The Application of Artificial Intelligence in the Field of Dental Restoration for Designing Dental Crowns: A Meta-Analysis

The Application of Artificial Intelligence in the Field of Dental Restoration for Designing Dental Crowns: A Meta-Analysis | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article The Application of Artificial Intelligence in the Field of Dental Restoration for Designing Dental Crowns: A Meta-Analysis Jiaxuan Hu, Binding Bai, Yuzhou Wang, Bo Hu, Xiaoming Fu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8691105/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Background This meta-analysis was aimed at investigating the differences between dental crowns designed by artificial intelligence (AI) and those designed through traditional computer-aided design (CAD) processes to provide a reference for the clinical application of AI in the field of dental crown restoration. Methods Searches were conducted in PubMed, Web of Science, CENTRAL, EMBASE, WFPD, VIP, and CNKI to collect randomized controlled trials (RCTs) on AI-designed dental crowns and traditional CAD-based dental crowns. After the data were extracted and the risk of bias was assessed with the Cochrane Collaboration’s risk assessment tool, a meta-analysis was conducted to clarify the differences between AI-designed dental crowns and traditional CAD-based dental crowns. The search period was from the establishment of each database to January 2026. Two researchers independently screened the articles, extracted their basic information and assessed the risk of bias. The meta-analysis was conducted using Review Manager 5.3. Results A total of 12 articles were ultimately included. The meta-analysis revealed that the design time of the AI group was shorter than that of the traditional CAD group (mean difference, -279.27; 95% confidence interval, -423.18 to -135.36; P = 0.0001), and the occlusal accuracy of the former was better than that of the traditional CAD group (mean difference, -67.39; 95% confidence interval, -132.36 to -2.42; P = 0.04); however, no significant difference was observed between the occlusal morphology (mean difference, -0.02; 95% confidence interval, -0.06 to -0.02; P = 0.34), and the cusp angle designed in the AI group was smaller than that of the traditional CAD group (mean difference, 3.31; 95% confidence interval, 1.12 to 5.50; P = 0.003). Conclusions Compared with traditional CAD, AI significantly reduces the required design time while producing similar occlusal morphology results and demonstrating greater stability in occlusal accuracy. However, compared with that of the traditional CAD method, the cusp angle designed by AI still needs further optimization. Overall, as an auxiliary tool for dental crown design, AI design is suitable for clinical promotion and application. Nevertheless, it is necessary to continuously optimize the architecture of the AI algorithm and the performance of the model to enhance their applicability and service efficiency in the field of dental crown restoration, thereby providing technological support for digital dental restoration tasks. Artificial intelligence Computer-aided design Dental crown design Dental restoration Meta-analysis Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Background Tooth defects, as some of the most common clinical oral diseases, refer to damage or varying degrees of abnormalities on the surfaces or in the internal hard tissues of teeth. They not only directly affect the facial appearances and physiological functions (such as chewing) of patients but also have negative effects on the quality of life and mental health of patients[ 1 , 2 ]. In the field of prosthodontics, dental crowns, as a common fixed restoration method for tooth defects, have undergone an evolution process concerning their manufacturing technology from traditional artificial manufacturing to digital manufacturing. The traditional artificial manufacturing techniques (lost-wax casting) have dominated for a long time. However, they have significant limitations, such as being time-consuming, labor-intensive, and overly reliant on the operational experience and technical proficiency of skilled workers. These limitations make it difficult to meet the higher demands of modern stomatology regarding the precision, functionality and aesthetic effects of restorations. With the advancement of digital technology, computer-aided design/computer-aided manufacturing (CAD/CAM) technology has gradually become the mainstream method for producing dental crowns. Digital manufacturing technology supported by CAD/CAM has achieved a high degree of automation and precise control in the dental crown production process, significantly improving the accuracy and efficiency of dental crown production, shortening the production cycle, and reducing the reliance of the procedure on the experience of technicians[ 3 ]. Although CAD/CAM technology offers distinct advantages over the lost-wax casting process, in traditional CAD/CAM workflows, the crown design phase relies primarily on technicians using dental CAD software. This approach still requires significant manpower and time, particularly in complex cases where technicians must devote substantial hours to making meticulous adjustments. AI refers to the ability of algorithms encoded in information technology to learn from data. Its advantage lies in its ability to simulate human thinking, learn independently, solve problems, and achieve automation[ 4 ]. As an emerging technology, if AI is applied to dental crown design, algorithms can be used to simulate the thought processes of technicians, and automated design-based software programs can be developed to further save time and effort, improve the efficiency of design, and achieve automated and precise dental crown design. With the development of AI technology, many scholars have focused on applying AI to the design of dental crowns, but their conclusions vary. Chau et al. [ 5 ] reported that when AI was used to design single-crown restorations for molars, the morphological differences were smaller than those of natural teeth, demonstrating the feasibility of AI in a single-crown design scenario. Feng et al. [ 6 ] demonstrated that AI design not only provides enhanced efficiency but also automatically and accurately reconstructs the three-dimensional (3D) shapes of missing maxillary anterior tooth crowns. However, some studies have shown [ 7 – 9 ] that during the design process, AI may encounter dynamic interference, inaccurate automatic digital edge detection results, and the loss of some feature information during the 3D shape restoration procedure applied to the target dental crown. These issues require technicians to make adjustments and modifications later on; otherwise, doctors will need to spend a considerable amount of time on chairside adjustments, and the final clinical performance of the dental crown may even be affected. Therefore, it is important to conduct a meta-analysis to evaluate the differences between AI-designed dental crowns and traditional CAD-based dental crowns to provide a reference for the application of AI in the field of dental crown restoration. Methods This study adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. Search strategy From the establishment of each utilized database to January 2026, a literature retrieval procedure was conducted with respect to the application of AI technology for fabricating dental crown restorations in multiple databases, such as PubMed, Web of Science, Cochrane Central Register of Controlled Trials(CENTRAL), EMBASE, Chinese Medicine Premier's Wanfang database(WFPD), VIP Chinese Science and Technology Journal Databases (VIP), and China National Knowledge Infrastructure (CNKI), using a combination of subject terms and free terms. The search scope covered the relevant studies on AI-designed dental crowns and traditional CAD-based dental crowns. The search terms included “artificial intelligence”, “intelligence”, “computational intelligence”, “crown”, “crown appearance”, “crown morphology”, and “crown prostheses”. The search retrieval formula was as follows: ((((crown [Title/Abstract]) OR (crown appearance [Title/Abstract])) OR (crown morphology [Title/Abstract])) OR (crown prostheses [Title/Abstract])) AND (((artificial intelligence [Title/Abstract]) OR (intelligence [Title/Abstract])) OR (computational intelligence [Title/Abstract]). Inclusion and exclusion criteria The inclusion criteria were as follows: 1. research subjects: dental crowns; 2. research types: RCTs of AI-designed dental crowns and traditional CAD-based dental crowns; 3. publication languages: Chinese and English; 4. publication time: from the establishment of each electronic database to January 2026; and 5. outcome measures: design time, occlusal morphology, occlusal accuracy and cusp angle. The exclusion criteria were as follows: 1. reviews or animal experiments; 2. studies for which detailed data or the full text could not be obtained; 3. studies with obvious abnormalities in the relevant data, where no further information could be obtained by contacting the authors; 4. studies with incomplete data or for which the original data could not be extracted; and 5. studies lacking a control group. Study selection and data extraction Two researchers independently conducted the study screening and exclusion steps and ultimately determined the included studies through discussions and comparisons. If differences of opinion were encountered during the screening process and if no consensus could be reached through discussion, a third researcher arbitrated the decision. The extracted data included the name of the first author, year of publication, study type, study object, sample size, and outcome measures. Quality assessment The quality of the included studies was evaluated using Review Manager 5.3 software on the basis of the Cochrane risk of the provided bias assessment items. The evaluated risk levels included “low risk”, “high risk”, and “unclear”. We assessed and