Examining the diagnostic accuracy of artificial intelligence for detecting dental caries across a range of imaging modalities: An umbrella review with meta-analysis

Sarah Arzani; Ali Karimi; Pedram Iranmanesh; Maryam Yazdi; Mohammad A. Sabeti; Mohammad Hossein Nekoofar; Jafar Kolahi; Heejung Bang; Paul M.H. Dummer

doi:10.1371/journal.pone.0329986

Peer Review History

Original SubmissionFebruary 9, 2025
9 Feb 2025 Author Response Attachments Attachment Submitted filename: Rebuttal letter.docx https://doi.org/10.1371/journal.pone.0329986.r001
11 Jun 2025 Decision Letter - Giang Vu, Editor Dear Dr. Arzani, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Jul 26 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols . We look forward to receiving your revised manuscript. Kind regards, Giang Truong Vu, D.D.S., M.S., Ph.D. Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Please remove all personal information, ensure that the data shared are in accordance with participant consent, and re-upload a fully anonymized data set. Note: spreadsheet columns with personal information must be removed and not hidden as all hidden columns will appear in the published file. Additional guidance on preparing raw data for publication can be found in our Data Policy (https://journals.plos.org/plosone/s/data-availability#loc-human-research-participant-data-and-other-sensitive-data) and in the following article: http://www.bmj.com/content/340/bmj.c181.long. 3. Please include captions for your Supporting Information files at the end of your manuscript, and update any in-text citations to match accordingly. Please see our Supporting Information guidelines for more information: http://journals.plos.org/plosone/s/supporting-information. 4. Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice. Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? Reviewer #1: Yes Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? -->?> Reviewer #1: Yes Reviewer #2: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available??> The PLOS Data policy Reviewer #1: Yes Reviewer #2: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English??> Reviewer #1: Yes Reviewer #2: Yes ****** Reviewer #1: The manuscript is technically sound and well written. However, some minor corrections would improve the quality. Heterogeneity has been discussed, however the implications of high variability across studies (e.g., imaging modality, AI model type) could be discussed further. The impact of publication bias on the pooled estimates should be elaborated. The references have to be formatted according to journal guidelines. Reviewer #2: Review Comments to the Author: The topic of this manuscript is timely and relevant. The authors present a broad summary of existing evidence on the use of artificial intelligence (AI) for detecting dental caries, which seems important and useful for the field. Strengths: The methodology is clearly described, and the tools used for analysis appear to be appropriate and well chosen for the study’s objective. The conclusions are well linked to the presented data, and the results are carefully analyzed. It is also appreciated that the underlying data are fully available. Suggestions: It might be helpful to discuss more clearly the limitations related to the fact that only a small number of original studies were included in the meta-analysis. A short explanation on how overlapping studies across the included reviews were handled could also be useful. The manuscript would benefit from more critical reflection on how the presence or absence of caries was determined in the original studies. There is little detail on the reference standard, and it remains unclear whether definitions of caries were consistent, validated, or clinically reliable. It would strengthen the discussion to acknowledge that the most reliable conclusions would come from reviews comparing studies conducted under the same diagnostic protocols and caries definitions. The type of dental imaging strongly influences diagnostic performance. AI evaluating panoramic radiographs (with tooth overlap) operates under very different conditions than AI analyzing bitewing images (with clear interproximal visibility). Pooling such results may reduce the clinical interpretability of the findings and should be acknowledged as a limitation. In future analyses, the most valuable evidence will likely come from studies that simulate real-world diagnostic conditions, including time pressure, clinician–patient interaction, and the integration of AI as part of the clinical workflow rather than in isolated image review. A recently published study demonstrates the importance of incorporating such clinical constraints in AI evaluation and could be considered for citation: PMID: 40095536 Conclusion: Overall, this seems to be a well-prepared and solid piece of work. I recommend it for publication after minor clarifications. ****** what does this mean? ). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy Reviewer #1: No Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org https://doi.org/10.1371/journal.pone.0329986.r002
Revision 1
