Assessing the value of deep neural networks for postoperative complication prediction in pancreaticoduodenectomy patients

Mikkel Bonde; Alexander Bonde; Haytham Kaafarani; Andreas Millarch; Martin Sillesen

doi:10.1371/journal.pone.0316402

Peer Review History

Original SubmissionSeptember 20, 2023
30 Jan 2024 Decision Letter - Robert Jeenchen Chen, Editor Transfer Alert This paper was transferred from another journal. As a result, its full editorial history (including decision letters, peer reviews and author responses) may not be present. PONE-D-23-30439ASSESSING THE VALUE OF DEEP NEURAL NETWORKS FOR POSTOPERARTIVE COMPLICATION PREDICTION IN PANCREATICODUODENECTOMY PATIENTSPLOS ONE Dear Dr. Sillesen, 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 revise. Please submit your revised manuscript by Mar 15 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, Robert Jeenchen Chen, MD, MPH 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 provide additional details regarding participant consent. In the ethics statement in the Methods and online submission information, please ensure that you have specified what type you obtained (for instance, written or verbal, and if verbal, how it was documented and witnessed). If your study included minors, state whether you obtained consent from parents or guardians. If the need for consent was waived by the ethics committee, please include this information. 3. Thank you for stating the following in the Competing Interests section: "I have read the journal's policy and the authors of this manuscript have the following competing interests: Authors AB and MS have founded Aiomic Aps, a healthtech company fielding artificial intelligence models for healthcare use. The present work is for research only and is not related to any commercial activities." Please confirm that this does not alter your adherence to all PLOS ONE policies on sharing data and materials, by including the following statement: "This does not alter our adherence to PLOS ONE policies on sharing data and materials.” (as detailed online in our guide for authors http://journals.plos.org/plosone/s/competing-interests). If there are restrictions on sharing of data and/or materials, please state these. Please note that we cannot proceed with consideration of your article until this information has been declared. Please include your updated Competing Interests statement in your cover letter; we will change the online submission form on your behalf. [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: No Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: No Reviewer #2: 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 ****** 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 ****** 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: I appreciate the opportunity to examine this interesting paper. Nevertheless, there are a few concerns regarding the work. Conduct a comprehensive review of existing literature pertaining to the utilization of machine learning and deep learning techniques in the context of mortality and morbidity, as well as any relevant studies in related fields. The utilization of Deep Neural Networks (DNN) and Random Forest (RF) can be justified based on their respective advantages and capabilities. There are numerous AI algorithms available, with the latest one being ensemble learning, which offers superior performance. Deep neural networks (DNN) may not consistently perform as effectively as other machine learning methods, but they are particularly notable for their application in image processing. This is evident when the area under the curve (AUC) has a relatively low value. A value that is considered acceptable is 0.75 or higher. The authors should explicitly state their objective and anticipated outcome in the objective section. As I comprehend, there are multiple morbidity outcomes and death outcomes, and the authors conducted different modeling for each result. Alternatively, is it a prediction involving many classes? The authors should explicitly articulate this. In the data section, specify the percentage of missing values for final variables and identify the data imputation method employed. The authors determined the final features from the 150 variables listed in the study. The ultimate result must also be explicitly expressed. It is necessary to provide a clear explanation of how the dataset is allocated to the four models. How did the authors address the issue of data imbalance, which can explain the low AUC value? There is a noticeable imbalance in the data when merging patients with PD with people without PD. Summary statistics of each dataset are compared against the outcome using chi square analysis, yielding the chi square value for categorical and corresponding p-value continuous variable. Did the authors undertake parameter optimization on the RF model to enhance its performance? Support Vector Machines (SVM) are a suitable option for conducting benchmarking. I suggest incorporating Net Index Reclassification (NRI) for the purpose of comparing it with traditional methodologies. Additionally, the use of SHAP can provide a clearer understanding of the relationship between input properties and the resulting conclusion. Reviewer #2: I commend you for taking up a comprehensive research analysis of data set and use it for prediction of post operative complications in a subset of pancreaticoduodenectomy cases. The different models formulated and tested are based on sound reasoning and parameters. I hope that, with use of similar computer-generated applications in health care research would help resolve many issues in future ****** 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: Yes: sorayya malek Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0316402.r001