categorized each risk-of-bias evaluation according to the following criteria: low risk of bias: studies for which we identified 6 issues as “low risk”, moderate risk of bias: studies for which we identified 1 or more issues as “unclear”, and high risk of bias: studies for which we identified 1 or more issues as “high risk”. The assessment items included random sequence generation biases, allocation scheme concealment, blinding of the participants and staff, blinding of the result evaluation, and whether the data results were complete, etc. Statistical analysis Two researchers were responsible for exporting and processing the data. The articles were recorded in detail using NoteExpress software, and a meta-analysis was conducted with the help of Review Manager 5.3 software. In the meta-analysis, we calculated overall continuous variables estimates using the mean differences (MD) and the upper and lower limits of the 95% confidence intervals (CI) to assess overall efficacy from all the eligible studies.The heterogeneity was assessed by Q statistic ( P < 0.10 indicating significant heterogeneity), and I squared (I 2 ) statistic. An I 2 value of more than 50% represented high heterogeneity; thus, the random effect model would be adopted. I 2 less than 50% representing low heterogeneity, fixed-effects models were used. Statistical significance was declared if the P-value was < 0.05. Results Data selection A total of 576 articles were retrieved from the databases employed in this study, including 60 from PubMed, 147 from the Web of Science, 368 from EMBASE, and 1 from the CNKI. Moreover, 23 articles were retrieved manually. On this basis, 24 duplicate articles were identified and eliminated, and 575 articles were initially screened out. The researchers read the titles and abstracts of these articles, eliminated 552 articles on the basis of the principle of relevance, and then rescreened them to obtain 23 articles. Ultimately, based on the preset inclusion and exclusion criteria for the included studies, a detailed full-text study of these 23 articles was conducted, and 12 of them that satisfied the imposed requirements were identified for a subsequent quality risk assessment. The screening process employed in this study is shown in Fig. 1. Characteristics of the included studies This study ultimately included 12 articles. First, the basic information of each article was summarized, as shown in Table 1. Afterward, the Cochrane Collaboration’s risk assessment tool was used to assess the risk of bias on the basis of several evaluation indicators, including random sequence generation (selection bias), allocation concealment (selection bias), participant and researcher blinding (implementation bias), outcome evaluation blinding (detection bias), incomplete outcome data (loss bias), selective reporting (report bias), and other biases. Table 1 Basic characteristics of the included studies First Author Year Study Type Study Object Sample Size Outcome Measures E C Chen Y [10] 2022 RCT Dental Crown 12 12 Occlusal Surface Contour, Cusp Angle Kollmuss M [11] 2013 RCT Dental Crown 39 39 Occlusal Surface Contour Kollmuss M [12] 2016 RCT Dental Crown 22 22 Occlusal Surface Contour Litzenburger AP [13] 2013 RCT Dental Crown 5 25 Occlusal Surface Contour Chao JH [14] 2024 RCT Dental Crown 30 30 Cusp Angle Ding H [15] 2023 RCT Dental Crown 12 12 Cusp Angle Liu CM [16] 2024 RCT Dental Crown 12 12 Design Time Lei L [17] 2024 RCT Dental Crown 58 58 Design Time Ender A [18] 2011 RCT Dental Crown 12 12 Design Time Koudai Nagata [19] 2025 RCT Dental Crown 10 10 Design Time, the Accuracy of Occlusal Surface Liu CM [20] 2025 RCT Dental Crown 10 10 the Accuracy of Occlusal Surface Wu ZQ [21] 2025 RCT Dental Crown 33 33 Design Time, the Accuracy of Occlusal Surface Abbreviations: RCT: Randomized controlled trial; E: Experimental group; C: Control group Risk of bias The methodology and quality of the trials included in the review are presented in Fig. 2. Approximately half of the included studies did not report random sequence generation procedures. All the considered studies were judged to exhibit moderate risk of bias. Analysis results of the outcome measures Design time The 5 included studies compared the time required for designing dental crowns between the AI group and the traditional CAD group [16-19, 21]. The heterogeneity test results (I 2 =99%) indicated heterogeneity between the studies, so a random-effects model was used for the analysis. The results revealed that the design time of the AI group was significantly shorter than that of the traditional CAD group [MD=-279.27, 95% CI (-423.18, -135.36), P =0.0001] (Fig. 3). Occlusal morphology The 4 included studies analyzed the occlusal morphology of dental crowns designed by AI and the traditional CAD method [10-13]. A heterogeneity test (I 2 =85%) indicated heterogeneity between the studies; thus, a random-effects model was used for analysis purposes. The results revealed that there was no statistically significant difference between the occlusal morphology of the two groups [MD=-0.02, 95% CI (-0.06, -0.02), P=0.34] (Fig. 4). Occlusal a ccuracy The 3 included studies compared the accuracy of the occlusal surfaces of dental crowns designed by AI and the traditional CAD method [19-21]. A heterogeneity test (I 2 =97%) indicated heterogeneity between the studies; thus, a random-effects model was used for analysis purposes. The results revealed that the occlusal accuracy of the AI-designed dental crowns was better than that of the traditional CAD-based crowns [MD=-67.39, 95% CI (-132.36, -2.42), P =0.04] (Fig. 5). Cusp angle The 3 included studies analyzed the cusp angles of dental crowns designed by AI and the traditional CAD method [10, 14, 15]. A heterogeneity test (I 2 =0%) indicated extremely low heterogeneity between the studies; therefore, a fixed-effects model was used for analysis purposes. The results revealed that the cusp angles designed by AI were smaller than those designed by the traditional CAD method [MD=3.31, 95% CI (1.12, 5.50), P =0.003] (Fig. 6). Discussion Crown restoration is a widely used treatment method in the field of stomatology. The advent of CAD/CAM technology has greatly promoted technological innovation in this field. It has rapidly replaced traditional techniques such as lost-wax casting and ceramic stacking, gradually transforming cumbersome manual operations into efficient digital and mechanized process flows. Although CAD/CAM technology has many advantages, it still requires considerable manpower, material resources and time for dental crown design tasks. In addition, traditional CAD technology relies on manual design procedures, and the dental crowns manufactured through this approach still have certain limitations in terms of personalized effects. Clinically, problems such dental crowns with poor marginal fits and deviations in the designs of the occlusal and adjacent surfaces often occur, which usually require additional adjustments or remaking [22]. With the rapid development of computer technology and the advent of the big data era, the applications of AI design in dental crown design scenarios have gradually increased, injecting new vitality into CAD/CAM technology. By integrating AI algorithms into CAD/CAM systems and leveraging advanced deep learning (DL) algorithms and big data analyses, it is possible to automatically design dental crowns that are more accurate and highly simulate the shapes of natural teeth. This innovation has further enhanced the personalized customization levels of dental crowns. A total of 12 RCTs were included in this study. The experimental group and the control group were AI-designed dental crowns and traditional CAD-based dental crowns, respectively. A meta-analysis was conducted on the design time, occlusal morphology, occlusal accuracy, and cusp angle of AI-designed and traditional CAD-based dental crowns. This study first analyzed the time difference between AI-designed and traditional CAD-based dental crowns. The results showed that AI design had a significant advantage in terms of temporal efficiency. Compared with traditional manual labor, the advantages of AI mainly lie in its ultrahigh-speed data processing capabilities, its algorithm-driven stability, its continuous and efficient hardware design process, and the autonomous learning and evolution capabilities of deep neural networks [23]. The traditional CAD/CAM-based dental crown restoration and manufacturing process mainly relies on manual design, which usually takes a long time [24]. However, through automated and intelligent design techniques, AI design significantly shortens the design and adjustment time, yields improved work efficiency, and reduces the demand for manpower. In addition to the design time, the occlusal accuracy of a dental crown is equally important, as it directly affects the aesthetics and functionality of the restoration. The results of the present study were analyzed on the basis of two indicators: the occlusal morphology and the occlusal accuracy. The results revealed no significant difference between the occlusal morphology of the AI design and traditional CAD method. However, in terms of the occlusal accuracy, the AI design process is superior to traditional CAD method. The included studies on occlusal morphology adopted the volume/area method. The volume/area method is mainly used for analyzing the morphologies of 3D structures. It does not require the setting of reference points, has no related selection bias, makes morphological comparisons more standardized, and has a smaller impact on extreme values. The studies included in the meta-analysis of the occlusal accuracy adopted the fitting method. Through fitting software such as Geomagic, 3D alignment fitting was performed on the 3D images of the two objects via best-fit alignment. This automatic alignment method is widely used to align complex and irregularly shaped objects. These two results suggest that compared with traditional CAD method, AI design may have greater accuracy in terms of determining the morphologies of the occlusal surfaces of dental crowns. This might be related to the use of DL algorithms in AI technology. DL, as an important branch of AI, is widely used in various clinical tasks for automatically making decisions. DL models are constructed through artificial neural networks. Through multilayer convolutional neural networks and generative adversarial networks, datasets can be classified and learned at multiple levels. DL also automatically extracts the learning features contained in the input data to improve the quality and accuracy of the output [25]. Farook et al. [26] employed a 3D convolutional neural network model to conduct deep learning and an analysis on the 3D preparation data obtained through digital intraoral scanning technology, achieving personalized designs for some crowns with an accuracy of up to 83%. DL algorithms can automatically extract the features of tooth morphologies by learning from a large amount of data and can conduct multilevel optimization during the design process, thereby improving the accuracy of dental crown morphologies. This fully demonstrates the potential and application prospects of DL algorithms in the field of dental restoration. Although AI has certain advantages regarding the design of the morphologies of the occlusal surfaces of dental crowns, this study revealed that the designs of the cusp angles of dental crowns differ from those of the traditional CAD method. The cusp angle refers to the angle between the cusp plane and the cusp of the longitudinal axis of a tooth. When a dental crown is designed, the cusp angle is among the key indicators for evaluating the quality of the design. It not only affects the aesthetic effect of the dental crown but is also related to its anti-fracture ability. When most dental crowns experience catastrophic overall fractures, such fractures are clinically difficult to repair. Scholars believe that a cusp angle range of 50° to 70° is clinically acceptable [28, 29, 30]. This study revealed that the cusp angles designed by AI are slightly larger than those designed by the traditional CAD method. However, the cusp angles designed by traditional CAD are closer to those of the original teeth. This might be related to the following factors. When AI design addresses high-dimensional objects (such as 3D datasets), the vector representation method induces generalization errors. The vertical-dimensional data obtained by intraoral scanners lack systematic consistency, resulting in errors that affect mainly the determination of vertical positions and randomness [27]. This results in AI-designed dental crowns having larger cusp angles than those of the original teeth, reflecting reduced steepness in the functional cusps. In contrast, although the traditional CAD method relies on the experience of technicians and the selection of CAD software templates, it can flexibly adjust cusp angles according to the actual situation of the patient's teeth, avoiding errors caused by algorithmic and data issues in AI design scenarios. Furthermore, AI design relies on a large amount of training data. However, the sample sizes used in the existing studies are far from those required for developing clinically applicable AI, and if the employed data sources are biased, the quality of the results varies. This might also be one of the reasons for the deficiencies of this technique in the detailed design of the cusp angles of dental crowns. Simultaneously, several limitations of the present study should be acknowledged. First, AI, which is a new technique in dental crown design, lacks many primary studies associated with it, as we found only 12 articles that could be included in our study. Second, we noticed that there were certain degrees of heterogeneity among some of the studies. Heterogeneity is related to the presence of confounding factors within and among the included studies, such as tooth position and design software differences. Third, all included studies were assessed as having a moderate risk of bias. Given the small number of articles, we did not evaluate their publication biases or perform sensitivity analyses. Fourth, we determined that certain research metrics, such as occlusal contact and the absolute marginal discrepancy, serve as valuable analytical indicators. However, owing to the insufficient number of relevant studies, a systematic analysis on this topic was not feasible. Considering the limitations described previously, future research should incorporate additional evaluation indicators and conduct more rigorous controlled trials. These measures will help assess the advantages and disadvantages of AI design in the field of dental crown restoration, ultimately developing a standardized evaluation framework for AI applications in this field. Conclusion In summary, compared with the traditional CAD method, AI design can significantly reduce time consumption levels, generate occlusal morphology with similar effects for dental crowns, and perform more stably in terms of the occlusal accuracy. However, there is still room for improving upon the traditional CAD method regarding the design of the cusp angles of dental crowns. Overall, AI is suitable as an auxiliary tool for dental crown design tasks and is recommended for clinical promotion. However, it is still necessary to continuously optimize the algorithmic architectures and model performance of AI to enhance its applicability and service efficiency in the field of dental crown restoration and provide technical support for digital dental restoration scenarios. Abbreviations AI Artificial intelligence CAD Computer-aided design RCT Randomized controlled trial CAD/CAM Computer-aided design/Computer-aided manufacturing 3D Three-dimensional PRISMA Preferred reporting items for systematic reviews and meta-analysis MD Mean difference CI Confidence interval DL Deep learning Declarations Ethics approval and consent to participate Not applicable. Consent for publication Not applicable. Availability of data and materials All Data generated or analysed during this study are included in this published article. Competing interests The authors declare that they have no competing interests. Funding This work was supported by funding from Project of Chongqing Higher Education and Teaching Reform (grant numbers: 193070). Authors’ Contributions JX H and YZ W extracted, analyzed and interpreted the data. JX H and BD B drafted and edited the manuscript. XM F and B H designed the study and revised the manuscript. All authors have read and approved the manuscript. Acknowledgments Not applicable. References Hawthan M, Larsson C, Chrcanovic BR. Survival of fixed prosthetic restorations on vital and nonvital teeth: A systematic review. J Prosthodont. 2024;33(2):110–22. Chen WW, Liu YM, Liu LC, Wang ZW. Effect of all-ceramic crown and onlay on the restoration of posterior tooth defects and their influence on masticatory function and gingival condition. J Clin Exp Med. 2023;22(3):326–9. Wang SF, Song CH, Yang YQ. Rapid manufacturing technology and progress of digital dental restorations. Mater Res Appl. 2012;6(2):91–5. Wang T, Song HB, Wang Q, Hou YF, Liu HL, Zhang L. Brief introduction and implications of WHO guidance on ethics & governance of artificial intelligence for health. Chin J Pharmacovigil. 2024;21(8):906–9. Chau RCW, Hsung RT, McGrath C, Pow EHN, Lam WYH. Accuracy of artificial intelligence-designed single-molar dental prostheses: A feasibility study. J Prosthet Dent. 2024;131(6):1111–7. Feng Y, Tao B, Fan J, Wang S, Mo J, Wu Y, Liang Q. 3D reconstruction for maxillary anterior tooth crown based on shape and pose estimation networks. Int J Comput Assist Radiol Surg. 2023;18(8):1405–16. Tian S, Huang R, Li Z, Fiorenza L, Dai N, Sun Y, Ma H. A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction. J Healthc Eng. 2022, 2022:1933617. Tian S, Wang M, Dai N, Ma H, Li L, Fiorenza L, Sun Y, Li Y. DCPR-GAN: Dental Crown Prosthesis Restoration Using Two-Stage Generative Adversarial Networks. IEEE J Biomed Health Inf. 2022;26(1):151–60. Bohner LO, Neto PT, Ahmed AS, Mori M, Laganá DC, Sesma N. CEREC Chairside System to Register and Design the Occlusion in Restorative Dentistry: A Systematic Literature Review. J esthetic Restor dentistry: official publication Am Acad Esthetic Dentistry [et al]. 2016;28(4):208–20. Chen Y, Lee JKY, Kwong G, Pow EHN, Tsoi JKH. Morphology and fracture behavior of lithium disilicate dental crowns designed by human and knowledge-based AI. J Mech Behav Biomed Mater. 2022;131:105256. Kollmuss M, Jakob FM, Kirchner HG, Ilie N, Hickel R, Huth KC. Comparison of biogenerically reconstructed and waxed-up complete occlusal surfaces with respect to the original tooth morphology. Clin Oral Investig. 2013;17(3):851–7. Kollmuss M, Kist S, Goeke JE, Hickel R, Huth KC. Comparison of chairside and laboratory CAD/CAM to conventional produced all-ceramic crowns regarding morphology, occlusion, and aesthetics. Clin Oral Investig. 2016;20(4):791–7. Litzenburger AP, Hickel R, Richter MJ, Mehl AC, Probst FA. Fully automatic CAD design of the occlusal morphology of partial crowns compared to dental technicians' design. Clin Oral Investig. 2013;17(2):491–6. Cho JH, Cakmak G, Yi Y, Yoon HI, Yilmaz B, Schimmel M. Tooth morphology, internal fit, occlusion and proximal contacts of dental crowns designed by deep learning-based dental software: A comparative study. J Dent. 2024;141:104830. Ding H, Cui Z, Maghami E, Chen Y, Matinlinna JP, Pow EHN, Fok ASL, Burrow MF, Wang W, Tsoi JKH. Morphology and mechanical performance of dental crown designed by 3D-DCGAN. Dent Mater. 2023;39(3):320–32. Liu CM, Lin WC, Lee SY. Evaluation of the efficiency, trueness, and clinical application of novel artificial intelligence design for dental crown prostheses. Dent Mater. 2024;40(1):19–27. Liu L, Shen LL, Ding X. Comparative clinical outcomes of AI-designed versus conventional CAD/CAM-designed zirconia full-crown restoration of molar defects. Oral Biomed. 2024;15(5):276–80. Ender A, Mormann WH, Mehl A. Efficiency of a mathematical model in generating CAD/CAM-partial crowns with natural tooth morphology. Clin Oral Investig. 2011;15(2):283–9. Nagata K, Inoue E, Nakashizu T, Seimiya K, Atsumi M, Kimoto K, Kuroda S, Hoshi N. Verification of the accuracy and design time of crowns designed with artificial intelligence. J Adv Prosthodont. 2025;17(1):1–10. Liu CM, Lu TY, Wang CS, Feng SW, Lin YC, Lee SY, Lin WC. Evaluation of the accuracy, occlusal contact and clinical applications of zirconia crowns using artificial intelligence design versus human design. J Dent Sci. 2025;20(3):1665–72. Wu Z, Zhang C, Ye X, Dai Y, Zhao J, Zhao W, Zheng Y. Comparison of the Efficacy of Artificial Intelligence-Powered Software in Crown Design: An In Vitro Study. Int Dent J. 2025;75(1):127–34. Alqahtani F. Marginal fit of all-ceramic crowns fabricated using two extraoral CAD/CAM systems in comparison with the conventional technique. Clin Cosmet Investig Dent. 2017;9:13–8. Naskar S, Sharma S, Kuotsu K, Halder S, Pal G, Saha S, Mondal S, Biswas UK, Jana M, Bhattacharjee S. The biomedical applications of artificial intelligence: an overview of decades of research. J Drug Target 2025:1–32. Blatz MB, Conejo J. The Current State of Chairside Digital Dentistry and Materials. Dent Clin North Am. 2019;63(2):175–97. Park WJ, Park JB. History and application of artificial neural networks in dentistry. Eur J Dent. 2018;12(4):594–601. Farook TH, Ahmed S, Jamayet NB, Rashid F, Barman A, Sidhu P, Patil P, Lisan AM, Eusufzai SZ, Dudley J, et al. Computer-aided design and 3-dimensional artificial/convolutional neural network for digital partial dental crown synthesis and validation. Sci Rep. 2023;13(1):1561. Mehl A, Blanz V, Hickel R. A new mathematical process for the calculation of average forms of teeth. J Prosthet Dent. 2005;94(6):561–6. Additional Declarations No competing interests reported. Supplementary Files Table1.docx PRISMA2020checklist.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 26 Mar, 2026 Reviews received at journal 24 Mar, 2026 Reviews received at journal 23 Mar, 2026 Reviewers agreed at journal 22 Mar, 2026 Reviewers agreed at journal 18 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers invited by journal 06 Mar, 2026 Editor assigned by journal 03 Feb, 2026 Editor invited by journal 02 Feb, 2026 Submission checks completed at journal 01 Feb, 2026 First submitted to journal 01 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8691105","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":601856570,"identity":"623e68b1-6be2-4b6f-b91c-b0d0739df889","order_by":0,"name":"Jiaxuan Hu","email":"","orcid":"","institution":"Chongqing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiaxuan","middleName":"","lastName":"Hu","suffix":""},{"id":601856571,"identity":"eb42319d-e6c3-4f6c-8859-c0ffee772be6","order_by":1,"name":"Binding Bai","email":"","orcid":"","institution":"Chongqing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Binding","middleName":"","lastName":"Bai","suffix":""},{"id":601856572,"identity":"c2de6cd2-426a-4e36-b84d-18af36e2ff18","order_by":2,"name":"Yuzhou Wang","email":"","orcid":"","institution":"Chongqing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Yuzhou","middleName":"","lastName":"Wang","suffix":""},{"id":601856573,"identity":"79e0cb08-3ea1-4131-9738-5b98e5c546a4","order_by":3,"name":"Bo Hu","email":"","orcid":"","institution":"Chongqing Medical University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Hu","suffix":""},{"id":601856574,"identity":"51be061d-3b24-4087-b260-967501780039","order_by":4,"name":"Xiaoming Fu","email":"data:image/png;base64,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","orcid":"","institution":"Chongqing Medical University","correspondingAuthor":true,"prefix":"","firstName":"Xiaoming","middleName":"","lastName":"Fu","suffix":""}],"badges":[],"createdAt":"2026-01-25 08:23:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8691105/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8691105/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104375156,"identity":"da2f0332-ff61-4318-a41e-566769a1ad88","added_by":"auto","created_at":"2026-03-11 06:13:02","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":445669,"visible":true,"origin":"","legend":"\u003cp\u003eThe flow chart of the study screening process\u003c/p\u003e","description":"","filename":"Fig.1.png","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/90f4647e3aded418a2ca6562.png"},{"id":104405353,"identity":"94119718-3b22-49c2-937c-3c31aa5daa7e","added_by":"auto","created_at":"2026-03-11 12:22:41","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":701635,"visible":true,"origin":"","legend":"\u003cp\u003eRisk-of-bias evaluations of the included studies. The authors’ judgments about each risk-of-bias item were reviewed and presented as percentages across all included studies. Red, yellow, and green indicate high, unclear, and low risk of bias, respectively\u003c/p\u003e","description":"","filename":"Fig.2.png","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/e18d702e8be5ff8d1c36f6fa.png"},{"id":104375163,"identity":"bb7e6635-ef31-48a2-8579-649a5b58b7fe","added_by":"auto","created_at":"2026-03-11 06:13:02","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":517999,"visible":true,"origin":"","legend":"\u003cp\u003eForest plot comparing the design time of the AI-designed dental crowns and traditional CAD-based dental crowns\u003c/p\u003e","description":"","filename":"Fig.3.png","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/38b3a62f92a7ad81c04319fb.png"},{"id":104405705,"identity":"2d5d6e31-4986-4e4b-aca2-48044f473dd8","added_by":"auto","created_at":"2026-03-11 12:23:38","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":490519,"visible":true,"origin":"","legend":"\u003cp\u003eForest plot comparing the occlusal morphology of the AI-designed dental crowns and traditional CAD-based dental crowns\u003c/p\u003e","description":"","filename":"Fig.4.png","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/8a0877216f0afbc907c1e935.png"},{"id":104375160,"identity":"dd71b78f-017f-4db8-a39c-4abc897415a4","added_by":"auto","created_at":"2026-03-11 06:13:02","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":473760,"visible":true,"origin":"","legend":"\u003cp\u003eForest plot comparing the occlusal accuracy of the AI-designed dental crowns and traditional CAD-based dental crowns\u003c/p\u003e","description":"","filename":"Fig.5.png","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/7144d1359c124b3029bbb88d.png"},{"id":104375161,"identity":"16f86b53-13e8-4628-9e2b-363b0f0c0823","added_by":"auto","created_at":"2026-03-11 06:13:02","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":517999,"visible":true,"origin":"","legend":"\u003cp\u003eForest plot comparing the cusp angles of the AI-designed dental crowns and traditional CAD-based dental crowns\u003c/p\u003e","description":"","filename":"Fig.6.png","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/01a7e83e6f9a0f04d71bd434.png"},{"id":104784226,"identity":"ef4cb7d2-e42b-4b91-adf7-f7914ce9cbf8","added_by":"auto","created_at":"2026-03-17 08:05:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4487420,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/a4bde77a-1eb9-4579-877c-b84b3fe7baee.pdf"},{"id":104779974,"identity":"b9894ac1-38da-4337-9416-dc0343c6b6fb","added_by":"auto","created_at":"2026-03-17 07:48:43","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":34122,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/538087640fabf08aac806e8a.docx"},{"id":104375162,"identity":"b4a0a736-26d3-4879-98d5-3c5b4e4f4598","added_by":"auto","created_at":"2026-03-11 06:13:02","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":271613,"visible":true,"origin":"","legend":"","description":"","filename":"PRISMA2020checklist.docx","url":"https://assets-eu.researchsquare.com/files/rs-8691105/v1/492fd9a990f0a36cf615c513.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"The Application of Artificial Intelligence in the Field of Dental Restoration for Designing Dental Crowns: A Meta-Analysis","fulltext":[{"header":"Background","content":"\u003cp\u003eTooth defects, as some of the most common clinical oral diseases, refer to damage or varying degrees of abnormalities on the surfaces or in the internal hard tissues of teeth. They not only directly affect the facial appearances and physiological functions (such as chewing) of patients but also have negative effects on the quality of life and mental health of patients[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. In the field of prosthodontics, dental crowns, as a common fixed restoration method for tooth defects, have undergone an evolution process concerning their manufacturing technology from traditional artificial manufacturing to digital manufacturing. The traditional artificial manufacturing techniques (lost-wax casting) have dominated for a long time. However, they have significant limitations, such as being time-consuming, labor-intensive, and overly reliant on the operational experience and technical proficiency of skilled workers. These limitations make it difficult to meet the higher demands of modern stomatology regarding the precision, functionality and aesthetic effects of restorations. With the advancement of digital technology, computer-aided design/computer-aided manufacturing (CAD/CAM) technology has gradually become the mainstream method for producing dental crowns. Digital manufacturing technology supported by CAD/CAM has achieved a high degree of automation and precise control in the dental crown production process, significantly improving the accuracy and efficiency of dental crown production, shortening the production cycle, and reducing the reliance of the procedure on the experience of technicians[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Although CAD/CAM technology offers distinct advantages over the lost-wax casting process, in traditional CAD/CAM workflows, the crown design phase relies primarily on technicians using dental CAD software. This approach still requires significant manpower and time, particularly in complex cases where technicians must devote substantial hours to making meticulous adjustments.\u003c/p\u003e \u003cp\u003eAI refers to the ability of algorithms encoded in information technology to learn from data. Its advantage lies in its ability to simulate human thinking, learn independently, solve problems, and achieve automation[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. As an emerging technology, if AI is applied to dental crown design, algorithms can be used to simulate the thought processes of technicians, and automated design-based software programs can be developed to further save time and effort, improve the efficiency of design, and achieve automated and precise dental crown design. With the development of AI technology, many scholars have focused on applying AI to the design of dental crowns, but their conclusions vary. Chau et al. [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e] reported that when AI was used to design single-crown restorations for molars, the morphological differences were smaller than those of natural teeth, demonstrating the feasibility of AI in a single-crown design scenario. Feng et al. [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] demonstrated that AI design not only provides enhanced efficiency but also automatically and accurately reconstructs the three-dimensional (3D) shapes of missing maxillary anterior tooth crowns. However, some studies have shown [\u003cspan additionalcitationids=\"CR8\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] that during the design process, AI may encounter dynamic interference, inaccurate automatic digital edge detection results, and the loss of some feature information during the 3D shape restoration procedure applied to the target dental crown. These issues require technicians to make adjustments and modifications later on; otherwise, doctors will need to spend a considerable amount of time on chairside adjustments, and the final clinical performance of the dental crown may even be affected.\u003c/p\u003e \u003cp\u003eTherefore, it is important to conduct a meta-analysis to evaluate the differences between AI-designed dental crowns and traditional CAD-based dental crowns to provide a reference for the application of AI in the field of dental crown restoration.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003eThis study adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eSearch strategy\u003c/h2\u003e \u003cp\u003eFrom the establishment of each utilized database to January 2026, a literature retrieval procedure was conducted with respect to the application of AI technology for fabricating dental crown restorations in multiple databases, such as PubMed, Web of Science, Cochrane Central Register of Controlled Trials(CENTRAL), EMBASE, Chinese Medicine Premier's Wanfang database(WFPD), VIP Chinese Science and Technology Journal Databases (VIP), and China National Knowledge Infrastructure (CNKI), using a combination of subject terms and free terms. The search scope covered the relevant studies on AI-designed dental crowns and traditional CAD-based dental crowns. The search terms included \u0026ldquo;artificial intelligence\u0026rdquo;, \u0026ldquo;intelligence\u0026rdquo;, \u0026ldquo;computational intelligence\u0026rdquo;, \u0026ldquo;crown\u0026rdquo;, \u0026ldquo;crown appearance\u0026rdquo;, \u0026ldquo;crown morphology\u0026rdquo;, and \u0026ldquo;crown prostheses\u0026rdquo;.\u003c/p\u003e \u003cp\u003eThe search retrieval formula was as follows:\u003c/p\u003e \u003cp\u003e((((crown [Title/Abstract]) OR (crown appearance [Title/Abstract])) OR (crown morphology [Title/Abstract])) OR (crown prostheses [Title/Abstract])) AND (((artificial intelligence [Title/Abstract]) OR (intelligence [Title/Abstract])) OR (computational intelligence [Title/Abstract]).\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eInclusion and exclusion criteria\u003c/h3\u003e\n\u003cp\u003eThe inclusion criteria were as follows: 1. research subjects: dental crowns; 2. research types: RCTs of AI-designed dental crowns and traditional CAD-based dental crowns; 3. publication languages: Chinese and English; 4. publication time: from the establishment of each electronic database to January 2026; and 5. outcome measures: design time, occlusal morphology, occlusal accuracy and cusp angle.\u003c/p\u003e \u003cp\u003eThe exclusion criteria were as follows: 1. reviews or animal experiments; 2. studies for which detailed data or the full text could not be obtained; 3. studies with obvious abnormalities in the relevant data, where no further information could be obtained by contacting the authors; 4. studies with incomplete data or for which the original data could not be extracted; and 5. studies lacking a control group.\u003c/p\u003e\n\u003ch3\u003eStudy selection and data extraction\u003c/h3\u003e\n\u003cp\u003eTwo researchers independently conducted the study screening and exclusion steps and ultimately determined the included studies through discussions and comparisons. If differences of opinion were encountered during the screening process and if no consensus could be reached through discussion, a third researcher arbitrated the decision. The extracted data included the name of the first author, year of publication, study type, study object, sample size, and outcome measures.\u003c/p\u003e\n\u003ch3\u003eQuality assessment\u003c/h3\u003e\n\u003cp\u003eThe quality of the included studies was evaluated using Review Manager 5.3 software on the basis of the Cochrane risk of the provided bias assessment items. The evaluated risk levels included \u0026ldquo;low risk\u0026rdquo;, \u0026ldquo;high risk\u0026rdquo;, and \u0026ldquo;unclear\u0026rdquo;. We assessed and categorized each risk-of-bias evaluation according to the following criteria: low risk of bias: studies for which we identified 6 issues as \u0026ldquo;low risk\u0026rdquo;, moderate risk of bias: studies for which we identified 1 or more issues as \u0026ldquo;unclear\u0026rdquo;, and high risk of bias: studies for which we identified 1 or more issues as \u0026ldquo;high risk\u0026rdquo;. The assessment items included random sequence generation biases, allocation scheme concealment, blinding of the participants and staff, blinding of the result evaluation, and whether the data results were complete, etc.\u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eTwo researchers were responsible for exporting and processing the data. The articles were recorded in detail using NoteExpress software, and a meta-analysis was conducted with the help of Review Manager 5.3 software. In the meta-analysis, we calculated overall continuous variables estimates using the mean differences (MD) and the upper and lower limits of the 95% confidence intervals (CI) to assess overall efficacy from all the eligible studies.The heterogeneity was assessed by Q statistic (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.10 indicating significant heterogeneity), and I squared (I\u003csup\u003e2\u003c/sup\u003e) statistic. An I\u003csup\u003e2\u003c/sup\u003e value of more than 50% represented high heterogeneity; thus, the random effect model would be adopted. I\u003csup\u003e2\u003c/sup\u003e less than 50% representing low heterogeneity, fixed-effects models were used. Statistical significance was declared if the P-value was \u0026lt;\u0026thinsp;0.05.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003eData selection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 576 articles were retrieved from the databases employed in this study, including 60 from PubMed, 147 from the Web of Science, 368 from EMBASE, and 1 from the CNKI. Moreover, 23 articles were retrieved manually. On this basis, 24 duplicate articles were identified and eliminated, and 575 articles were initially screened out. The researchers read the titles and abstracts of these articles, eliminated 552 articles on the basis of the principle of relevance, and then rescreened them to obtain 23 articles. Ultimately, based on the preset inclusion and exclusion criteria for the included studies, a detailed full-text study of these 23 articles was conducted, and 12 of them that satisfied the imposed requirements were identified for a subsequent quality risk assessment. The screening process employed in this study is shown in Fig. \u0026nbsp;1.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCharacteristics of\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003ethe\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eincluded studies\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study ultimately included 12 articles. First, the basic information of each article was summarized, as shown in Table 1. Afterward, the Cochrane Collaboration\u0026rsquo;s risk assessment tool was used to assess the risk of bias on the basis of several evaluation indicators, including random sequence generation (selection bias), allocation concealment (selection bias), participant and researcher blinding (implementation bias), outcome evaluation blinding (detection bias), incomplete outcome data (loss bias), selective reporting (report bias), and other biases.