Non-Cochrane · DTA · PM41597160
Artificial Intelligence in Pediatric Dentistry: A Systematic Review and Meta-Analysis.
Karamüftüoğlu Nevra, Üçpunar Büşra Yavuz, Birben İrem, et al. · Children (Basel, Switzerland) · 2026 · PubMed · doi:10.3390/children13010152
Findings
19 findings
| Population | ||||
|---|---|---|---|---|
| All pediatric dental AI diagnostic tasks | AI-based diagnostic or predictive models | Reference standard (expert consensus, clinical examination, radiographic or histological) | Pooled specificity | Specificity 0.91 GRADE not reported 15 studies |
| All pediatric dental AI diagnostic tasks | AI-based diagnostic or predictive models | Reference standard (expert consensus, clinical examination, radiographic or histological) | Pooled sensitivity | Sensitivity 0.89 GRADE not reported 15 studies |
| Children, primary teeth on panoramic radiographs | AI model for primary tooth identification and numbering | Reference standard | Pooled AUC | AUC 0.98 GRADE not reported Studies not reported |
| Children, primary teeth on panoramic radiographs | AI model for primary tooth identification and numbering | Reference standard | Pooled sensitivity | Sensitivity 0.90 GRADE not reported Studies not reported |
| Children, primary teeth on panoramic radiographs | AI model for primary tooth identification and numbering | Reference standard | Pooled specificity | Specificity 0.96 GRADE not reported Studies not reported |
| Children, panoramic and periapical radiographs | AI model for supernumerary tooth and mesiodens detection | Reference standard | Pooled specificity | Specificity 0.94 GRADE not reported Studies not reported |
| Children (0-18 y) with intraoral photographs or biofilm data | AI model (CNN) for early childhood caries (ECC) detection | Reference standard | AUC (ECC detection) Clinical photographs and biofilm | AUC 0.98 GRADE not reported Studies not reported |
| Children, panoramic and periapical radiographs | AI model for supernumerary tooth and mesiodens detection | Reference standard | Pooled sensitivity | Sensitivity 0.94 GRADE not reported Studies not reported |
| Children (0-18 y) with intraoral photographs or biofilm data | AI model (CNN) for early childhood caries (ECC) detection | Reference standard | Specificity (ECC detection) Clinical photographs and biofilm | Specificity 0.97 GRADE not reported Studies not reported |
| Children (0-18 y) with intraoral photographs or biofilm data | AI model (CNN) for early childhood caries (ECC) detection | Reference standard | Sensitivity (ECC detection) Clinical photographs and biofilm | Sensitivity 0.91 GRADE not reported Studies not reported |
| Children, early childhood caries, clinical photographs and biofilm | AI model for ECC detection | Reference standard | Pooled sensitivity | Sensitivity 0.91 GRADE not reported Studies not reported |
| Children, early childhood caries, clinical photographs and biofilm | AI model for ECC detection | Reference standard | Pooled AUC | AUC 0.98 GRADE not reported Studies not reported |
| Children, early childhood caries, clinical photographs and biofilm | AI model for ECC detection | Reference standard | Pooled sensitivity, forest plot of ECC detection studies | Sensitivity 0.89 GRADE not reported 10 studies |
| Children, early childhood caries, clinical photographs and biofilm | AI model for ECC detection | Reference standard | Pooled sensitivity, forest plot of ECC detection studies (figure legend) | Sensitivity 0.86 GRADE not reported 10 studies |
| Children, early childhood caries, clinical photographs and biofilm | AI model for ECC detection | Reference standard | Pooled specificity | Specificity 0.97 GRADE not reported Studies not reported |
| Children, early childhood caries risk, clinical and microbiome data | AI model for ECC prediction | Reference standard or observed ECC outcome | Pooled AUC | AUC 0.89 GRADE not reported Studies not reported |
| Children, early childhood caries risk, clinical and microbiome data | AI model for ECC prediction | Reference standard or observed ECC outcome | Pooled specificity | Specificity 0.82 GRADE not reported Studies not reported |
| Children, early childhood caries risk, clinical and microbiome data | AI model for ECC prediction | Reference standard or observed ECC outcome | Pooled sensitivity | Sensitivity 0.86 GRADE not reported Studies not reported |
| Children and adolescents, dental radiographs | AI model for dental age estimation | Chronological age | Pooled mean absolute error of dental age estimation | MAE 1.7 GRADE not reported Studies not reported |
