-->PONE-D-26-02771-->-->Estimation of Resting Metabolic Rate in Professional Soccer Players: A Cross-Sectional Study Comparing Traditional Predictive Equations and a Pilot Machine Learning Model Against Indirect Calorimetry-->-->PLOS One

Dear Dr. López-Gil,

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: Dear Author, please revise your manuscript based on the comments provided by the reviewers. -->

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

Please submit your revised manuscript by May 01 2026 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 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,

Zulkarnain Jaafar

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. Please include a complete copy of PLOS’ questionnaire on inclusivity in global research in your revised manuscript. Our policy for research in this area aims to improve transparency in the reporting of research performed outside of researchers’ own country or community. The policy applies to researchers who have travelled to a different country to conduct research, research with Indigenous populations or their lands, and research on cultural artefacts. The questionnaire can also be requested at the journal’s discretion for any other submissions, even if these conditions are not met.  Please find more information on the policy and a link to download a blank copy of the questionnaire here: https://journals.plos.org/plosone/s/best-practices-in-research-reporting. Please upload a completed version of your questionnaire as Supporting Information when you resubmit your manuscript.

4. We note that your Data Availability Statement is currently as follows: “All relevant data are within the manuscript and its Supporting Information files.”

Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition).

For example, authors should submit the following data:

- The values behind the means, standard deviations and other measures reported;

- The values used to build graphs;

- The points extracted from images for analysis.

Authors do not need to submit their entire data set if only a portion of the data was used in the reported study.

If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories.

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

5. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager.

6. 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?

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: Partly

Reviewer #2: No

**********

-->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 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: 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: No

**********

-->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: This study evaluated the agreement between twelve traditional RMR predictive equations and indirect calorimetry (IC) measurements in professional male soccer players, and introduced a machine learning approach (Support Vector Regression) to test prediction accuracy of athletes’ RMR. My comments and suggestions are presented as follows.

1)The machine learning sample consisted of 40 cases, which may be insufficient for constructing a robust predictive model (as acknowledged by the authors in the limitations section). A small sample size increases the risk of overfitting. Although the study conducted cross-validation and learning curve analyses, if feasible, it would be beneficial to report the effect size (as illustrated in Figure 1) of the predictive model to further validate model stability. In addition, while cross-validation was performed, the specific method should be clearly stated. Was k-fold cross-validation used, or another approach?

2)The model included body mass, stature, BMI, and BSA as predictors. Given that BMI and BSA are calculated from body mass and stature, correlations exist among these variables, potentially leading to multicollinearity. It is recommended that variance inflation factor (VIF) diagnostics be conducted to assess the extent of multicollinearity.

3)In the study, the dataset was randomly partitioned into an 80–20 split for model training and external validation. However, this procedure still constitutes internal hold-out validation. True external validation would require testing the model on an independent dataset from a separate group of athletes.

4)The discussion section, the authors may consider discussing whether similar modeling approaches have been adopted in prior research and comparing their findings with existing studies. This would help clarify the theoretical contribution and practical implications of the present study.

Reviewer #2: Manuscript Number: PONE-D-26-02771

Title: Estimation of Resting Metabolic Rate in Professional Soccer Players: A Cross-Sectional Study Comparing Traditional Predictive Equations and a Pilot Machine Learning Model Against Indirect Calorimetry

Abstract

This study evaluated the accuracy of 12 traditional resting metabolic rate (RMR) prediction equations in professional football (soccer) players by comparing them with indirect calorimetry (IC). The findings revealed that all traditional equations performed poorly, systematically overestimating RMR. In contrast, the research team developed an optimized Support Vector Regression (SVR) machine learning model, which demonstrated significantly superior predictive accuracy compared to the traditional equations (MAE: 169.3 kcal/day). These results set the stage for a discussion of the study's overall impact and limitations.

Overall Impression

The chosen topic holds significant practical importance, as it directly addresses a core challenge in sports nutrition: accurately assessing the energy requirements of athletes. Introducing machine learning methods to this field represents noteworthy methodological innovation. While the study offers valuable insights, it faces some limitations, including sample size, data age, methodological details, and result interpretation, which may affect the generalizability and immediate practical applicability of the model.