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1\u003c/strong\u003e Basic characteristics of the included studies\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"595\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 136px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFirst Author\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 46px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eYear\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 86px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStudy Type\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStudy Object\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" style=\"width: 89px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSample Size\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 143px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOutcome Measures\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eE\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eChen Y [10]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2022\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eOcclusal Surface Contour, Cusp Angle\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eKollmuss M [11]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2013\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eOcclusal Surface Contour\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eKollmuss M [12]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2016\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eOcclusal Surface Contour\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eLitzenburger AP [13]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2013\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eOcclusal Surface Contour\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eChao JH [14]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2024\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eCusp Angle\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eDing H [15]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2023\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eCusp Angle\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eLiu CM [16]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2024\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eDesign Time\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eLei L [17]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2024\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e58\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e58\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eDesign Time\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eEnder A [18]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2011\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eDesign Time\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eKoudai Nagata [19]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2025\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eDesign Time, the Accuracy of Occlusal Surface\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eLiu CM [20]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2025\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003ethe Accuracy of\u0026nbsp;Occlusal\u0026nbsp;Surface\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 136px;\"\u003e\n \u003cp\u003eWu ZQ [21]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e2025\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 86px;\"\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eDental Crown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 44px;\"\u003e\n \u003cp\u003e33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 45px;\"\u003e\n \u003cp\u003e33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 143px;\"\u003e\n \u003cp\u003eDesign Time, the Accuracy of Occlusal Surface\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eAbbreviations: RCT: Randomized controlled trial; E: Experimental group; C: Control group\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRisk of bias\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe methodology and quality of the trials included in the review are presented in Fig. 2. Approximately half of the included studies did not report random sequence generation procedures. All the considered studies were judged to exhibit moderate risk of bias.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAnalysis results of the outcome measures\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDesign time\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe 5 included studies compared the time required for designing dental crowns between the AI group and the traditional CAD group [16-19, 21]. The heterogeneity test results (I\u003csup\u003e2\u003c/sup\u003e=99%) indicated heterogeneity between the studies, so a random-effects model was used for the analysis. The results revealed that the design time of the AI group was significantly shorter than that of the traditional CAD group [MD=-279.27, 95% CI (-423.18, -135.36), \u003cem\u003eP\u003c/em\u003e=0.0001] (Fig. 3).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eOcclusal\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003emorphology\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe 4 included studies analyzed the occlusal morphology of dental crowns designed by AI and the traditional CAD method [10-13]. A heterogeneity test (I\u003csup\u003e2\u003c/sup\u003e=85%) indicated heterogeneity between the studies; thus, a random-effects model was used for analysis purposes. The results revealed that there was no statistically significant difference between the occlusal morphology of the two groups [MD=-0.02, 95% CI (-0.06, -0.02), P=0.34] (Fig. 4).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eOcclusal a\u003c/strong\u003e\u003cstrong\u003eccuracy\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe 3 included studies compared the accuracy of the occlusal surfaces of dental crowns designed by AI and the traditional CAD method [19-21]. A heterogeneity test (I\u003csup\u003e2\u003c/sup\u003e=97%) indicated heterogeneity between the studies; thus, a random-effects model was used for analysis purposes. The results revealed that the occlusal accuracy of the AI-designed dental crowns was better than that of the traditional CAD-based crowns [MD=-67.39, 95% CI (-132.36, -2.42), \u003cem\u003eP\u003c/em\u003e=0.04] (Fig. 5).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCusp angle\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe 3 included studies analyzed the cusp angles of dental crowns designed by AI and the traditional CAD method [10, 14, 15]. A heterogeneity test (I\u003csup\u003e2\u003c/sup\u003e=0%) indicated extremely low heterogeneity between the studies; therefore, a fixed-effects model was used for analysis purposes. The results revealed that the cusp angles designed by AI were smaller than those designed by the traditional CAD method [MD=3.31, 95% CI (1.12, 5.50), \u003cem\u003eP\u003c/em\u003e=0.003] (Fig. 6).\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eCrown restoration is a widely used treatment method in the field of stomatology. The advent of CAD/CAM technology has greatly promoted technological innovation in this field. It has rapidly replaced traditional techniques such as lost-wax casting and ceramic stacking, gradually transforming cumbersome manual operations into efficient digital and mechanized process flows. Although CAD/CAM technology has many advantages, it still requires considerable manpower, material resources and time for dental crown design tasks. In addition, traditional CAD technology relies on manual design procedures, and the dental crowns manufactured through this approach still have certain limitations in terms of personalized effects. Clinically, problems such dental crowns with poor marginal fits and deviations in the designs of the occlusal and adjacent surfaces often occur, which usually require additional adjustments or remaking [22]. With the rapid development of computer technology and the advent of the big data era, the applications of AI design in dental crown design scenarios have gradually increased, injecting new vitality into CAD/CAM technology. By integrating AI algorithms into CAD/CAM systems and leveraging advanced deep learning (DL) algorithms and big data analyses, it is possible to automatically design dental crowns that are more accurate and highly simulate the shapes of natural teeth. This innovation has further enhanced the personalized customization levels of dental crowns. A total of 12 RCTs were included in this study. The experimental group and the control group were AI-designed dental crowns and traditional CAD-based dental crowns, respectively. A meta-analysis was conducted on the design time, occlusal morphology, occlusal accuracy, and cusp angle of AI-designed and traditional CAD-based dental crowns.\u003c/p\u003e\n\u003cp\u003eThis study first analyzed the time difference between AI-designed and traditional CAD-based dental crowns. The results showed that AI design had a significant advantage in terms of temporal efficiency. Compared with traditional manual labor, the advantages of AI mainly lie in its ultrahigh-speed data processing capabilities, its algorithm-driven stability, its continuous and efficient hardware design process, and the autonomous learning and evolution capabilities of deep neural networks [23]. The traditional CAD/CAM-based dental crown restoration and manufacturing process mainly relies on manual design, which usually takes a long time [24]. However, through automated and intelligent design techniques, AI design significantly shortens the design and adjustment time, yields improved work efficiency, and reduces the demand for manpower.