Analyzing and forecasting under-5 mortality trends in Bangladesh using machine learning techniques

Shayla Naznin; Md Jamal Uddin; Ishmam Ahmad; Ahmad Kabir

doi:10.1371/journal.pone.0317715

Peer Review History

Original SubmissionSeptember 20, 2024
20 Sep 2024 Author Response https://doi.org/10.1371/journal.pone.0317715.r001
22 Oct 2024 Decision Letter - Zeyar Aung, Editor PONE-D-24-41552Analyzing and Forecasting Under-5 Mortality Trends in Bangladesh using Machine Learning TechniquesPLOS ONE Dear Dr. Naznin, 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. ============================== MAJOR REVISION:The paper has limitations in terms of its technical contents and presentation.Please address all the comments by the reviewers carefully in your revised submission. Thank you. ============================== Please submit your revised manuscript by Dec 06 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, Zeyar Aung 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. 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. [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: Yes Reviewer #3: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes 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: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes 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: Here are my views: 1.The author should explore the distribution characteristics of data and the correlation between variables, so as to better explain why the linear model performs best. 2.Why does 5 - fold cross - validation perform best in most models? The author can analyze the distribution characteristics of data, the relationship between the sample quantity and the number of folds. 3.The research uses BDHS data and mentions integrating supplementary data from the World Bank and UNICEF. It is necessary to explain how these supplementary data enhance the robustness of the analysis. 4.The annual reduction rate is simply presented, but how ARR changes over time has not been explored. The connection between the change of ARR and specific intervention measures should be discussed. 5.The research predicts the trend until 2035, but does not discuss the reliability of long - term prediction, which is not rigorous enough. Reviewer #2: Comment #1 - (Abstract) - Linear Regression Overemphasis The abstract focuses too much on Linear Regression, neglecting a balanced discussion of other models' performance. Comment #2 - (Introduction) - Lack of Machine Learning Rationale The introduction does not explain why ML techniques were chosen over traditional methods. Comment #3 - (Methods) - Missing Model Justification No rationale is provided for selecting specific ML models like CatBoost or XGBoost. Comment #4 - (Methods) - Insufficient Data Preprocessing Details The paper lacks detail on how missing data and outliers were handled during preprocessing. Comment #5 - (Results) - Linear Regression Focus Other models' poor performance is not adequately discussed, with an overemphasis on Linear Regression. Comment #6 - (Results) - No External Validation The study lacks external validation to confirm the models' forecasting accuracy. Comment #7 - (Discussion) - Lack of Policy Implications The discussion does not translate the findings into specific policy recommendations. Comment #8 - (Discussion) - Missing External Variables Important variables like healthcare access and maternal health are not included in the models. Comment #9 - (Limitations) - Insufficient Data Bias Acknowledgment The limitations section does not sufficiently address biases in the self-reported data. Comment #10 - (Conclusion) - Overly Optimistic Projections The projections may be too optimistic, without considering potential socio-economic changes. Reviewer #3: Here are some feedback points and suggestions for improving the clarity and quality of the article: Abstract: 1. Conciseness: The abstract is comprehensive but could be slightly condensed for better readability. Consider trimming redundant phrases without losing essential details. - For example: “employs advanced machine learning models including...” could be shortened to “employs machine learning models like...” 2. Impact Statement: Add a brief sentence at the end highlighting the potential impact of your findings on policy and health interventions in Bangladesh. Background: 1. Context Clarity: Provide a brief explanation of why machine learning models are preferable for forecasting under-5 mortality, perhaps elaborating on the limitations of traditional methods. 2. Relevance: Emphasize the significance of choosing Bangladesh for this study, and how findings here may relate to global child mortality trends in similar countries. Methods: 1. Model Justification: Explain briefly why so many machine learning models were tested. It would be useful to state why linear models performed better for this dataset, such as due to linear trends in mortality rates. 2. Error Metrics: The evaluation metrics used (MAE, RMSE, etc.) are appropriate, but you could explain why these specific metrics were chosen and how they relate to practical applications of the forecasts. 3. Temporal Variables: When discussing lag features and rolling averages, briefly explain why these were incorporated to improve the model. Results: 1. Model Discussion: More emphasis could be placed on why linear models performed significantly better than non-inear models (e.g., Decision Tree, XGBoost). You could hypothesize why non-linear relationships were not as critical in predicting mortality rates. 2. Table Presentation: The table comparing model performances is very informative, but ensure the table is well-labeled with clear headings and definitions for each metric (e.g., explain MAE briefly). 3. Interpretation: In discussing the accuracy metrics, try to make a stronger connection between the model performance and real-world implications (e.g., how a lower RMSE can translate to better policy planning). Conclusions: 1. Policy Implications: While the conclusion mentions the gap between forecasted values and the SDG target, further elaboration on how the predictions can influence specific interventions or where further resources should be directed would strengthen the section. 2. Future Work: Suggest potential ways to improve the forecasting models or factors that future research should consider (e.g., incorporating more complex social or environmental variables). General Suggestions: - Grammar/Flow: Some sentences could be streamlined for better readability. For instance: “These techniques offer improved accuracy and reliability in forecasting providing valuable insights...” could be rephrased for smoother flow. - Consistency: Ensure consistent use of terms like “under-5 mortality” and “U5M” throughout the article. - Visuals: Including a well-labeled graph or chart illustrating the predicted trend in under-5 mortality over time would make the results more digestible for the reader. Overall, the article is informative and presents the data in a clear, structured manner. With a few adjustments to clarity, flow, and further explanation of key points, it will be more impactful. ****** 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: Yes: Ahmed Abdelmoety Reviewer #3: Yes: Neda Ahmadi ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org . Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0317715.r002
Revision 1
8 Dec 2024 Author Response Response to Editors & Reviewers “Analyzing and Forecasting Under-5 Mortality Trends in Bangladesh using Machine Learning Techniques” Ref: Manuscript Number:PONE-D-24-41552- [EMID:98e0e853d61e585b] Dear Editors, Regarding our manuscript, we thank you for the comments sent on October 22, 2024. My co-authors and I have revised the manuscript accordingly and would like it to be reconsidered for publication. As requested, we have included point-by-point responses to editors’ and reviewers’ comments below. Please let us know if anything further is required at this time, and we thank you very much for considering our revised manuscript. Shayla Naznin Editors comments Response The paper has limitations in terms of its technical contents and presentation. Please address all the comments by the reviewers carefully in your revised submission. Thank you. Thank you very much for your feedback! We have endeavored to address all of the reviewers’ comments as detailed below to further strengthen the paper. Reviewer 1 1.The author should explore the distribution characteristics of data and the correlation between variables, so as to better explain why the linear model performs best. Thank you for this careful reading of our Abstract has been revised line#210-218 2.Why does 5 - fold cross - validation perform best in most models? The author can analyze the distribution characteristics of data, the relationship between the sample quantity and the number of folds. The superior performance of 5-fold cross-validation likely arises from its balance between bias and variance, particularly with the dataset's small size. Splitting the data into 5 parts ensures adequate training data in each fold while maintaining reasonably sized validation sets, avoiding the instability of higher folds (e.g., leave-one-out) or the inefficiency of fewer folds. This balance makes it well-suited for small datasets. 3.The research uses BDHS data and mentions integrating supplementary data from the World Bank and UNICEF. It is necessary to explain how these supplementary data enhance the robustness of the analysis. Thank you for this careful reading this has been revised kindly address the line #131-164 4.The annual reduction rate is simply presented, but how ARR changes over time has not been explored. The connection between the change of ARR and specific intervention measures should be discussed. Thank you for this careful reading this has been revised in the line #427-440 5.The research predicts the trend until 2035, but does not discuss the reliability of long - term prediction, which is not rigorous enough. Thank you for this careful reading this has been revised kindly address the line #525-529 Reviewer 2 Comment #1 - (Abstract) - Linear Regression Overemphasis The abstract focuses too much on Linear Regression, neglecting a balanced discussion of other models' performance. Thank you for this careful reading this has been revised kindly address the line #10-63 Comment #2 - (Introduction) - Lack of Machine Learning Rationale The introduction does not explain why ML techniques were chosen over traditional methods. Thank you for this careful reading this has been revised kindly address the line #67-130 Comment #3 - (Methods) - Missing Model Justification No rationale is provided for selecting specific ML models like CatBoost or XGBoost. Thank you for this careful reading this has been revised kindly address the line #131-251 Comment #4 - (Methods) - Insufficient Data Preprocessing Details The paper lacks detail on how missing data and outliers were handled during preprocessing. Thank you for this careful reading this has been revised kindly address the line #131-251 Comment #5 - (Results) - Linear Regression Focus Other models' poor performance is not adequately discussed, with an overemphasis on Linear Regression. Thank you for this careful reading this has been revised kindly address the line #252-447 Comment #6 - (Results) - No External Validation The study lacks external validation to confirm the models' forecasting accuracy. Thank you for this careful reading this has been revised kindly address the line #252-447 Comment #7 - (Discussion) - Lack of Policy Implications The discussion does not translate the findings into specific policy recommendations. Thank you for this careful reading this has been revised kindly address the line #449-506 Comment #8 - (Discussion) - Missing External Variables Important variables like healthcare access and maternal health are not included in the models. Thank you for this careful reading this has been revised kindly address the line #449-506 Comment #9 - (Limitations) - Insufficient Data Bias Acknowledgment The limitations section does not sufficiently address biases in the self-reported data. Thank you for this careful reading this has been revised kindly address the line #508-543 Comment #10 - (Conclusion) - Overly Optimistic Projections The projections may be too optimistic, without considering potential socio-economic changes. Thank you for this careful reading this has been revised kindly address the line #545-597 Reviewer 3 Abstract: 1. Conciseness: The abstract is comprehensive but could be slightly condensed for better readability. Consider trimming redundant phrases without losing essential details. - For example: “employs advanced machine learning models including...” could be shortened to “employs machine learning models like...” Thank you for this careful reading this has been revised kindly address the line #10-63 2. Impact Statement: Add a brief sentence at the end highlighting the potential impact of your findings on policy and health interventions in Bangladesh. Thank you for this careful reading this has been revised kindly address the line #10-63 Background: 1. Context Clarity: Provide a brief explanation of why machine learning models are preferable for forecasting under-5 mortality, perhaps elaborating on the limitations of traditional methods. 2. Relevance: Emphasize the significance of choosing Bangladesh for this study, and how findings here may relate to global child mortality trends in similar countries. Thank you for this careful reading this has been revised kindly address the line #10-63 & 67-130 Methods: 1. Model Justification: Explain briefly why so many machine learning models were tested. It would be useful to state why linear models performed better for this dataset, such as due to linear trends in mortality rates. 2. Error Metrics: The evaluation metrics used (MAE, RMSE, etc.) are appropriate, but you could explain why these specific metrics were chosen and how they relate to practical applications of the forecasts. 3. Temporal Variables: When discussing lag features and rolling averages, briefly explain why these were incorporated to improve the model. Thank you for this careful reading this has been revised kindly address the line #131-251 Results: 1. Model Discussion: More emphasis could be placed on why linear models performed significantly better than non-inear models (e.g., Decision Tree, XGBoost). You could hypothesize why non-linear relationships were not as critical in predicting mortality rates. 2. Table Presentation: The table comparing model performances is very informative, but ensure the table is well-labeled with clear headings and definitions for each metric (e.g., explain MAE briefly). 3. Interpretation: In discussing the accuracy metrics, try to make a stronger connection between the model performance and real-world implications (e.g., how a lower RMSE can translate to better policy planning). Thank you for this careful reading this has been revised kindly address the line #252-447 Conclusions: 1. Policy Implications: While the conclusion mentions the gap between forecasted values and the SDG target, further elaboration on how the predictions can influence specific interventions or where further resources should be directed would strengthen the section. 2. Future Work: Suggest potential ways to improve the forecasting models or factors that future research should consider (e.g., incorporating more complex social or environmental variables). Thank you for this careful reading this has been revised kindly address the line #545-597 General Suggestions: - Grammar/Flow: Some sentences could be streamlined for better readability. For instance: “These techniques offer improved accuracy and reliability in forecasting providing valuable insights...” could be rephrased for smoother flow. - Consistency: Ensure consistent use of terms like “under-5 mortality” and “U5M” throughout the article. - Visuals: Including a well-labeled graph or chart illustrating the predicted trend in under-5 mortality over time would make the results more digestible for the reader. Overall, the article is informative and presents the data in a clear, structured manner. With a few adjustments to clarity, flow, and further explanation of key points, it will be more impactful. Thank you for this careful reading this has been revised Attachments Attachment Submitted filename: point by point Response - Review 1.doc https://doi.org/10.1371/journal.pone.0317715.r003
3 Jan 2025 Decision Letter - Zeyar Aung, Editor Analyzing and Forecasting Under-5 Mortality Trends in Bangladesh using Machine Learning Techniques PONE-D-24-41552R1 Dear Dr. Naznin, 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, Zeyar Aung 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 #1: (No Response) 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 #1: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy 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 ****** 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: 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 #1: Upon reviewing the revised manuscript titled 'Analyzing and Forecasting Under-5 Mortality Trends in Bangladesh using Machine Learning Techniques,' I am pleased to see that the authors have addressed my comments. I have expanded upon the data distribution and correlation, which provides a clearer rationale for the superior performance of the linear model. The explanation of why 5-fold cross-validation is most effective, especially given the small dataset, is both clear and convincing. They have included a justification for the inclusion of supplementary data from the World Bank and UNICEF, which enhances the robustness of the analysis. The discussion on the annual reduction rate and its connection to intervention measures is now more detailed, and the manuscript addresses the reliability of long-term predictions, which was a significant concern. They have rectified the overemphasis on Linear Regression in the abstract, providing a more balanced discussion of all models. The rationale for choosing machine learning techniques over traditional methods has been articulated in the introduction, and the justification for specific model selections has been included in the methods section. Furthermore, they have detailed the data preprocessing steps, including handling of missing data and outliers. The discussion on policy implications has been strengthened, and the manuscript now better translates findings into actionable policy recommendations. Overall, the revisions have significantly strengthened the manuscript, making it a valuable contribution to the field of public health forecasting. I recommend acceptance of this manuscript for publication in PLOS ONE. Reviewer #2: All comments have been thoroughly addressed. Thank you to the authors for their diligent efforts and thoughtful revisions. The paper is now ready for 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 #1: No Reviewer #2: Yes: Ahmed AbdelMoety ******** https://doi.org/10.1371/journal.pone.0317715.r004
Formally Accepted
Acceptance Letter - Zeyar Aung, Editor PONE-D-24-41552R1 PLOS ONE Dear Dr. Naznin, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Zeyar Aung Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0317715.r005

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .