Dear Dr. Hong,

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 Sep 28 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 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,

Vijayalakshmi Kakulapati, 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. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match.

When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

3. We note that you have indicated that there are restrictions to data sharing for this study. For studies involving human research participant data or other sensitive data, we encourage authors to share de-identified or anonymized data. However, when data cannot be publicly shared for ethical reasons, we allow authors to make their data sets available upon request. For information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions.

Before we proceed with your manuscript, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. Please see http://www.bmj.com/content/340/bmj.c181.long for guidelines on how to de-identify and prepare clinical data for publication. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible.

Please update your Data Availability statement in the submission form accordingly.

4. Thank you for stating the following in your manuscript:

“This research was supported and funded by the SNUH Lee Kun-hee Child Cancer & Rare Disease Project, Republic of Korea (grant number: 24C-003-0100) and supported by research fund from Chungnam National University.”

We note that you have provided additional information within the Acknowledgements Section that is not currently declared in your Funding Statement. Please note that funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form.

Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows:

“The author(s) received no specific funding for this work.”

Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

5. Your ethics statement should only appear in the Methods section of your manuscript. If your ethics statement is written in any section besides the Methods, please move it to the Methods section and delete it from any other section. Please ensure that your ethics statement is included in your manuscript, as the ethics statement entered into the online submission form will not be published alongside your manuscript.

6. We notice that your supplementary [figures/tables] are included in the manuscript file. Please remove them and upload them with the file type 'Supporting Information'. Please ensure that each Supporting Information file has a legend listed in the manuscript after the references list.

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. 

Additional Editor Comments (if provided):

[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: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: I Don't Know

**********

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

The PLOS Data policy

Reviewer #1: Yes

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 study addresses pediatric hypoxemia prediction using machine learning models. While technically sound, several methodological issues must be clear up before publication.

Major Concerns:

1. Circular Logic in SpO2-based Prediction

The study defines hypoxemia as SpO2 < 95% while simultaneously using SpO2 as the primary predictor variable. SHAP analysis confirms SpO2 as the most important feature, creating a circular prediction framework. To demonstrate true clinical value, the authors should compare performance against: (1) SpO2-only models, (2) simple threshold-based rules, and (3) existing clinical practice standards if possible. Or state it on limitation.

2. Poor Precision Performance

The AUPRC values are critically low: XGBoost achieved 0.1816 (internal) and 0.0402 (external), while LSTM achieved 0.0605(external). The F1 scores remain poor (XGBoost: 0.2382 internal, 0.0824 external). These metrics indicate severely limited precision in clinical application, yet the authors fail to adequately discuss whether such performance justifies implementation or potential harm from false alarms.

3. Inadequate Prediction Timeline Justification.

The authors should justify why they defined a 1-minute prediction window. Is this timeframe sufficient for clinical intervention or prevention?

Reviewer #2: Many thanks for providing the manuscript for review. The authors utilise physiological data captured from intra-operative anaesthesia devices in order to predict the onset of hypoxemia in a subset of paediatric patients undergoing general anaesthesia in the Republic of Korea. They utilise a rolling window method in which 120 second segments of data are classified as either hypoxemia or no hypoxemia and make use of the first half (60 seconds) to predict occurrence of any hypoxemia in the second (61-120 seconds) half of the window.

The models utilise include XGBoost, LSTM, transformer model and a CNN approach (InceptionTime). The authors report a high AUROC performance for each of the models and utilise this to perform external validation on patients from another institution.

Comments

1. I would like to see the Tripod AI checklist included within the supplementary material provided

2. It would be useful to have further clarity in the introduction on the relationship between a low SpO2 reading and true hypoxemia – what criteria is used to define hypoxemia conventionally e.g. will this include low arterial blood gas oxygen pressures? Helpful for readers who do not work within anaesthesia for example.

3. I would like to also see data on the different types of surgery cases included in the baseline descriptions to understand the population better.

4. The authors mention that relying on SpO2 readings alone is insufficient for accurately assessing true hypoxemia – however their definition of hypoxemia used for model training and evaluation appears to be based largely on SpO2 alone. Can they elaborate on what processes are used to ensure this is clinically valid (e.g. annotation process)

5. What is the nature of the ‘vital signs’ used to train the initial models? Are these tabular data extracted from the machines, continuous waveforms or a composite – useful to be explicit and describe the data, data quality, and what pre-processing work was involved in making them useable.

6. How were the hyperparameters chosen? Is this through cross-validation if so what are the performances? Reporting only the hold out set metrics for model development may not provide the full picture.

7. The model utilises SpO2 as their primary input feature in order to predict subsequent SpO2. How is the nature of repeated measurement accounted for in the models (if they need to be). For example, I would imagine a low SpO2 in the first half of the window is predictive of a low SpO2 in the second half?

8. Can the authors comment on why XGBoost was the best performing in the internal validation set but did not perform as well in external validation? There is a disproportionate difference between XGBoost and LSTM approaches internally.

9. The dataset is highly imbalanced with only around 1.4% at most positive. This means that the AUROC will be high regardless and therefore can be misleading to present this as the primary result. The AUPRC for the external validation is around 0.06 (where the baseline will be around 0.012) – can the authors comment on the suitability of the model for clinical implementation? Is this a useful model to inform clinicians?

10. I would disagree with the statement that machine learning models are not inherently designed (or suitable) for time series data – when alternatives include linear modelling.

11 . What is the significance of the SHAP analysis and figure – especially when height is the greatest contributor to model prediction but most features are centred around 0.

12. Could the captions and figures be provided in higher resolution?

13. Can I urge the anonymised data to be provided as part of submission given this would be valuable contribution to medical research into signal analysis where possible.

Many thanks

**********

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: Yes:  Damien Ming

**********

[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.

Hypoxemia prediction in pediatric patients under general anesthesia using machine learning: a retrospective observational study and external validation

PONE-D-25-28107R1

Dear Dr. Hong,

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,

Vijayalakshmi Kakulapati, Ph.D

Academic Editor

PLOS ONE

Reviewers' comments:

Reviewer #1: All comments have been addressed

Reviewer #3: All comments have been addressed

Reviewer #1: The author's revised manuscript has successfully addressed all scientific concerns raised during the review process. The revisions demonstrate a thorough understanding all comments and provide satisfactory responses to each point. The scientific rigor, methodology, and interpretation of results have been appropriately strengthened in accordance with the feedback provided.

I suggested this revised version justifying for publication.