Included primary studies 39
Open in Studies| Study | Year | Also included by | Outcomes it informs here | Trial data |
|---|---|---|---|---|
| Grier 2021 Oral Microbiota Composition Predicts Early Childhood Caries Onset. PMID:33356775 | 2021 | 1 other review | PM41597160-P3-O4 | not extracted yet |
| Kurt 2024 Evaluation of tooth development stages with deep learning-based artificial intelligence algorithm. PMID:39227802 | 2024 | 1 other review | not stated | not extracted yet |
| Park 2021 Prediction Models of Early Childhood Caries Based on Machine Learning Algorithms. PMID:34444368 | 2021 | 1 other review | PM41597160-P3-O4 | not extracted yet |
| Qu 2022 Prediction model for early childhood caries risk based on behavioral determinants using a machine learning algorithm DOI:10.1016/j.cmpb.2022.107221 | 2022 | 1 other review | not stated | not extracted yet |
| Qu 2022 Prediction model for early childhood caries risk based on behavioral determinants using a machine learning algorithm. PMID:36384058 | 2022 | 1 other review | PM41597160-P3-O4 | not extracted yet |
| Toledo Reyes 2023 Early Childhood Predictors for Dental Caries: A Machine Learning Approach. PMID:37246832 | 2023 | 1 other review | PM41597160-P3-O4 | not extracted yet |
| Al-Jallad 2022 Artificial intelligence-powered smartphone application, AICaries, improves at-home dental caries screening in children: Moderated and… DOI:10.1371/journal.pdig.0000046 | 2022 | this review only | not stated | not extracted yet |
| Al-Jallad 2022 Artificial intelligence-powered smartphone application, AICaries, improves at-home dental caries screening in children: Moderated and… PMID:36381137 | 2022 | this review only | PM41597160-P3-O4 | not extracted yet |
| Alevizakos 2022 Artificial intelligence system for training diagnosis and differentiation with molar incisor hypomineralization (MIH) and similar… DOI:10.1007/s00784-022-04646-z | 2022 | this review only | not stated | not extracted yet |
| Alevizakos 2022 Artificial intelligence system for training diagnosis and differentiation with molar incisor hypomineralization (MIH) and similar… PMID:36065023 | 2022 | this review only | not stated | not extracted yet |
| Bunyarit 2020 Dental age estimation of Malaysian Chinese children and adolescents: Chaillet and Demirjian’s method revisited using artificial multilayer… DOI:10.1080/00450618.2019.1567810 | 2019 | this review only | not stated | not extracted yet |
| Gajic 2021 Analysis of the Impact of Oral Health on Adolescent Quality of Life Using Standard Statistical Methods and Artificial Intelligence… DOI:10.3390/children8121156 | 2021 | this review only | not stated | not extracted yet |
| Gajic 2021 Analysis of the Impact of Oral Health on Adolescent Quality of Life Using Standard Statistical Methods and Artificial Intelligence… PMID:34943352 | 2021 | this review only | not stated | not extracted yet |
| Ha 2021 Automatic detection of mesiodens on panoramic radiographs using artificial intelligence DOI:10.1038/s41598-021-02571-x | 2021 | this review only | not stated | not extracted yet |
| Ha 2021 Automatic detection of mesiodens on panoramic radiographs using artificial intelligence. PMID:34845320 | 2021 | this review only | not stated | not extracted yet |
| Heimisdottir 2021 Metabolomics Insights in Early Childhood Caries DOI:10.1177/0022034520982963 | 2021 | this review only | not stated | not extracted yet |
| Heimisdottir 2021 Metabolomics Insights in Early Childhood Caries. PMID:33423574 | 2021 | this review only | PM41597160-P3-O4 | not extracted yet |
| Karhade 2021 An Automated Machine Learning Classifier for Early Childhood Caries. PMID:34172112 | 2021 | this review only | not stated | not extracted yet |
| Kaya 2022 A deep learning approach to permanent tooth germ detection on pediatric panoramic radiographs. PMID:36238699 | 2022 | this review only | not stated | not extracted yet |
| Kayaci 2025 End-to-end CNN-based detection of permanent first molars and prediction of root development stages from panoramic radiographs DOI:10.1038/s41598-025-22707-7 | 2025 | this review only | not stated | not extracted yet |
| Kayaci 2025 End-to-end CNN-based detection of permanent first molars and prediction of root development stages from panoramic radiographs. PMID:41193653 | 2025 | this review only | not stated | not extracted yet |
| Kilic 2021 Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs DOI:10.1259/dmfr.20200172 | 2021 | this review only | not stated | not extracted yet |
| Kilic 2021 Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs. PMID:33661699 | 2021 | this review only | not stated | not extracted yet |
| Kim 2022 Deep learning-based identification of mesiodens using automatic maxillary anterior region estimation in panoramic radiography of children DOI:10.1259/dmfr.20210528 | 2022 | this review only | not stated | not extracted yet |
| Kim 2022 Deep learning-based identification of mesiodens using automatic maxillary anterior region estimation in panoramic radiography of children. PMID:35731733 | 2022 | this review only | not stated | not extracted yet |
| Kurt 2024 Evaluation of tooth development stages with deep learning-based artificial intelligence algorithm DOI:10.1186/s12903-024-04786-6 | 2024 | this review only | not stated | not extracted yet |
| Li 2021 DOI:10.3760/cma.j.cn112144-20210712-00323 | NR | this review only | not stated | not extracted yet |
| Li 2021 [Development of a deep learning based prototype artificial intelligence system for the detection of dental caries in children]. PMID:34915661 | 2021 | this review only | PM41597160-P3-O4 | not extracted yet |
| Mine 2022 Detecting the presence of supernumerary teeth during the early mixed dentition stage using deep learning algorithms: A pilot study DOI:10.1111/ipd.12946 | 2022 | this review only | not stated | not extracted yet |
| Mine 2022 Detecting the presence of supernumerary teeth during the early mixed dentition stage using deep learning algorithms: A pilot study. PMID:34904304 | 2022 | this review only | not stated | not extracted yet |
| Raksakmanut 2023 Prediction of Future Caries in 1-Year-Old Children via the Salivary Microbiome DOI:10.1177/00220345231152802 | 2023 | this review only | not stated | not extracted yet |
| Raksakmanut 2023 Prediction of Future Caries in 1-Year-Old Children via the Salivary Microbiome. PMID:36919874 | 2023 | this review only | PM41597160-P3-O4 | not extracted yet |
| Toledo Reyes 2023 Early Childhood Predictors for Dental Caries: A Machine Learning Approach DOI:10.1177/00220345231170535 | 2023 | this review only | not stated | not extracted yet |
| Zaborowicz 2021 Tooth and Bone Parameters in the Assessment of the Chronological Age of Children and Adolescents Using Neural Modelling Methods. PMID:34577221 | 2021 | this review only | not stated | not extracted yet |
| Zaborowicz 2022 Deep Learning Neural Modelling as a Precise Method in the Assessment of the Chronological Age of Children and Adolescents Using Tooth and… PMID:35062599 | 2022 | this review only | not stated | not extracted yet |
| Zaorska 2021 Prediction of Early Childhood Caries Based on Single Nucleotide Polymorphisms Using Neural Networks DOI:10.3390/genes12040462 | 2021 | this review only | not stated | not extracted yet |
| Zaorska 2021 Prediction of Early Childhood Caries Based on Single Nucleotide Polymorphisms Using Neural Networks. PMID:33805090 | 2021 | this review only | PM41597160-P3-O4 | not extracted yet |
| Zhang 2021 The predictive power of saliva electrolytes exceeds that of saliva microbiomes in diagnosing early childhood caries DOI:10.1080/20002297.2021.1921486 | 2021 | this review only | not stated | not extracted yet |
| Zhang 2021 The predictive power of saliva electrolytes exceeds that of saliva microbiomes in diagnosing early childhood caries. PMID:34035879 | 2021 | this review only | PM41597160-P3-O4 | not extracted yet |
Overlap with other reviews
Reviews that include the same primary studies are not independent evidence. Shared counts match studies by PMID, DOI or NCT, and otherwise by author and year (a probable match). Only the non-Cochrane dental reviews have study lists, so overlap with Cochrane reviews is not counted yet.
Review question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Pediatric populations aged 0-18 years | Children and adolescents; 32 studies in qualitative synthesis, 15 in meta-analysis (n=15) |
| Intervention | AI model (machine learning, deep learning or hybrid) applied to a diagnostic or predictive task in dentistry | AI models: CNN, YOLO, ANN, transformer; tasks: tooth numbering, mesiodens detection, ECC detection, ECC prediction, age estimation |
| Comparison | Reference standards (expert consensus, clinical examination, radiographic interpretation, histological confirmation) | Reference standards varied across studies |
| Outcomes | Sensitivity, specificity, accuracy, AUC, mean absolute error | Pooled sensitivity, specificity and AUC by task; MAE for age estimation |
| Study designs | Diagnostic accuracy studies | Diagnostic accuracy studies (retrospective, mostly single-center) |
| Timing | Not specified | Not specified |