4 Jul 2025 Author Response The manuscript was revised based on the journal requirements and guidlines. Comments to the Author Reviewer #1: The manuscript is technically sound and well written. However, some minor corrections would improve the quality. Heterogeneity has been discussed, however the implications of high variability across studies (e.g., imaging modality, AI model type) could be discussed further. Discussion section (page 22): -High levels of heterogeneity (I2>95) were found regarding sensitivity, specificity, and log diagnostic odds ratio among the included studies. These levels of heterogeneity can be explained by diversity in imaging modalities (e.g., bitewing vs. panoramic radiographs), differences in AI algorithm architectures, and training dataset characteristics. The impact of publication bias on the pooled estimates should be elaborated. Results section (page 17): -The nonparametric trim-and-fill analysis was employed to assess the impact of publication bias on the pooled estimates and results were presented at Table 6 The references have to be formatted according to journal guidelines. -Done Reviewer #2: Review Comments to the Author: The topic of this manuscript is timely and relevant. The authors present a broad summary of existing evidence on the use of artificial intelligence (AI) for detecting dental caries, which seems important and useful for the field. Strengths: The methodology is clearly described, and the tools used for analysis appear to be appropriate and well chosen for the study’s objective. The conclusions are well linked to the presented data, and the results are carefully analyzed. It is also appreciated that the underlying data are fully available. Suggestions: It might be helpful to discuss more clearly the limitations related to the fact that only a small number of original studies were included in the meta-analysis. Discussion section (page 22): -The main limitation of this umbrella review and meta-analysis include the fact that only 20 original studies were included in meta-analysis quantitative data synthesis. The number of primary original research studies was 137, with only 20 (14.5 %) original research articles reporting the necessary details of AI–based caries diagnostic test results including numbers TP, TN, FP, and FN involved in the meta-analysis. To facilitate future meta-analysis, authors are encouraged to report details of AI–based caries diagnostic tests including numbers of TP, TN, FP, and FN, all of which are essential for a meta-analysis. A short explanation on how overlapping studies across the included reviews were handled could also be useful. Methods section (page 7): -Overlapping studies across the included reviews were handled by creation of citation matrix and calculation of corrected covered area (CCA) using ccaR package of R software (R Foundation for Statistical Computing, Vienna, Austria). Results section (page 15): -The citation matrix of primary studies included in the systematic reviews was presented at Supplementary Table 1. The CCA_Proportion was 0.07 and CCA_Percentage was 6.90, showing moderate overlap. The pairwise CCA presented at Supplementary Figure 1, showed which combinations of paired reviews had the highest overlap. The manuscript would benefit from more critical reflection on how the presence or absence of caries was determined in the original studies. There is little detail on the reference standard, and it remains unclear whether definitions of caries were consistent, validated, or clinically reliable. Results section (page 15): -Table 5 was added to manuscript. At this table the caries detection method, reference standard and AI algorithm were presented. It would strengthen the discussion to acknowledge that the most reliable conclusions would come from reviews comparing studies conducted under the same diagnostic protocols and caries definitions. Discussion section (page 20): -It is well-known that, the most reliable conclusions would come from reviews comparing studies conducted under the same diagnostic protocols and caries definitions. As showed at Table 5, caries detection method, reference standard and AI algorithm were same among included studies in meta-analysis. The type of dental imaging strongly influences diagnostic performance. AI evaluating panoramic radiographs (with tooth overlap) operates under very different conditions than AI analyzing bitewing images (with clear interproximal visibility). Pooling such results may reduce the clinical interpretability of the findings and should be acknowledged as a limitation. Discussion section (page 19): -Readers must note, the type of dental imaging strongly influences diagnostic performance. AI evaluating panoramic radiographs (with tooth overlap) operates under very different conditions than AI analyzing bitewing images (with clear interproximal visibility). Pooling such results may reduce the clinical interpretability of the findings. To address this issue we conduct subgroup meta-analysis for different imaging modalities and results presented at Figure 4. In future analyses, the most valuable evidence will likely come from studies that simulate real-world diagnostic conditions, including time pressure, clinician–patient interaction, and the integration of AI as part of the clinical workflow rather than in isolated image review. A recently published study demonstrates the importance of incorporating such clinical constraints in AI evaluation and could be considered for citation: -Done Attachments Attachment Submitted filename: Reviewers comments.docx https://doi.org/10.1371/journal.pone.0329986.r003
25 Jul 2025 Decision Letter - Giang Vu, Editor Examining the diagnostic accuracy of artificial intelligence for detecting dental caries across a range of imaging modalities: An umbrella review with meta-analysis PONE-D-25-05467R1 Dear Dr. Arzani, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support . If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Giang Truong Vu, D.D.S., M.S., Ph.D. Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0329986.r004
Formally Accepted
Acceptance Letter - Giang Vu, Editor PONE-D-25-05467R1 PLOS ONE Dear Dr. Arzani, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. You will receive an invoice from PLOS for your publication fee after your manuscript has reached the completed accept phase. If you receive an email requesting payment before acceptance or for any other service, this may be a phishing scheme. Learn how to identify phishing emails and protect your accounts at https://explore.plos.org/phishing. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Giang Truong Vu Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0329986.r005

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .