PLOS ONE

Dear Dr. Raman,

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 check the comments from the reviewers. Few comments from my side:

- Novel approach using pupillometry is interesting, but dataset is small, imbalanced, and lacks external validation. Risk of overfitting (ANN) not fully addressed.

- Methods / reproducibility: Key details on model training, cross-validation, and parameter tuning are missing. Data/code not publicly available, which conflicts with PLOS ONE policy.

- Discussion / conclusions: Conclusions are overstated given preliminary data. Limitations and comparison with established retinal imaging methods should be expanded.

- Ethics / data availability: Ethics approval is in place, but data availability does not comply with journal requirements; public data/code deposition is expected.

Please submit your revised manuscript by Oct 15 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.

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,

Tomo Popovic, 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 note that PLOS One has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. In the online submission form, you indicated that the data are not publicly available but can be obtained from the corresponding author upon reasonable request.

All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either a. In a public repository, b. Within the manuscript itself, or c. Uploaded as supplementary information.

This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval.

4. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. 

[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?

Reviewer #1: Yes

Reviewer #2: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: Yes

Reviewer #2: No

**********

3. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: No

Reviewer #2: No

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

Reviewer #2: Yes

**********

Reviewer #1: This is an interesting and innovative study that uses pupillometry-derived biomarkers with machine learning models to predict diabetic retinopathy (DR). The use of a non-invasive, inexpensive, and scalable method is a strong contribution, especially for low-resource settings where retinal imaging may not be widely available. The manuscript is well-structured, compares multiple machine learning models, and demonstrates that ANN outperforms other classifiers (93% accuracy, AUC 0.98).

However, there are several important points that require clarification and expansion before the manuscript can be considered for publication.

Major Comments

1. The novelty is clear: using pupillary abnormalities instead of fundus images for DR prediction. However, the introduction currently emphasizes prior work on risk scores and fundus-based ML models without sufficiently highlighting how pupillometry could complement or outperform these approaches.

The authors should explicitly emphasize the clinical practicality of pupillometry (speed, cost, portability) compared to fundus photography, particularly in low-resource screening contexts.

2. The ANN architecture is described, but hyperparameter tuning (layers, neurons, batch size, epochs) seems arbitrary. Were these parameters chosen empirically or optimized systematically? Please clarify.

Tables 3 and 4: It is unclear what input features were used to generate these results (e.g., age, time for one Hippus cycle, BPD, VPC). This needs to be explicitly described in the Methods and clearly displayed in the tables.

3. Table 2 provides cut-offs for pupillary features. While statistically valuable, the clinical interpretability is uncertain. For example, is a BPD cut-off of 4.50 mm meaningful in real-world screening?

If possible, the authors should expand the discussion on how pupillometry correlates with DR severity and whether these findings align with, or add predictive value beyond, standard risk factors such as HbA1c and diabetes duration. A comparative discussion would better highlight potential clinical application of the cut-offs.

4. The limitations are understated. The main limitation is that impairments in pupillary dynamics are not disease-specific and must be interpreted in the broader clinical context. As the authors note, changes may reflect diabetic autonomic neuropathy, but pupillary dysfunction can also result from other conditions that affect the vision (e.g., macular degeneration, optic neuropathies). This confounding is critical and must be emphasized.

The dataset is from a single-center, South Indian cohort. The generalizability of findings to other ethnicities and healthcare contexts is limited and should be explicitly acknowledged.

5. The current statement (“Data and code available upon request”) does not meet PLOS ONE data policy. Authors should deposit anonymized data and analysis code in a public repository (e.g., Dryad, Figshare, GitHub). Without this, reproducibility and transparency are limited.

Minor Comments

1. Figures 3 and 4 are useful but require higher resolution and clearer labeling. Figure legends should be made more informative, with all abbreviations defined, so that readers can interpret the figures without referring back to the text.

Reviewer #2: There are several methodical and reporting issues with this article that are limiting its scientific validity and generalizability:

- The use of both eyes from the same patient without clear patient-level data splitting raises concerns about data independence and potential overestimation of model performance

- Although the authors attempted to address class imbalance using SMOTE, the models were trained on the original imbalanced dataset without providing detailed comparative analysis

- The ANN architecture is relatively simple (with only 2433 parameters) and trained with no regularization techniques which raises concerns for showcase of overfitting

- The ANN performance is very high (accuracy 93%, AUC score 0.96 on test data), yet the validation AUC drops sharply to 0.57% (which suggest possible problems such as overfitting and should be addressed)

- The model was trained on relatively small dataset (405 eyes), and validation set size (n=30) which is insufficient to draw strong conclusions

- Standard metrics are reported without consideration of confidence intervals or statistical significance of the results

- Additionally, neither the code repository nor the dataset is publicly available, raising concerns about the study’s reproducibility. If data access is restricted, a clear justification should be provided, as stating 'available upon request' is insufficient under standard open data policies (see instructions on how to report this).

**********

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 . Please note that Supporting Information files do not need this step.

Dear Dr. Raman,

• Please check the comments from the reviewers.

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,

Tomo Popovic, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

1. If the reviewer comments include a recommendation to cite specific previously published works, please review and evaluate these publications to determine whether they are relevant and should be cited. There is no requirement to cite these works unless the editor has indicated otherwise. 

2. 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.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #1: All comments have been addressed

Reviewer #2: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions??>

Reviewer #1: Yes

Reviewer #2: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

Reviewer #2: Yes

**********

Reviewer #1:  The authors have substantially improved the manuscript following the previous round of reviews. All major concerns have been addressed. The Introduction has been streamlined, the methodological description is now more clear and transparent. The flow and clarity of the Results section are markedly improved as well. The Discussion has been revised to avoid overinterpretation, and the study’s limitations are appropriately acknowledged.

The study’s contribution is now well articulated: if externally validated, AI-assisted analysis of pupillometry could serve as a rapid, non-invasive, and cost-effective adjunct for triage and screening of diabetic retinopathy, particularly in low-resource or community-based settings where access to retinal imaging is limited.

I have only one minor remaining comment: Figure 2 is not referenced in the main text and should be cited at the appropriate location.

Overall, the manuscript is suitable for publication pending this minor correction.

Reviewer #2:  Thank you for addressing the previous comments. The amount of work and revision that has gone into improving this study is greatly appreciated. There are still several important inconsistencies to discuss/clarify:

-The revised version state the one eye per participant used, the resulting sample size (145) does not match the number of subjects (244). It remains unclear how the subjects were excluded and how the single eye was selected.

-The original submission indicates that SMOTE was tested, but not used in the final analysis. Current version states SMOTE as part of the methodology. It should be clearly stated whether the SMOTE was used pre or post splitting the dataset. Potential data leakage if used in the split. How was SMOTE integrated with cross-validation?

-Both SMOTE-based and non-SMOTE analyses are presented. Please state clearly which set of results is used to support the study’s final conclusions.

-Hyperparameters were added in the revision, the ANN still includes no regularization (L1/L2 penalties, early stopping) while the dropout is 0. Please explicitly explain what changes to the pipeline led to the improved results (or is it only the effect of the SMOTE?).

-Although 95% confidence intervals are mentioned in the Abstract, they do not appear anywhere in the Results section or in the tables, nor is the bootstrapping methodology described. Please report the full confidence intervals within the Results and explain precisely how they were computed, or remove this claim.

**********

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.]

To ensure your figures meet our technical requirements, please review our figure guidelines: https://journals.plos.org/plosone/s/figures 

You may also use PLOS’s free figure tool, NAAS, to help you prepare publication quality figures: https://journals.plos.org/plosone/s/figures#loc-tools-for-figure-preparation. 

NAAS will assess whether your figures meet our technical requirements by comparing each figure against our figure specifications.

Machine Learning-Based Prediction of  Diabetic Retinopathy from Pupillary Abnormalities in a South Indian Population

PONE-D-25-25752R2

Dear Dr. Raman,

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,

Tomo Popovic, Ph.D.

Academic Editor

PLOS One