Bidirectional gated recurrent unit network model can generate future visual field with variable number of input elements

Joohwang Lee; Keunheung Park; Hwayeong Kim; Sangwoo Moon; Junglim Kim; Sangwook Jin; Seunguk Lee; Jiwoong Lee

doi:10.1371/journal.pone.0307498

Peer Review History

Original SubmissionDecember 12, 2023
24 Mar 2024 Decision Letter - Natasha Gautam, Editor PONE-D-23-36114Bidirectional gated recurrent unit network model can generate future visual field with variable number of input elementsPLOS ONE Dear Dr. Lee, 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. The authors have drafted very nice manuscript with robust quantitative analysis to support the role of bidirectional gated recurrent unit network model to generate future VF with variable number of input elements. Please scroll down to the bottom of the email for the specific additional feedback. Please submit your revised manuscript by May 08 2024 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. Please include the following items when submitting your revised manuscript: 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 you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. 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, Natasha Gautam, MBBS, MS 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. Thank you for stating in your Funding Statement: “This work was supported by the National Research Foundation of Korea grants (No. RS-2023-00247504 and by Convergence Medical Institute of Technology R&D project (CMIT2023-00), Pusan National University Hospital.” Please provide an amended statement that declares all the funding or sources of support (whether external or internal to your organization) received during this study, as detailed online in our guide for authors at http://journals.plos.org/plosone/s/submit-now. Please also include the statement “There was no additional external funding received for this study.” in your updated Funding Statement. Please include your amended Funding Statement within your cover letter. We will change the online submission form on your behalf. 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. Additional Editor Comments (if provided): This is a well written manuscript. I would advise to move the results and details of training dataset including table 1 from methodology to results section, before describing the results about test dataset. Similarly the authors described the criteria to determine glaucoma severity (early, moderate and severe) in results section, which should be written in methodology instead of results. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: In this study, the authors proposed a deep learning method based on bidirectional gated recurrent units (Bi-GRU) to predict 24-2 Humphrey visual field (HVF) tests. I am impressed by the amount of data the authors used in their training set (23,517 eyes out of 185,858 VF tests from five hospitals from 06/2004 - 04/2022). I also appreciate that the authors clearly stated that the training and test data sets were separated by subject to keep the data sets independent. It is an excellent design that the proposed method can receive a varying number of VFs (up to a maximum of 80 examinations) and is able to predict the mean deviation (MD), pattern standard deviation (PSD), visual field index (VFI), 54 points of pattern deviation value (PDVs), and total deviation value (TDVs). Overall, this is a well-written manuscript describing a study with an important clinical objective and a straightforward methodology. Here are some suggestions that could further enhance its strengths and clarity. 1. Recurrent neural networks (RNNs) are well-established deep learning (DL) techniques for handling sequential data. However, recent advances have led to the development of newer methods (e.g., transformers) that may provide surprisingly good results. I believe that adding comparisons with a standard (basic) and state-of-the-art method to the test datasets could further validate the results and increase the manuscript's contribution to the field. 2. With such a large number of VF tests, I wonder how the authors digitally access the values in the VF reports. Meanwhile, what are the quality control steps to ensure that the digitally obtained values are the same as those in the HVF reports? 3. The manuscript provides a solid quantitative analysis. Including qualitative results for a few best and worst cases in each prediction category (i.e., glaucoma severity, number of VF tests, and prediction intervals) would substantially provide valuable insights and enrich the narrative and depth of the study. 4. The manuscript demonstrates a thorough analysis using an Asian dataset, which provides valuable insights specific to this population. To enhance the clarity and applicability of the manuscript, I believe it would be beneficial to acknowledge that the focus on this particular dataset may influence the generalizability of the findings to other racial groups. Including a brief discussion of this aspect could further strengthen the study by highlighting areas for future research and the potential application of a more diverse dataset. ****** 6. PLOS authors have the option to publish the peer review history of their article (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 ******** [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. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0307498.r001
Revision 1
31 May 2024 Author Response Reviewer’s comment 1. Recurrent neural networks (RNNs) are well-established deep learning (DL) techniques for handling sequential data. However, recent advances have led to the development of newer methods (e.g., transformers) that may provide surprisingly good results. I believe that adding comparisons with a standard (basic) and state-of-the-art method to the test datasets could further validate the results and increase the manuscript's contribution to the field. Response: Thank you for the comment. In fact, we have already tested “transformer network” as well as BiGRU model. As you mentioned, “transformer network” is a SOTA algorithm and we were very excited to use it. We expected its overwhelming performance just like chatBot does but on the contrary to our expectation, the performance was not so good. Now we are re-trying transformer network to solve the issue. We are also considering to use GTN (Gated Transformer Network) because visual field data contains channel like data (i.e. TDV, PDV, THV). Other than transformer network, we are trying another new architecture, CRU (Correlation Recurrent Units: A Novel Neural Architecture for Improving the Predictive Performance of Time-Series Data, https://ieeexplore.ieee.org/abstract/document/10264112). CRU internally utilizes correlation between input data similar to attention method in transformer. We expect CRU is lighter than transformer but it will show better performance than GRU. Taken together all above methods, we are planning to write a next paper comparing various SOTA architectures including transformer. At the moment, research is still ongoing and we did not yet conclude anything. We are very much thankful of your valuable suggestion but we would be glad if you can wait us to complete the research. 2. With such a large number of VF tests, I wonder how the authors digitally access the values in the VF reports. Meanwhile, what are the quality control steps to ensure that the digitally obtained values are the same as those in the HVF reports? Response: Thank you for the comment. To obtain such a large amount of visual field data digitally, Zeiss provides a “study mode” in their HVF machine. To activate this mode, you need license key from Zeiss. When study mode activated, you can export all exam data as “XML” files (1 exam per 1 XML file). We developed a custom software to transform XML files to a single excel file which contains all patients’ exam data. Because the manufacturer, Zeiss, guarantees XML file data exported from HVF machine is exactly same as HVF reports, we do not need quality control step. We also confirmed that our custom software converts XML file to excel file without error. 3. The manuscript provides a solid quantitative analysis. Including qualitative results for a few best and worst cases in each prediction category (i.e., glaucoma severity, number of VF tests, and prediction intervals) would substantially provide valuable insights and enrich the narrative and depth of the study. Response: Thank you for the comment. We have added qualitative results for a representative example for different glaucoma severity, number of input visual field exams, and prediction interval as supplementary materials (S1_fig, S2_fig, S3_fig.pdf including captions and legends) shown as below. and updated the in-text citations. Early stage Moderate stage Advanced stage S1 Figure. Representative examples of visual field (VF) prediction according to glaucoma severity (early, moderate and advanced) based on patient’s last VF mean deviation (MD) value. Input VFs are shown in chronological order from left to right, followed by actual VF and the predicted VF of the bidirectional gated recurrent unit model at different future time points. VF total deviation values for each of the 52 test locations are shown in gray scale. Number of input visual field: 3~5 Number of input visual field: 6~10 Number of input visual field: 11~15 Number of input visual field: >15 S2 Figure. Representative examples of visual field (VF) prediction according to number of input VF exams. Input VFs are shown in chronological order from left to right, followed by actual VF and the predicted VF of the bidirectional gated recurrent unit model at different future time points. VF total deviation values for each of the 52 test locations are shown in gray scale. Prediction interval < 6 months 6 months ≤ Prediction interval < 12 months 12 months ≤ Prediction interval < 24 months 24 months ≤ Prediction interval S3 Figure. Representative examples of visual field (VF) prediction according to prediction interval. Input VFs are shown in chronological order from left to right, followed by actual VF and the predicted VF of the bidirectional gated recurrent unit model at different future time points. VF total deviation values for each of the 52 test locations are shown in gray scale. 4. The manuscript demonstrates a thorough analysis using an Asian dataset, which provides valuable insights specific to this population. To enhance the clarity and applicability of the manuscript, I believe it would be beneficial to acknowledge that the focus on this particular dataset may influence the generalizability of the findings to other racial groups. Including a brief discussion of this aspect could further strengthen the study by highlighting areas for future research and the potential application of a more diverse dataset. Response: Thank you for the comment. We have added data bias and generalization issues due to the single ethnic group in the Asian dataset to the limitation section. We have added following sentences as shown below. “Lastly, in this study, the RNN algorithm was trained on a single ethnic group consisting of Asian, which can lead to data bias (racial bias). To reduce this issue and ensure data generalization, it is crucial to build a diverse and representative training datasets of all races and ethnicities to test and report its performance.” Sincerely, Jiwoong Lee, MD, PhD Department of Ophthalmology, Pusan National University Hospital, 179 Gudeok-ro, Seo-gu, Busan 49241, South Korea Tel: +82-51-240-7326 Fax: +82-51-242-7341 E-mail: alertlee@naver.com Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0307498.r002
8 Jul 2024 Decision Letter - Natasha Gautam, Editor Bidirectional gated recurrent unit network model can generate future visual field with variable number of input elements PONE-D-23-36114R1 Dear Dr. Lee, 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. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org. 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, Natasha Gautam, MBBS, MS Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: https://doi.org/10.1371/journal.pone.0307498.r003
Formally Accepted
16 Jul 2024 Acceptance Letter - Natasha Gautam, Editor PONE-D-23-36114R1 PLOS ONE Dear Dr. Lee, 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 If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks 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. 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. Natasha Gautam Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0307498.r004

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 .