PONE-D-24-20623Optimizing mechanical ventilation: personalizing mechanical power to reduce icu mortality - a retrospective cohort studyPLOS ONE

Dear Dr. alkhalifah,

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.

==============================

ACADEMIC EDITOR:

lease carefully assess all the reviewers comments

==============================

Please submit your revised manuscript by Sep 13 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,

Silvia Fiorelli

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. You indicated that ethical approval was not necessary for your study. We understand that the framework for ethical oversight requirements for studies of this type may differ depending on the setting and we would appreciate some further clarification regarding your research. Could you please provide further details on why your study is exempt from the need for approval and confirmation from your institutional review board or research ethics committee (e.g., in the form of a letter or email correspondence) that ethics review was not necessary for this study? Please include a copy of the correspondence as an ""Other"" file.

3. In the online submission form, you indicated that [The datasets generated and analyzed for this study are available from the corresponding author on request.]. 

All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. 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. Please include your full ethics statement in the ‘Methods’ section of your manuscript file. In your statement, please include the full name of the IRB or ethics committee who approved or waived your study, as well as whether or not you obtained informed written or verbal consent. If consent was waived for your study, please include this information in your statement as well. 

[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

Reviewer #2: Partly

Reviewer #3: Partly

**********

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

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: 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

Reviewer #2: Yes

Reviewer #3: No

**********

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

Reviewer #2: Yes

Reviewer #3: 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: It is a good study about personalising mechanical power in hypoxic patients with use of advanced statistical and machine learning methods. It has also focused on individualised patient care, aligning with modern precision medicine trends. I agree with the limitations you have highlighted.

Reviewer #2: Thank you for the interesting and potentially impactful study. There are some concerns about this study.

1. Please provide more details on the machine learning models, including feature selection process and hyperparameter tuning.

2. Please expand on the proposed individualization method for mechanical ventilation settings. How exactly would this be implemented clinically?

3. The authors should include a multivariable analysis to assess the independent association of mechanical power with mortality after adjusting for confounders.

4. Please consider external validation of the findings using another ICU dataset, if possible.

5. The authors should clarify how the "safe upper limits" for mechanical power were determined statistically.

6. The counter-intuitive findings in severely hypoxemic patients warrant further discussion and analysis.

7. More context on how these findings compare to existing literature on mechanical power thresholds would be needed.

8. The clinical implications and potential next steps for research should be elaborated on in the discussion.

Reviewer #3: The manuscript investigates the relationship between the Mechanical Power (MP) during mechanical ventilation and ICU mortality. The authors analyzed data from 2338 patients in the Amsterdam University Medical Centers Database and employed statistical and machine learning techniques. The authors found that nonsurvivors had significantly higher time-weighted average mechanical power (TWA-MP) than survivors, defined safe upper limits for IBW-adjusted MP for different hypoxemia groups and developed an individualized approach to change mechanical ventilation settings to reduce predicted mortality.

While the manuscript presents valuable insights, several areas could benefit from further refinement to enhance clarity, reproducibility, and impact. The strengths of the study lie on the large sample size from a critical care database, the good statistical methodology to define the cohort and the proposed novel approach to individualize mechanical ventilation settings. However, the manuscript presents several weaknesses: the primary outcome is ICU mortality, and this might not be the most appropriate measure for studying the effects of the first 48h of Mechanical Power; the methodology is not detailed and lacks basic data pipeline explanations; the results of the survival analysis with safe upper limits for IBW-adjusted MP on different hypoxemia groups show no statistically significance, what rejects one conclusion of the paper; the background and discussion of the manuscript are not explored in depth; and finally, it appears that there is no connection between the identification of the upper MP limit and the individualization of mechanical ventilation settings in the methodology of the manuscript.

Taking all of this into account, my recommendation for the manuscript is: Major Revision.

I wish that these comments find the authors of the paper well, I found very interesting their approach to individualize the MV settings. In order to help the authors to improve the manuscript, the authors should deal with or clarify the following issues.

Major issues:

1. Clarity in Background and Literature Context: The background section is concise and informative on the research but lacks depth in contextualizing existing literature. It gives the impression that the field of mechanical ventilation (including MP) and it’s relation to ICU mortality is less explored by machine learning and deep learning that it actually is. I would recommend expanding the background to include a more comprehensive review.

2. Wrong primary outcome: The research uses the ICU mortality as primary outcome, and this might not be the best outcome for this type of study. ICU mortality relies on several factors not related to mechanical ventilation, and patients with long stays at the ICU usually not die because of bad mechanical ventilation. Usually, other outcomes are used in this type of studies because the represent better a bad ventilation, like ventilator free days, time to successful extubation, or short or medium term mortality.

3. Data transparency: The journal inquires in the guidelines about the importance on data sharing, while it is understandable that the data does not belong to the researchers, it would be ideal that the researchers share the code to extract the data from the original database.

4. Methodological transparency. The methodology of the manuscript lacks detail in data processing, cleaning, missing filling and division in datasets. All of this information is needed to be able to reproduce the research. The subsection “Mortality prediction” of the manuscript it’s the only section in which a bit of the methodology of the data pipeline is explained and it clearly lacks detail. My recommendation would be to write one subsection dedicated to the data pipeline, and separate it from the methodology of the different data experiments.

5. Conclusion not supported by the results. The results in the survival analysis and figure 3 show that there is NO statical significance on the survival probability based on the upper limits identified. The researchers are mistaken and the conclusion based on this result is wrong.

Minor issues:

1. Definition of inadequate data. In abstract and methodology (line number 87) the authors write that they eliminated patients with inadequate data. The manuscript should be more concrete on what is inadequate data and how the authors defined it and processed it.

2. Data extraction. The authors talk about data extraction only at line 93, but code is unavailable and there is almost not real description on how data was extracted (procedure, technical details, tools used). To be able to reproduce the research, this is needed.

3. Statistical and Machine Learning analysis. The authors state at the lines 124-126 that they developed several models. Sadly, they only expose the results of XGBoost. Results of all models should be shown in results to contextualize the good results from XGBoost.

4. Relation between identified MP limits and individualization methods. While the individualization methods for mechanical ventilation settings are a very interesting approach, the authors don’t seem to connect the identified MP limits with the individualization methods. It would be appropriate if they could relate both parts of the paper, if not, is like two different investigations separated and they might want to focus on one for the paper.

5. Result of general limit for MP is not explained on the methodology. At line 167, the authors state that an upper limit of 16.51 J/min was determined for all patients, nonetheless, the authors don’t mention on the methodology how they determine the limit.

6. Provide more details on the algorithm or function used for optimizing MV settings based on MP and other physiological variables. In the subsection of the methodology “Individualization of MV settings”, the authors explain the process of individualization of MV settings, but they don’t explicitly say how the new values of MV are calculated. Ar they random approximation? A inequation being solved? Suggested by any algorithm? They should explain more this part.

7. More in-depth discussion. During the discussion, the authors mainly repeat the results obtained. While I understand that they want to reinstate their results, they should focus more on the clinical meaning of this results.

8. More in-depth limitations. More limitations of this study should be mentioned like that the research is done only on PCV patients, the use ICU mortality outcome (or not if changed to sorth/medium days ICU mortality), and potential biases in the individualization method’s predictions.

9. Table 1. This table has feature “Admitting speciality” with over 10 categories. Some of these categories have less than 10 patients between both groups. As a data cleaning process this feature should be grouped into main categories and “other” category.

10. Table 2. Table has laboratory data, but the extraction is not mentioned in methodology. It should be added to the methodology if this is important.

Conclusion:

The manuscript presents valuable insights into the personalization of mechanical ventilation settings to reduce ICU mortality. However, significant revisions are needed to improve clarity, methodological transparency, and alignment between results and conclusions. Addressing these points will enhance the manuscript's quality and impact.

**********

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

Reviewer #2: No

Reviewer #3: Yes: Manuel Ruiz-Botella

**********

[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.

PONE-D-24-20623R1Optimizing mechanical ventilation: personalizing mechanical power to reduce icu mortality - a retrospective cohort studyPLOS ONE

Dear Dr. Ahmed Alkhalifah,

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.

==============================

ACADEMIC EDITOR:

please carefully assess the reviewer comments 

==============================

Please submit your revised manuscript by  Nov 22 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,

Silvia Fiorelli

Academic Editor

PLOS ONE

Journal Requirements:

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

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: (No Response)

Reviewer #3: All comments have been addressed

**********

2. 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 #2: Partly

Reviewer #3: (No Response)

**********

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

Reviewer #2: Yes

Reviewer #3: (No Response)

**********

4. 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 #2: Yes

Reviewer #3: (No Response)

**********

5. 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 #2: Yes

Reviewer #3: (No Response)

**********

6. 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 #2: There are some aspects to be revised to make the paper more useful to readers.

1. Machine Learning Models: While the authors have added more details about the models (lines 137-148), further information on the feature selection process and hyperparameter tuning would enhance reproducibility.

2. Individualization Method: The expanded explanation (lines 150-166) improves understanding, but more concrete examples of how this method would be implemented clinically would be beneficial.