Review Conclusion

Major Revision

Major Comments

Below are the key issues that require the authors' focused revision and response:

1. Small Sample Size and Outdated Data (Critical Limitation)

Problem: The study sample consists of only 40 individuals, with data collected in 2014 (referred to as the "Opening Tournament 2014"). This small sample size not only limits the training efficacy and generalizability of the machine learning model (even though the authors use learning curves to suggest no overfitting, the small sample remains a major constraint) but also raises questions about whether data nearly a decade old accurately reflects the physiological characteristics of current professional football players. Training methodologies, nutritional strategies, and athlete body composition have evolved significantly over the past decade.

Suggestions:

(1)In the discussion section, this must be addressed more profoundly and transparently as the primary limitation. Clearly state the impact of the small sample size and outdated data on the generalizability of the conclusions.

(2)Explicitly frame the machine learning model as a "pilot exploration," as already indicated in the title and text. Emphasize that its results require external validation in larger, multi-center, and more recent cohorts before any practical application can be considered.

(3)If possible, attempt to contact the authors or the club to see if newer or additional data can be obtained to augment the sample. However, this is often difficult to achieve, so a frank acknowledgment of the limitations is the more realistic path forward.

2. Lack of External Validation for the Machine Learning Model

Problem:The model's superior performance is demonstrated solely based on an internal validation set (20% of the data) and cross-validation. In machine learning research, the absence of an independent external validation set is a critical weakness. This leaves the true generalizability of the model unknown, with a risk of overfitting to the specific characteristics of these 40 players. Although the authors examined learning curves, this does not substitute for external validation.

Suggestions:

(1) Explicit Differentiation:In the title, abstract, and conclusions, employ more cautious phrasing, such as "preliminary results suggest," "demonstrated strong performance in internal validation," etc., to avoid creating the impression that the model is ready for widespread application.

(2) Future Research Direction:In the discussion section, emphasize "external validation" as the most critical next step for research. Concrete suggestions could be made that future studies should validate the model in professional player cohorts from different leagues, different countries, and different age groups.

3. Lack of Methodological Clarity

Problem:The description of data preprocessing and feature engineering for the machine learning part is vague. For instance, how exactly were the "nonlinear and interaction terms" created? Which features were used? Similarly, the specific range and methods for hyperparameter tuning are not described, affecting the reproducibility of the study.

Suggestions:

(1) In the "Machine Learning Analysis" section, supplement the text with a table listing all features ultimately input into the model (e.g., weight, height, BMI, body surface area, and potentially constructed interaction terms like weight², weight × height).

(2) Provide a detailed description of the hyperparameter tuning process. For example, for the SVR model, specify the kernel function type (e.g., RBF kernel) and describe the range used for tuning parameters such as C, epsilon, and gamma using methods like GridSearch or RandomizedSearch, along with the final optimal values chosen. This would greatly enhance the scientific rigor of the study.

4. Contradictory Presentation and Over-interpretation of Results

Problem:The abstract mentions that the SVR model "reduced the error by 227 to 379 kcal/day." This value appears derived by subtracting the SVR's MAE from the "bias" of the traditional equations. This comparison is misleading. MAE measures the average absolute error at the individual level, while "bias" is the average difference (mean error). These are not the same concept, and directly subtracting them exaggerates the improvement. Furthermore, the SVR model's R² is only 0.169. Although this is better than the negative or near-zero values of the traditional equations, it still means the model can only explain approximately 17% of the variance in RMR, indicating its predictive capability is actually quite limited.

Suggestions:

(1) Rephrase the relevant descriptions in the abstract and conclusions. A more accurate statement would be: The SVR model's prediction error (MAE) was substantially lower than the average bias or RMSE of the traditional equations, demonstrating higher accuracy in individual prediction. Avoid directly subtracting values to derive a specific "reduction" range.

(2) In the discussion, provide a balanced interpretation of the R² value of 0.169. Acknowledge its progress compared to the traditional equations, while candidly pointing out that a large amount of unexplained variance remains. This highlights the complexity of RMR and suggests that future work may need to incorporate more predictive factors (such as training load, hormonal levels, more precise body composition data, etc.).

