Non-Cochrane · intervention · PM42368773
Accuracy and Functional Performance of Artificial Intelligence-Based Automated Crown Design Systems: A Systematic Review and Meta-Analysis.
Holiel Ahmed A, Al Nakouzi Mounir M, Enrique Cuevas-Suárez Carlos, et al. · Biomedical engineering and computational biology · 2026 · PubMed · doi:10.1177/11795972261463709
Findings
Population Digital datasets of teeth requiring crown restoration (clinical cases, typodont models, digital casts)
19 findings
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Occlusal contact points GAN based | SMD -0.87 [-1.13, -0.60] GRADE not reported 2 studies · 1250 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Overall accuracy (RMS deviation) | SMD -0.15 [-1.04, 0.74] GRADE not reported 6 studies · 424 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Internal fit | SMD -0.15 [-0.47, 0.17] GRADE not reported 2 studies · 180 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Cusp angle reproduction | SMD -0.24 [-0.88, 0.40] GRADE not reported 5 studies · 362 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Occlusal contact points | SMD -0.43 [-0.95, 0.10] GRADE not reported 4 studies · 1490 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Marginal gap | SMD 0.44 [0.17, 0.71] GRADE not reported 2 studies · 280 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Overall accuracy (RMS deviation) Knowledge-based | SMD 0.69 [-0.14, 1.52] GRADE not reported 1 study · 24 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Chamfer distance | SMD -1.00 [-1.20, -0.80] GRADE not reported 2 studies · 460 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Profile discrepancy GAN based | SMD 0.13 [-0.04, 0.29] GRADE not reported 2 studies · 546 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Occlusal morphology | SMD -0.70 [-0.90, -0.51] GRADE not reported 2 studies · 460 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Occlusal contact points Transformer-based model | SMD 0.57 [-1.81, 2.96] GRADE not reported 2 studies · 240 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Cusp angle reproduction GAN based | SMD -0.81 [-1.80, 0.19] GRADE not reported 3 studies · 242 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Profile discrepancy Transformer-based model | SMD 0.89 [-1.22, 3.01] GRADE not reported 3 studies · 208 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Overall accuracy (RMS deviation) Transformer-based model | SMD -0.79 [-1.63, 0.04] GRADE not reported 2 studies · 156 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Design time | SMD -1.44 [-1.91, -0.97] GRADE not reported 2 studies · 140 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Cusp angle reproduction Transformer-based model | SMD 0.30 [-0.66, 1.27] GRADE not reported 1 study · 96 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Profile discrepancy | SMD 0.46 [-0.14, 1.05] GRADE not reported 5 studies · 754 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Overall accuracy (RMS deviation) GAN based | SMD -0.19 [-1.49, 1.10] GRADE not reported 3 studies · 244 participants |
| AI-based automated crown design systems (ML, DL, GAN, transformer or knowledge-based) | Conventional crown design workflows (technician-driven or manual CAD, library-based CAD/CAM) | Cusp angle reproduction Knowledge-based | SMD 0.68 [-0.15, 1.50] GRADE not reported 1 study · 24 participants |
Included primary studies 17
Open in Studies| Study | Year | Also included by | Outcomes it informs here | Trial data |
|---|---|---|---|---|
| Chen 2022 Morphology and fracture behavior of lithium disilicate dental crowns designed by human and knowledge-based AI. PMID:35508087 | 2022 | 1 other review | not stated | not extracted yet |
| Cho 2024 Tooth morphology, internal fit, occlusion and proximal contacts of dental crowns designed by deep learning-based dental software: A… PMID:38163455 | 2024 | 1 other review | not stated | not extracted yet |
| Ding 2023 Morphology and mechanical performance of dental crown designed by 3D-DCGAN. PMID:36822895 | 2023 | 1 other review | not stated | not extracted yet |
| Liu 2025 Evaluation of the accuracy, occlusal contact and clinical applications of zirconia crowns using artificial intelligence design versus… PMID:40654460 | 2025 | 1 other review | not stated | not extracted yet |
| Nagata 2025 Verification of the accuracy and design time of crowns designed with artificial intelligence. PMID:40061025 | 2025 | 1 other review | not stated | not extracted yet |
| Wu 2024 Comparison of the Efficacy of Artificial Intelligence-Powered Software in Crown Design: An In Vitro Study. PMID:39069456 | 2025 | 1 other review | not stated | not extracted yet |
| Aktas 2024 Effects of design software program and manufacturing method on the marginal and internal adaptation of esthetic crowns for primary teeth:… PMID:38195256 | 2024 | this review only | not stated | not extracted yet |
| Broll 2025 Influence of digital crown design software on morphology, occlusal characteristics, fracture force and marginal fit. PMID:40947383 | 2026 | this review only | not stated | not extracted yet |
| Cakmak 2024 Can deep learning-designed anterior tooth-borne crown fulfill morphologic, aesthetic, and functional criteria in clinical practice? PMID:39326724 | 2024 | this review only | not stated | not extracted yet |
| Chau 2024 Accuracy of artificial intelligence-designed single-molar dental prostheses: A feasibility study. PMID:36631366 | 2024 | this review only | not stated | not extracted yet |
| Cho 2023 Time efficiency, occlusal morphology, and internal fit of anatomic contour crowns designed by dental software powered by generative… PMID:37804938 | 2023 | this review only | not stated | not extracted yet |
| Cho 2025 A comparison between commercially available artificial intelligence-based and conventional human expert-based digital workflows for… PMID:40628576 | 2026 | this review only | not stated | not extracted yet |
| Hlaing 2025 Artificial Intelligence-Driven Automated Design of Anterior and Posterior Crowns Under Diverse Occlusal Scenarios. PMID:40910757 | 2026 | this review only | not stated | not extracted yet |
| Sawangsri 2025 Acceptability and deviation of finish line detection and restoration contour design in single-unit crown: Comparative evaluation between 2… PMID:40234164 | 2025 | this review only | not stated | not extracted yet |
| Wang 2025 Comparative analysis of full crown morphology designed by artificial intelligence and dental technicians. PMID:40998103 | 2025 | this review only | not stated | not extracted yet |
| Win 2025 Fit accuracy of complete crowns fabricated by generative artificial intelligence design: a comparative clinical study. PMID:40919046 | 2025 | this review only | not stated | not extracted yet |
| Zhao 2026 Tooth generative adversarial network: Anatomical optimisation using Wasserstein generative adversarial network for tooth generation… DOI:10.1016/j.engappai.2026.114215 | 2026 | this review only | not stated | 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 | Shared studies | Jaccard |
|---|---|---|
| The application of artificial intelligence in the field of dental restoration for designing dental crowns: a meta-analysis. (2026) | 6 | 0.27 |
Review question
| Element | Planned (methods) | Found (results) |
|---|---|---|
| Population | Digital datasets of teeth requiring crown restoration (clinical cases, typodont models, digital casts; anterior and posterior) | Digital tooth datasets and crowns (in vitro models, digital casts, intraoral scans; 17 studies) |
| Intervention | AI-based automated crown design systems (ML, DL, GAN, diffusion, hybrid or knowledge-based) | GAN-based, knowledge-based and transformer-labeled AI crown design systems |
| Comparison | Conventional crown design (technician-driven, manual CAD, library-based CAD/CAM, virtual articulator) | Conventional CAD or technician-designed crowns |
| Outcomes | RMS deviation, occlusal contact accuracy, cusp morphology, internal fit; marginal adaptation, design time, functional occlusal performance | RMS deviation, cusp angle, occlusal contact points, profile discrepancy, internal fit, chamfer distance, marginal gap, design time, occlusal morphology (13 studies pooled) |
| Study designs | In vitro, in silico and clinical investigations | Mostly in vitro; one in vivo comparative clinical study |
| Timing | Not specified | Not specified |
AMSTAR 2 items
Two independent extractors rated each item. Their ratings are shown side by side because they have not been reconciled yet. The overall rating follows Shea et al. 2017: one critical flaw gives Low, more than one gives Critically Low.
| Item | Extractor A | Extractor B | Agree |
|---|---|---|---|
| 1Research question includes PICO components | Yes | Yes | yes |
| 2Protocol established before the reviewcritical | Partial Yes | Partial Yes | yes |
| 3Choice of study designs explained | No | No | yes |
| 4Comprehensive literature searchcritical | No | Partial Yes | no |
| 5Study selection in duplicate | Yes | Yes | yes |
| 6Data extraction in duplicate | Yes | Yes | yes |
| 7List of excluded studies with reasonscritical | No | No | yes |
| 8Included studies described in detail | Partial Yes | Partial Yes | yes |
| 9Risk of bias assessed satisfactorilycritical | NRSI: Partial Yes · RCT: N/A | RCT: N/A · NRSI: Yes | no |
| 10Funding of included studies reported | No | No | yes |
| 11Appropriate meta-analysis methodscritical | NRSI: No · RCT: N/A | RCT: N/A · NRSI: No | no |
| 12Impact of risk of bias on the pooled results | No | No | yes |
| 13Risk of bias accounted for in interpretationcritical | Yes | Yes | yes |
| 14Heterogeneity explained | Yes | Yes | yes |
| 15Publication bias investigatedcritical | No | No | yes |
| 16Conflicts of interest reported | Yes | Yes | yes |
| Overall | Critically Low | Critically Low | yes |