\u003c/p\u003e\n\u003cp\u003eIn addition to the design time, the occlusal accuracy of a dental crown is equally important, as it directly affects the aesthetics and functionality of the restoration. The results of the present study were analyzed on the basis of two indicators: the occlusal morphology and the occlusal accuracy. The results revealed no significant difference between the occlusal morphology of the AI design and traditional CAD method. However, in terms of the occlusal accuracy, the AI design process is superior to traditional CAD method. The included studies on occlusal morphology adopted the volume/area method. The volume/area method is mainly used for analyzing the morphologies of 3D structures. It does not require the setting of reference points, has no related selection bias, makes morphological comparisons more standardized, and has a smaller impact on extreme values. The studies included in the meta-analysis of the occlusal accuracy adopted the fitting method. Through fitting software such as Geomagic, 3D alignment fitting was performed on the 3D images of the two objects via best-fit alignment. This automatic alignment method is widely used to align complex and irregularly shaped objects. These two results suggest that compared with traditional CAD method, AI design may have greater accuracy in terms of determining the morphologies of the occlusal surfaces of dental crowns. This might be related to the use of DL algorithms in AI technology. DL, as an important branch of AI, is widely used in various clinical tasks for automatically making decisions. DL models are constructed through artificial neural networks. Through multilayer convolutional neural networks and generative adversarial networks, datasets can be classified and learned at multiple levels. DL also automatically extracts the learning features contained in the input data to improve the quality and accuracy of the output [25]. Farook et al. [26] employed a 3D convolutional neural network model to conduct deep learning and an analysis on the 3D preparation data obtained through digital intraoral scanning technology, achieving personalized designs for some crowns with an accuracy of up to 83%. DL algorithms can automatically extract the features of tooth morphologies by learning from a large amount of data and can conduct multilevel optimization during the design process, thereby improving the accuracy of dental crown morphologies. This fully demonstrates the potential and application prospects of DL algorithms in the field of dental restoration.\u003c/p\u003e\n\u003cp\u003eAlthough AI has certain advantages regarding the design of the morphologies of the occlusal surfaces of dental crowns, this study revealed that the designs of the cusp angles of dental crowns differ from those of the traditional CAD method. The cusp angle refers to the angle between the cusp plane and the cusp of the longitudinal axis of a tooth. When a dental crown is designed, the cusp angle is among the key indicators for evaluating the quality of the design. It not only affects the aesthetic effect of the dental crown but is also related to its anti-fracture ability. When most dental crowns experience catastrophic overall fractures, such fractures are clinically difficult to repair. Scholars believe that a cusp angle range of 50° to 70° is clinically acceptable\u0026nbsp;[28, 29, 30]. This study revealed that the cusp angles designed by AI are slightly larger than those designed by the traditional CAD method. However, the cusp angles designed by traditional CAD are closer to those of the original teeth. This might be related to the following factors. When AI design addresses high-dimensional objects (such as 3D datasets), the vector representation method induces generalization errors. The vertical-dimensional data obtained by intraoral scanners lack systematic consistency, resulting in errors that affect mainly the determination of vertical positions and randomness [27]. This results in AI-designed dental crowns having larger cusp angles\u0026nbsp;than\u0026nbsp;those of the original teeth, reflecting reduced steepness in the functional cusps. In contrast, although the traditional CAD method relies on the experience of technicians and the selection of CAD software templates, it can flexibly adjust cusp angles according to the actual situation of the patient's teeth, avoiding errors caused by algorithmic and data issues in AI design scenarios. Furthermore, AI design relies on a large amount of training data. However, the sample sizes used in the existing studies are far from those required for developing clinically applicable AI, and if the employed data sources are biased, the quality of the results varies. This might also be one of the reasons for the deficiencies of this technique in the detailed design of the cusp angles of dental crowns.\u003c/p\u003e\n\u003cp\u003eSimultaneously, several limitations of the present study should be acknowledged. First, AI, which is a new technique in dental crown design, lacks many primary studies associated with it, as we found only 12 articles that could be included in our study. Second, we noticed that there were certain degrees of heterogeneity among some of the studies. Heterogeneity is related to the presence of confounding factors within and among the included studies, such as tooth position and design software differences. Third, all included studies were assessed as having a moderate risk of bias. Given the small number of articles, we did not evaluate their publication biases or perform sensitivity analyses. Fourth, we determined that certain research metrics, such as\u0026nbsp;occlusal contact\u0026nbsp;and\u0026nbsp;the absolute marginal discrepancy, serve as valuable analytical indicators. However, owing to the insufficient number of relevant studies, a systematic analysis on this topic was not feasible.\u003c/p\u003e\n\u003cp\u003eConsidering the limitations described previously, future research should incorporate additional evaluation indicators and conduct more rigorous controlled trials. These measures will help assess the advantages and disadvantages of AI design in the field of dental crown restoration, ultimately developing a standardized evaluation framework for AI applications in this field.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn summary, compared with the traditional CAD method, AI design can significantly reduce time consumption levels, generate occlusal morphology with similar effects for dental crowns, and perform more stably in terms of the occlusal accuracy. However, there is still room for improving upon the traditional CAD method regarding the design of the cusp angles of dental crowns. Overall, AI is suitable as an auxiliary tool for dental crown design tasks and is recommended for clinical promotion. However, it is still necessary to continuously optimize the algorithmic architectures and model performance of AI to enhance its applicability and service efficiency in the field of dental crown restoration and provide technical support for digital dental restoration scenarios.\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eAI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;Artificial intelligence\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eCAD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;Computer-aided design\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eRCT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;Randomized controlled trial\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eCAD/CAM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eComputer-aided design/Computer-aided manufacturing\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e3D\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eThree-dimensional\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003ePRISMA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003ePreferred reporting items for systematic reviews and meta-analysis\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eMD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eMean difference\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eCI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eConfidence interval\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eDL\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eDeep learning\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll Data generated or analysed during this study are included in this published article.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by funding from Project of Chongqing Higher Education and Teaching Reform (grant numbers: 193070).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors’ Contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eJX H and YZ W extracted, analyzed and interpreted the data. JX H and BD B drafted and edited the manuscript. XM F and B H designed the study and revised the manuscript. All authors have read and approved the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eHawthan M, Larsson C, Chrcanovic BR. Survival of fixed prosthetic restorations on vital and nonvital teeth: A systematic review. J Prosthodont. 2024;33(2):110\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen WW, Liu YM, Liu LC, Wang ZW. Effect of all-ceramic crown and onlay on the restoration of posterior tooth defects and their influence on masticatory function and gingival condition. J Clin Exp Med. 2023;22(3):326\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang SF, Song CH, Yang YQ. Rapid manufacturing technology and progress of digital dental restorations. Mater Res Appl. 2012;6(2):91\u0026ndash;5.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang T, Song HB, Wang Q, Hou YF, Liu HL, Zhang L. Brief introduction and implications of WHO guidance on ethics \u0026amp; governance of artificial intelligence for health. Chin J Pharmacovigil. 2024;21(8):906\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChau RCW, Hsung RT, McGrath C, Pow EHN, Lam WYH. Accuracy of artificial intelligence-designed single-molar dental prostheses: A feasibility study. J Prosthet Dent. 2024;131(6):1111\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeng Y, Tao B, Fan J, Wang S, Mo J, Wu Y, Liang Q. 3D reconstruction for maxillary anterior tooth crown based on shape and pose estimation networks. Int J Comput Assist Radiol Surg. 2023;18(8):1405\u0026ndash;16.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTian S, Huang R, Li Z, Fiorenza L, Dai N, Sun Y, Ma H. A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction. J Healthc Eng. 2022, 2022:1933617.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTian S, Wang M, Dai N, Ma H, Li L, Fiorenza L, Sun Y, Li Y. DCPR-GAN: Dental Crown Prosthesis Restoration Using Two-Stage Generative Adversarial Networks. IEEE J Biomed Health Inf. 2022;26(1):151\u0026ndash;60.