on dental X-ray images (predominantly convolutional neural networks; also ANNs, DNNs, DCNN, FCNN, SVMs, decision trees, random forests; e.g. EfficientNet, ResNet, AlexNet) vs Human dentists / trained dental professionals or traditional radiographic interpretation (reference standard / reference models): Diagnostic accuracy (prevalence of accuracy)
- Population
- Patients undergoing dental X-ray (radiographic) imaging for caries detection
- Intervention
- AI systems for caries detection/segmentation on dental X-ray images (predominantly convolutional neural networks; also ANNs, DNNs, DCNN, FCNN, SVMs, decision trees, random forests; e.g. EfficientNet, ResNet, AlexNet)
- Comparison
- Human dentists / trained dental professionals or traditional radiographic interpretation (reference standard / reference models)
- Outcome
- Diagnostic accuracy (prevalence of accuracy)
On digital bitewing X-rays, AI accuracy was around 80% (single study, narrow CI; ungraded subgroup, numeric estimate not precisely readable).
What each review found
Current versions onlyNo studies found 0 · 0%GRADE not reported 4 · 100%Very low 0 · 0%Low 0 · 0%Moderate 0 · 0%High 0 · 0%
| Finding | Effect | Studies | GRADE certainty |
|---|---|---|---|
AI systems for caries detection/segmentation on dental X-ray images (predominantly convolutional neural networks; also ANNs, DNNs, DCNN, FCNN, SVMs, decision trees, random forests; e.g. EfficientNet, ResNet, AlexNet) vs Human dentists / trained dental professionals or traditional radiographic interpretation (reference standard / reference models) Diagnostic accuracy (prevalence of accuracy) · Patients undergoing dental X-ray (radiographic) imaging for caries detection · Dental radiography (digital periapical, bitewing, panoramic; OCT/micro-CT in one study); studies 2017-2023 across China, South Korea, Brazil, Turkey, France, USA, UK, Taiwan, Germany, India, Netherlands, Digital bitewing X-rays (Fig 4a) On digital bitewing X-rays, AI accuracy was around 80% (single study, narrow CI; ungraded subgroup, numeric estimate not precisely readable). Accuracy of artificial intelligence in caries detection: a systematic review and meta-analysis. (2025) All outcomes | ~80 | 1 study | GRADE not reported |
AI systems for caries detection/segmentation on dental X-ray images (predominantly convolutional neural networks; also ANNs, DNNs, DCNN, FCNN, SVMs, decision trees, random forests; e.g. EfficientNet, ResNet, AlexNet) vs Human dentists / trained dental professionals or traditional radiographic interpretation (reference standard / reference models) Diagnostic accuracy (prevalence of accuracy) · Patients undergoing dental X-ray (radiographic) imaging for caries detection · Dental radiography (digital periapical, bitewing, panoramic; OCT/micro-CT in one study); studies 2017-2023 across China, South Korea, Brazil, Turkey, France, USA, UK, Taiwan, Germany, India, Netherlands, Periapical X-rays (Fig 4c) On periapical X-rays, AI accuracy was around 76% (wide CI; ungraded subgroup, numeric estimate not precisely readable). Accuracy of artificial intelligence in caries detection: a systematic review and meta-analysis. (2025) All outcomes | ~76 | Not reported | GRADE not reported |
AI systems for caries detection/segmentation on dental X-ray images (predominantly convolutional neural networks; also ANNs, DNNs, DCNN, FCNN, SVMs, decision trees, random forests; e.g. EfficientNet, ResNet, AlexNet) vs Human dentists / trained dental professionals or traditional radiographic interpretation (reference standard / reference models) Diagnostic accuracy (prevalence of accuracy) · Patients undergoing dental X-ray (radiographic) imaging for caries detection · Dental radiography (digital periapical, bitewing, panoramic; OCT/micro-CT in one study); studies 2017-2023 across China, South Korea, Brazil, Turkey, France, USA, UK, Taiwan, Germany, India, Netherlands, Digital panoramic X-rays (Fig 4b) On digital panoramic X-rays, AI accuracy was around 70% (single study, wide CI; ungraded subgroup, numeric estimate not precisely readable). Accuracy of artificial intelligence in caries detection: a systematic review and meta-analysis. (2025) All outcomes | ~70 | 1 study | GRADE not reported |
AI systems for caries detection/segmentation on dental X-ray images (predominantly convolutional neural networks; also ANNs, DNNs, DCNN, FCNN, SVMs, decision trees, random forests; e.g. EfficientNet, ResNet, AlexNet) vs Human dentists / trained dental professionals or traditional radiographic interpretation (reference standard / reference models) Diagnostic accuracy (prevalence of accuracy) · Patients undergoing dental X-ray (radiographic) imaging for caries detection · Dental radiography (digital periapical, bitewing, panoramic; OCT/micro-CT in one study); studies 2017-2023 across China, South Korea, Brazil, Turkey, France, USA, UK, Taiwan, Germany, India, Netherlands, Overall (all X-ray types pooled) Across 14 studies, AI showed high diagnostic accuracy for caries detection on dental X-rays (pooled OR ~2.72), with substantial heterogeneity (I2=88%) and no GRADE rating (ungraded). Accuracy of artificial intelligence in caries detection: a systematic review and meta-analysis. (2025) All outcomes | OR 2.72 [14.65, 14.65] | 14 studies | GRADE not reported |
Findings are shown side by side, never pooled across reviews.
The reviews
| Review | Searched up to | Included studies | AMSTAR 2 |
|---|---|---|---|
| Accuracy of artificial intelligence in caries detection: a systematic review and meta-analysis. 2025 All outcomes | Up to January 2024 (data collected up to January 2024; electronic search completed 19 May 2023, final search included research up to January 2024) | 35 | Not applicable |
Studies behind the findings
The primary studies the full-text reviews tie to this outcome. Reviews with headline outcomes only do not list them here.
- Tracking of serum 25-hydroxyvitamin D levels during 14 years in a population-based study and during 12 months in an intervention study. · 2010 · included by 1 of these review
- [Changes in skin enzyme activity in experimental burns]. · 1977 · included by 1 of these review
- Bayraktar 2022 · included by 1 of these review
- Cantu 2020 · included by 1 of these review
- Chen 2023 · included by 1 of these review
- De Araujo Faria 2021 · included by 1 of these review
- Huang 2021 · included by 1 of these review
- Lian 2021 · included by 1 of these review
- Moran 2021 · included by 1 of these review
- Srivastava 2017 · included by 1 of these review
- Vinayahalingam 2021 · included by 1 of these review
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.