3. Multivariable Analysis: The addition of the supplementary table (S1 Table) addressing the independent association of mechanical power with mortality is valuable. This should be referenced and discussed in the main text.

4. External Validation: While understandable due to data access constraints, the lack of external validation remains a limitation. The authors should discuss potential implications of this limitation more thoroughly.

5. Safe Upper Limits: The added details (lines 127-132) clarify the statistical determination of safe upper limits. However, a brief discussion on the clinical significance of these thresholds would be helpful.

6. Severely Hypoxemic Patients: The additional discussion (lines 253-255) on the counter-intuitive findings in severely hypoxemic patients is appreciated, but further exploration of potential mechanisms or implications would strengthen the paper.

7. Comparison to Existing Literature: The added context (lines 262-264) comparing findings to existing literature is helpful. Expanding this comparison could provide readers with a better understanding of how this study advances the field.

8. Clinical Implications: The elaboration on clinical implications and future research directions (lines 285-295) improves the paper's impact. Consider discussing potential challenges in implementing the proposed individualized approach in clinical practice.

Reviewer #3: (No Response)

**********

7. 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 #2: No

Reviewer #3: Yes: Manuel Ruiz Botella

**********

[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.

PONE-D-24-20623R2Optimizing mechanical ventilation: personalizing mechanical power to reduce icu mortality - a retrospective cohort studyPLOS ONE

Dear Dr. alkhalifah,

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 Jan 03 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,

Silvia Fiorelli

Academic Editor

PLOS ONE

Journal Requirements:

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

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: (No Response)

Reviewer #3: All comments have been addressed

**********

2. 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 #2: Partly

Reviewer #3: (No Response)

**********

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

Reviewer #2: No

Reviewer #3: (No Response)

**********

4. 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 #2: Yes

Reviewer #3: (No Response)

**********

5. 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 #2: Yes

Reviewer #3: (No Response)

**********

6. 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 #2: Thank you for submitting your manuscript on personalizing mechanical power in mechanical ventilation to reduce ICU mortality. Your work addresses an important clinical challenge and offers innovative approaches using machine learning to optimize ventilation strategies.

1. Statistical Analysis:

- Please address the apparent discrepancy between univariate and multivariate analyses regarding MP's association with mortality. The discussion in lines 203-210 needs expansion.

- The Cox survival analysis results (p=0.35) need clearer interpretation, particularly given its implications for your safe limits hypothesis

- Consider additional sensitivity analyses to validate your identified MP thresholds

2. Machine Learning:

- Provide more details about the model development process, particularly:

* Feature selection criteria beyond correlation thresholds

* Rationale for choosing XGBoost over Stacking despite lower performance

3. Discussion:

- Strengthen the comparison with existing literature

- Elaborate on the unexpected findings in severe hypoxemia patients

- Add future research directions

Reviewer #3: (No Response)

**********

7. 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 #2: No

Reviewer #3: Yes: Manuel Ruiz-Botella

**********

[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.

Optimizing mechanical ventilation: personalizing mechanical power to reduce icu mortality - a retrospective cohort study

PONE-D-24-20623R3

Dear Dr.ahmed alkhalifah,

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,

Silvia Fiorelli

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #2: All comments have been addressed

**********

2. 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 #2: Yes

**********

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

Reviewer #2: Yes

**********

4. 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 #2: Yes

**********

5. 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 #2: Yes

**********

6. 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 #2: This manuscript presents a valuable contribution to the field of mechanical ventilation optimization through the analysis of mechanical power (MP) thresholds and their relationship with ICU mortality. The authors have satisfactorily addressed previous reviewer comments and made appropriate revisions to strengthen the manuscript.

The explanation for choosing XGBoost over Stacking despite slightly lower performance is reasonable, considering the practical implementation requirements in clinical settings. The discussion of unexpected findings in severely hypoxemic patients is comprehensive and well-reasoned.

While additional sensitivity analyses might have strengthened the findings further, the current analysis is sufficient for this proof-of-concept study. The authors have appropriately contextualized their findings within existing literature and acknowledged the limitations of their single-center database approach.

The manuscript provides important insights for clinical practice while maintaining a balanced view of the challenges and limitations in implementing personalized mechanical ventilation strategies. The clear presentation of safe upper limits for IBW-adjusted MP across different hypoxemia groups offers practical guidance for clinicians.

Based on these considerations, I recommend this manuscript for publication in its current form. The work represents a meaningful contribution to the field and provides a foundation for future research in mechanical ventilation optimization.

**********

7. 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 #2: No

**********