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBohner LO, Neto PT, Ahmed AS, Mori M, Lagan\u0026aacute; DC, Sesma N. CEREC Chairside System to Register and Design the Occlusion in Restorative Dentistry: A Systematic Literature Review. J esthetic Restor dentistry: official publication Am Acad Esthetic Dentistry [et al]. 2016;28(4):208\u0026ndash;20.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen Y, Lee JKY, Kwong G, Pow EHN, Tsoi JKH. Morphology and fracture behavior of lithium disilicate dental crowns designed by human and knowledge-based AI. J Mech Behav Biomed Mater. 2022;131:105256.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKollmuss M, Jakob FM, Kirchner HG, Ilie N, Hickel R, Huth KC. Comparison of biogenerically reconstructed and waxed-up complete occlusal surfaces with respect to the original tooth morphology. Clin Oral Investig. 2013;17(3):851\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKollmuss M, Kist S, Goeke JE, Hickel R, Huth KC. Comparison of chairside and laboratory CAD/CAM to conventional produced all-ceramic crowns regarding morphology, occlusion, and aesthetics. Clin Oral Investig. 2016;20(4):791\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLitzenburger AP, Hickel R, Richter MJ, Mehl AC, Probst FA. Fully automatic CAD design of the occlusal morphology of partial crowns compared to dental technicians' design. Clin Oral Investig. 2013;17(2):491\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCho JH, Cakmak G, Yi Y, Yoon HI, Yilmaz B, Schimmel M. Tooth morphology, internal fit, occlusion and proximal contacts of dental crowns designed by deep learning-based dental software: A comparative study. J Dent. 2024;141:104830.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDing H, Cui Z, Maghami E, Chen Y, Matinlinna JP, Pow EHN, Fok ASL, Burrow MF, Wang W, Tsoi JKH. Morphology and mechanical performance of dental crown designed by 3D-DCGAN. Dent Mater. 2023;39(3):320\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu CM, Lin WC, Lee SY. Evaluation of the efficiency, trueness, and clinical application of novel artificial intelligence design for dental crown prostheses. Dent Mater. 2024;40(1):19\u0026ndash;27.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu L, Shen LL, Ding X. Comparative clinical outcomes of AI-designed versus conventional CAD/CAM-designed zirconia full-crown restoration of molar defects. Oral Biomed. 2024;15(5):276\u0026ndash;80.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEnder A, Mormann WH, Mehl A. Efficiency of a mathematical model in generating CAD/CAM-partial crowns with natural tooth morphology. Clin Oral Investig. 2011;15(2):283\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNagata K, Inoue E, Nakashizu T, Seimiya K, Atsumi M, Kimoto K, Kuroda S, Hoshi N. Verification of the accuracy and design time of crowns designed with artificial intelligence. J Adv Prosthodont. 2025;17(1):1\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu CM, Lu TY, Wang CS, Feng SW, Lin YC, Lee SY, Lin WC. Evaluation of the accuracy, occlusal contact and clinical applications of zirconia crowns using artificial intelligence design versus human design. J Dent Sci. 2025;20(3):1665\u0026ndash;72.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu Z, Zhang C, Ye X, Dai Y, Zhao J, Zhao W, Zheng Y. Comparison of the Efficacy of Artificial Intelligence-Powered Software in Crown Design: An In Vitro Study. Int Dent J. 2025;75(1):127\u0026ndash;34.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlqahtani F. Marginal fit of all-ceramic crowns fabricated using two extraoral CAD/CAM systems in comparison with the conventional technique. Clin Cosmet Investig Dent. 2017;9:13\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNaskar S, Sharma S, Kuotsu K, Halder S, Pal G, Saha S, Mondal S, Biswas UK, Jana M, Bhattacharjee S. The biomedical applications of artificial intelligence: an overview of decades of research. J Drug Target 2025:1\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBlatz MB, Conejo J. The Current State of Chairside Digital Dentistry and Materials. Dent Clin North Am. 2019;63(2):175\u0026ndash;97.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePark WJ, Park JB. History and application of artificial neural networks in dentistry. Eur J Dent. 2018;12(4):594\u0026ndash;601.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFarook TH, Ahmed S, Jamayet NB, Rashid F, Barman A, Sidhu P, Patil P, Lisan AM, Eusufzai SZ, Dudley J, et al. Computer-aided design and 3-dimensional artificial/convolutional neural network for digital partial dental crown synthesis and validation. Sci Rep. 2023;13(1):1561.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMehl A, Blanz V, Hickel R. A new mathematical process for the calculation of average forms of teeth. J Prosthet Dent. 2005;94(6):561\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-oral-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ohea","sideBox":"Learn more about [BMC Oral Health](http://bmcoralhealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/ohea/default.aspx","title":"BMC Oral Health","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Artificial intelligence, Computer-aided design, Dental crown design, Dental restoration, Meta-analysis","lastPublishedDoi":"10.21203/rs.3.rs-8691105/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8691105/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eThis meta-analysis was aimed at investigating the differences between dental crowns designed by artificial intelligence (AI) and those designed through traditional computer-aided design (CAD) processes to provide a reference for the clinical application of AI in the field of dental crown restoration.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eSearches were conducted in PubMed, Web of Science, CENTRAL, EMBASE, WFPD, VIP, and CNKI to collect randomized controlled trials (RCTs) on AI-designed dental crowns and traditional CAD-based dental crowns. After the data were extracted and the risk of bias was assessed with the Cochrane Collaboration\u0026rsquo;s risk assessment tool, a meta-analysis was conducted to clarify the differences between AI-designed dental crowns and traditional CAD-based dental crowns. The search period was from the establishment of each database to January 2026. Two researchers independently screened the articles, extracted their basic information and assessed the risk of bias. The meta-analysis was conducted using Review Manager 5.3.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eA total of 12 articles were ultimately included. The meta-analysis revealed that the design time of the AI group was shorter than that of the traditional CAD group (mean difference, -279.27; 95% confidence interval, -423.18 to -135.36; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.0001), and the occlusal accuracy of the former was better than that of the traditional CAD group (mean difference, -67.39; 95% confidence interval, -132.36 to -2.42; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.04); however, no significant difference was observed between the occlusal morphology (mean difference, -0.02; 95% confidence interval, -0.06 to -0.02; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.34), and the cusp angle designed in the AI group was smaller than that of the traditional CAD group (mean difference, 3.31; 95% confidence interval, 1.12 to 5.50; \u003cem\u003eP\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.003).\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eCompared with traditional CAD, AI significantly reduces the required design time while producing similar occlusal morphology results and demonstrating greater stability in occlusal accuracy. However, compared with that of the traditional CAD method, the cusp angle designed by AI still needs further optimization. Overall, as an auxiliary tool for dental crown design, AI design is suitable for clinical promotion and application. Nevertheless, it is necessary to continuously optimize the architecture of the AI algorithm and the performance of the model to enhance their applicability and service efficiency in the field of dental crown restoration, thereby providing technological support for digital dental restoration tasks.\u003c/p\u003e","manuscriptTitle":"The Application of Artificial Intelligence in the Field of Dental Restoration for Designing Dental Crowns: A Meta-Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-11 06:12:57","doi":"10.21203/rs.3.rs-8691105/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-26T14:37:19+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-24T17:33:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-23T07:18:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"147636980607609426895154407002472055667","date":"2026-03-22T09:41:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"235126496125673774138433604835024397313","date":"2026-03-18T14:45:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"225081013772484374445699417280442014874","date":"2026-03-17T12:13:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-06T08:49:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-03T07:46:12+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-02T07:31:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-01T16:05:56+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Oral Health","date":"2026-02-01T14:38:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-oral-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ohea","sideBox":"Learn more about [BMC Oral Health](http://bmcoralhealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/ohea/default.aspx","title":"BMC Oral Health","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7dfecf15-5893-476f-9fbc-f739011dc8c8","owner":[],"postedDate":"March 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T08:38:53+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-11 06:12:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8691105","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8691105","identity":"rs-8691105","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}