Competing Interests Statement is Vague

Problem:Some authors have affiliations with Breezing Co., the company that manufactures the device used in this study. Although the statement mentions "no financial compensation was received," "technical consulting and development support" in itself constitutes a potential conflict of interest that could influence the objectivity of the research. The statement claims this "did not influence the study outcomes," but this judgment should ultimately be made by the reviewers and readers.

Suggestion:

(1) It is recommended that the authors provide a clearer and more transparent competing interests statement. For example, they could specify the nature and duration of the consulting/support, and the measures taken to prevent bias (e.g., data analysis was performed by a third party not involved in the commercial collaboration). The current statement, "It did not influence the study outcomes," is overly subjective. PLOS has strict requirements regarding competing interests; vague language could potentially raise issues.

Minor Comments

Writing and Grammar: The overall readability of the manuscript is acceptable, but there are minor grammatical errors and instances of unnatural phrasing. For example, the sentence in the abstract, "corresponding to a reduction of 227 to 379 kcal·day-1 based on the difference between its MAE and the observed biases," as previously noted, is inaccurately phrased and grammatically awkward. It is suggested that the authors ask a native English-speaking colleague or a professional editing service to polish the language of the full manuscript to enhance fluency and professionalism.

Clarity of Figures/Tables:

Table 3:The title is in English, but the header for the first column is "Modelo" (Spanish/Portuguese). This should be unified to English, i.e., "Model." Please review the entire manuscript to ensure all elements are in English.

Figure 1:The figure legend mentions "RMSE and bias values," but these numerical values are not shown in the figure itself; only effect sizes are displayed. It is recommended to either annotate the RMSE and bias for key equations directly on the figure or provide this information in a separate table for more complete presentation.

Reference Format: Please check the reference format to ensure it fully complies with the journal requirements of PLOS One. For instance, in reference number 5, the journal name is written in all capitals; this should be corrected to the standard format.

Data Availability Statement: The authors state, "All relevant data are within the manuscript and its Supporting Information files." It is recommended that the authors upload the anonymized data for the 40 players used to train the SVR model (age, height, weight, IC-measured RMR values) as a Supporting Information file. This would genuinely make the data open, which is a core policy requirement of PLOS journals.

Additional Comments

Introduction Section The introduction effectively establishes the background and necessity of the study. It could be slightly streamlined by reducing general knowledge about energy expenditure in football and focusing more on the limitations of existing RMR prediction equations in athletic populations. This would better highlight the innovative aspects and urgency of this research.

Discussion Section: The discussion provides a thorough analysis of why the traditional equations fail. However, when discussing the advantages of the ML model, greater caution is needed to avoid giving the erroneous impression that the "ML model is good enough." Its "preliminary" nature and the need for "validation" must be repeatedly emphasized. Concurrently, future research directions could be made more concrete. For example, proposing an ideal study design: a prospective, multi-center cohort study collecting multi-dimensional data including DXA body composition, training load, and hormonal levels to build and validate more robust prediction models.

Conclusion

This is an interesting study with innovative potential. It highlights the significant inadequacy of traditional RMR prediction equations in elite athletes and explores the feasibility of machine learning as an alternative approach. However, the notable shortcomings concerning sample size, data age, methodological transparency, and result interpretation mean that, in its current form, it is not yet suitable for acceptance by PLOS One

If the authors are able to undertake a major revision, discussing the study's limitations candidly and in depth, providing more transparent methodological details, and offering a more rigorous and balanced interpretation of the results, then this paper could become highly valuable. The value of the revised manuscript would lie primarily in its role as a warning to practitioners against relying on traditional equations, and in providing important proof-of-concept and directional guidance for future research on exercise metabolism utilizing larger datasets and advanced methodologies. We encourage the authors to carefully revise the manuscript according to the comments above and look forward to seeing the revised version.

**********

-->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

**********

[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.

-->PONE-D-26-02771R1-->-->Estimation of Resting Metabolic Rate in Professional Soccer Players: A Cross-Sectional Study Comparing Traditional Predictive Equations and a Preliminary Machine Learning Model Against Indirect Calorimetry-->-->PLOS One

Dear Dr. López-Gil,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Jul 17 2026 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 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.

As the corresponding author, your ORCID iD is verified in the submission system and will appear in the published article. PLOS supports the use of ORCID, and we encourage all coauthors to register for an ORCID iD and use it as well. Please encourage your coauthors to verify their ORCID iD within the submission system before final acceptance, as unverified ORCID iDs will not appear in the published article. Only  the individual author can complete the verification step; PLOS staff cannot  verify ORCID iDs on behalf of authors.

We look forward to receiving your revised manuscript.

Kind regards,

Zulkarnain Jaafar

Academic Editor

PLOS One

Journal Requirements:

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:

Dear Author, your manuscript still requiring major corrections. Please make necessary changes based on the comments provided by the reviewer.

[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 #1: All comments have been addressed

Reviewer #2: (No Response)

**********

-->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 #1: Yes

Reviewer #2: No

**********

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

Reviewer #1: Yes

Reviewer #2: No

**********

-->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 #1: Yes

Reviewer #2: No

**********

-->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 #1: Yes

Reviewer #2: No

**********

-->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 #1: The sample size is the main concern of this study; the authors have acknowledged this point in the limitations section and clarified that this study is intended as a proof-of-concept.

Reviewer #2: (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 #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.

Attachments

Attachment

Submitted filename: Minor Revision .doc

-->PONE-D-26-02771R2-->-->Estimation of Resting Metabolic Rate in Professional Soccer Players: A Cross-Sectional Study Comparing Traditional Predictive Equations and a Preliminary Machine Learning Model Against Indirect Calorimetry-->-->PLOS One

Dear Dr.  López-Gil,

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 Aug 06 2026 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 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.

As the corresponding author, your ORCID iD is verified in the submission system and will appear in the published article. PLOS supports the use of ORCID, and we encourage all coauthors to register for an ORCID iD and use it as well. Please encourage your coauthors to verify their ORCID iD within the submission system before final acceptance, as unverified ORCID iDs will not appear in the published article. Only  the individual author can complete the verification step; PLOS staff cannot  verify ORCID iDs on behalf of authors.

We look forward to receiving your revised manuscript.

Kind regards,

Zulkarnain Jaafar

Academic Editor

PLOS One

Journal Requirements:

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:

Dear Author, please revise your manuscript based on the comments provided by the reviewer.

[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)

**********

-->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

**********

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

Reviewer #2: No

**********

-->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: No

**********

-->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: Reviewer Comments

Recommendation: Major Revision

This revised manuscript addresses an applied and relevant question: whether commonly used resting metabolic rate prediction equations are suitable for professional soccer players, using indirect calorimetry as the reference method, and whether a preliminary machine-learning model may improve prediction. The topic is of practical interest to sports nutrition and athlete monitoring, and the comparison against indirect calorimetry is appropriate. The manuscript has also improved in tone by presenting the machine-learning component more cautiously as exploratory.

However, several issues still require clarification before the manuscript can be considered suitable for publication. The main concerns relate to the consistency of the submitted files, the strength of the claims regarding the SVR model, the small sample size, model validation, multicollinearity among predictors, and the need for full transparency regarding ethics, data availability, and numerical consistency.

Major Comments

1. Potential inconsistency in the submitted review file

The reviewer PDF appears to contain a response-to-reviewers section referring to a different manuscript, titled “Optimizing Football Analytics: Dimensionality Reduction Meets Machine Learning for Offensive and Defensive Player Profiling,” with comments about PCA, SHAP, offensive and defensive player profiling, and train-test leakage. This content does not correspond to the present manuscript on resting metabolic rate in professional soccer players.

The authors and editorial office should verify whether this is a file-compilation error or whether incorrect response material was included in the submission. A clean and internally consistent manuscript package should be submitted.

2. The machine-learning model should remain clearly framed as exploratory

The SVR model is potentially interesting, but the dataset is small, with only 40 participants. If the model development used an 80/20 split, the held-out validation subset would include only approximately eight participants, making performance estimates highly unstable. Although the model showed lower MAE/RMSE than traditional equations, the reported R² of 0.169 indicates that most between-individual variability in RMR remains unexplained.

The manuscript should avoid any wording suggesting that the SVR model is validated, generalizable, reliable for practice, or ready for applied use. It should consistently be described as a preliminary, proof-of-concept internal-validation analysis requiring external validation.

3. Validation strategy and data leakage prevention must be fully transparent

The Methods should clearly state the exact validation procedure, including:

o the training/validation split ratio;

o whether hyperparameter tuning was conducted only within the training subset;

o whether preprocessing, outlier screening, scaling, and feature engineering were fitted only on the training data;

o whether the held-out subset was used only once for final internal validation.

Given the small sample, the authors should also explicitly acknowledge the risk of optimistic performance estimates.

4. Multicollinearity among predictors should be handled cautiously

Several predictors used in the SVR model are mathematically related, including body mass, stature, BMI, BSA, squared body mass, and body mass × stature. This creates strong multicollinearity by construction, especially problematic with n = 40.

The authors should report VIF diagnostics or clearly state that the model is intended only for prediction and that no inference is made regarding the independent contribution or biological importance of individual predictors.

5. Indirect calorimetry procedures require sufficient methodological detail

Since indirect calorimetry is treated as the reference standard, the manuscript should provide adequate detail on the measurement protocol, including device calibration, fasting status, prior exercise restrictions, caffeine or stimulant control, environmental conditions, resting period, measurement duration, steady-state criteria, and handling of implausible respiratory exchange ratio values. Without these details, the validity of the reference RMR values is difficult to assess.

6. Numerical consistency across text, tables, and figures should be checked

The response indicates that previous inconsistencies existed regarding relative error rankings, bias ranges, Pearson correlations, and the definition of “best-performing” equations. The revised manuscript should ensure that all numerical statements in the Abstract, Results, Discussion, tables, and figure captions are fully consistent.

In particular, “best-performing” should be defined consistently, as different metrics may identify different equations: lowest RMSE, lowest bias, highest ICC/CCC, or lowest relative error.

7. Ethics and consent timeline should be clarified

The manuscript should clearly explain the apparent discrepancy between data collection in 2014 and the later ethics approval code. If the approval covered retrospective analysis and anonymized data sharing, this should be explicitly stated. The authors should also confirm that informed consent, and parental consent for minors where applicable, covered research use and public sharing of anonymized data.

Minor Comments

1. The conclusion “traditional equations are not suitable” may be too strong. A more cautious phrasing would be “traditional equations showed poor agreement in this sample of professional soccer players.”

2. Units should be standardized throughout the manuscript, especially kcal/day versus kcal·day⁻¹.

3. The abstract should maintain the cautious framing of the SVR model and avoid implying external validity.

4. The competing-interest statement should clearly identify any relationship with the indirect-calorimetry device or company, the authors involved, the role of the company, and who conducted the statistical analyses.

5. The Data Availability Statement should provide a clear and accessible link to the dataset and specify whether the shared dataset is raw, processed, or anonymized.

Overall Assessment

The manuscript has potential and addresses a useful applied problem. The strongest contribution is the finding that traditional RMR prediction equations show poor agreement with indirect calorimetry in this specific population. The machine-learning component is interesting but should remain secondary and exploratory because of the small sample size, limited internal validation, low R², and absence of external validation.

I recommend major revision, primarily to ensure file consistency, strengthen methodological transparency, moderate the interpretation of the SVR model, and confirm that all numerical and ethical statements are internally consistent.

**********

-->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

**********

[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.

Estimation of Resting Metabolic Rate in Professional Soccer Players: A Cross-Sectional Study Comparing Traditional Predictive Equations and a Preliminary Machine Learning Model Against Indirect Calorimetry

PONE-D-26-02771R3

Dear Dr. López-Gil,

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,

Zulkarnain Jaafar

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: I thank the authors for their careful and comprehensive responses to my comments. The revised manuscript appears to have addressed the main methodological, interpretive, numerical, ethical, and reporting concerns raised in the previous round. I particularly appreciate the more cautious framing of the machine-learning analysis, the clearer description of the validation procedure, and the improved reporting of the indirect calorimetry protocol.

I have no further substantive concerns and recommend acceptance.

**********

-->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

**********