Revision 1
7 Jun 2024 Author Response Dear Dr. Chen Thank you for the opportunity to resubmit our manuscript. Please find a point-by-point response to reviewers’ comments below. Also, please do not hesitate to reach out to us if further information is required. On behalf of the authors Martin Sillesen MD, PhD Assoc. Prof. of Surgery Dep. of Organ Surgery and Transplantation Copenhagen University Hospital, Rigshospitalet Denmark Martin.Sillesen@Regionh.dk Journal Requirements: When submitting your revision, we need you to address these additional requirements. Comment #1 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 Response: Thank you for highlighting this. The formatting issues have been addressed. Comment #2 2. Please provide additional details regarding participant consent. In the ethics statement in the Methods and online submission information, please ensure that you have specified what type you obtained (for instance, written or verbal, and if verbal, how it was documented and witnessed). If your study included minors, state whether you obtained consent from parents or guardians. If the need for consent was waived by the ethics committee, please include this information. Response: Thank you for this question. The project received a waiver of IRB approval from the Massachusetts General Hospital IRB. This is stated in the methods section. We have expanded this section further to detail that this entailed that patient consent was not required and thus not obtained. Comment #3 3. Thank you for stating the following in the Competing Interests section: "I have read the journal's policy and the authors of this manuscript have the following competing interests: Authors AB and MS have founded Aiomic Aps, a healthtech company fielding artificial intelligence models for healthcare use. The present work is for research only and is not related to any commercial activities." Response: You are welcome Comment #4 Please confirm that this does not alter your adherence to all PLOS ONE policies on sharing data and materials, by including the following statement: "This does not alter our adherence to PLOS ONE policies on sharing data and materials.” (as detailed online in our guide for authors http://journals.plos.org/plosone/s/competing-interests). If there are restrictions on sharing of data and/or materials, please state these. Please note that we cannot proceed with consideration of your article until this information has been declared. Please include your updated Competing Interests statement in your cover letter; we will change the online submission form on your behalf. Response: Thank you, we have updated the cover letter with the required information. Reviewers' comments: Reviewer's Responses to Questions Comments to the Author Reviewer #1: Comment #5 I appreciate the opportunity to examine this interesting paper. Nevertheless, there are a few concerns regarding the work. Conduct a comprehensive review of existing literature pertaining to the utilization of machine learning and deep learning techniques in the context of mortality and morbidity, as well as any relevant studies in related fields. The utilization of Deep Neural Networks (DNN) and Random Forest (RF) can be justified based on their respective advantages and capabilities. There are numerous AI algorithms available, with the latest one being ensemble learning, which offers superior performance. Deep neural networks (DNN) may not consistently perform as effectively as other machine learning methods, but they are particularly notable for their application in image processing. This is evident when the area under the curve (AUC) has a relatively low value. A value that is considered acceptable is 0.75 or higher. The authors should explicitly state their objective and anticipated outcome in the objective section. As I comprehend, there are multiple morbidity outcomes and death outcomes, and the authors conducted different modeling for each result. Alternatively, is it a prediction involving many classes? The authors should explicitly articulate this. Response: Thank you these comments. Overall, we fully agree with the reviewer that there are multiple different modeling options well suited for this prediction task. We have chosen the DNN architecture, as we have previously demonstrated superior performance using this approach on a general surgical dataset (Manuscript reference #12). In this modeling study, we use the DNNs to do multiclass prediction, so it is essentially the same network used for multi-label prediction of several different postoperative complications. We have augmented the manuscript with a further description of this important point, as well as elaborated on the expected outcome in the introduction as requested. Comment #6 In the data section, specify the percentage of missing values for final variables and identify the data imputation method employed. Response : Thank you for this question. We agree that the issue of missing data is important. For the final (output) variables, the dataset was complete and thus did not have missing data. This is because the NSQIP database does not allow for incomplete postoperative complication data entry when submitting cases. We have added this information to the methods section of the manuscript, as well as included a description of how missing data was handled for input variables. For the input data, an overview of demographic variables between datasets, as well as the percentage of missing data, has now been included in the supplementary data table 1. Comment #7 The authors determined the final features from the 150 variables listed in the study. The ultimate result must also be explicitly expressed. It is necessary to provide a clear explanation of how the dataset is allocated to the four models. How did the authors address the issue of data imbalance, which can explain the low AUC value? There is a noticeable imbalance in the data when merging patients with PD with people without PD. Response: Thank you for this insightful question. We agree that a full overview of the input features is important for assessing the data on which the model performs its predictions. We have added a table detailing the input features as supplementary data. The reviewer is indeed correct in stating that the class imbalance in the data may well impact on the AUC performance score. This problem often occurs in postoperative complication data, as the outcomes are infrequent. We have, however, sought to address this through the introduction of positive weights applied to the loss function of the DNN. This approach has been further detailed in the methods section Comment #8 Summary statistics of each dataset are compared against the outcome using chi square analysis, yielding the chi square value for categorical and corresponding p-value continuous variable. Response: In this study, we have not calculated summary statistics of the different datasets for several reasons. First, the objective is not to determine whether significant differences existed between input and output variables. This is no doubt the case, as a general surgical cohort will for example have a different spectrum and incidence of postoperative complications as would a specific pancreatic cohort. We thus feel that the objective of the study is not to compare cohorts and identify differences in these, but rather to investigate how optimal training of a PD specific model can be achieved. Even if it was chosen that summary statistics were required, the number of input and output variables would necessitate correction for multiple testing due to the number of variables included. As such, there would be a clear risk of a Type-II error, which again would diminish the usefulness of such a comparison. While this can in certain cases of cause be acceptable, we respectfully feel that a comparison of cohorts is not within the objective of this study. Rather this is a model comparison study. Comment #9 Did the authors undertake parameter optimization on the RF model to enhance its performance? Support Vector Machines (SVM) are a suitable option for conducting benchmarking. Response: Thank you for this comment. We agree that the SVM approach could be useful a study such as this. As suggested, we have benchmarked the RF models with an SVM approach with parameter optimization using grid search. This approach was inferior to the RF approach, resulting in a ROC AUC of 0.52 for morbidity and 0.50 for mortality. As such, the RF outperformed the grid search optimized SVM approach, indicating adequate hyper parameter optimization for the RF approach. This information has been added to the manuscript. Comment #10 I suggest incorporating Net Index Reclassification (NRI) for the purpose of comparing it with traditional methodologies. Response: Thank you for this suggestion. As suggested, we have included the NRI calculations as supplementary data, and updated the manuscript accordingly. Comment #11 Additionally, the use of SHAP can provide a clearer understanding of the relationship between input properties and the resulting conclusion. Response: Thank you for this suggestion. We agree that the addition of SHAP values would add value to the manuscript. We have thus included these in the revised manuscript. Comment#12 Reviewer #2: I commend you for taking up a comprehensive research analysis of data set and use it for prediction of post operative complications in a subset of pancreaticoduodenectomy cases. The different models formulated and tested are based on sound reasoning and parameters. I hope that, with use of similar computer-generated applications in health care research would help resolve many issues in future Response: Thank you for this comment! Attachments Attachment Submitted filename: Response to reviewers.docx https://doi.org/10.1371/journal.pone.0316402.r002
21 Oct 2024 Decision Letter - Robert Jeenchen Chen, Editor PONE-D-23-30439R1ASSESSING THE VALUE OF DEEP NEURAL NETWORKS FOR POSTOPERATIVE COMPLICATION PREDICTION IN PANCREATICODUODENECTOMY PATIENTSPLOS ONE Dear Dr. Sillesen, 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 address the preprint issue. Please submit your revised manuscript by Dec 05 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, Robert Jeenchen Chen, MD, MPH Academic Editor PLOS ONE [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: All comments have been addressed 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: Yes Reviewer #3: Partly ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #2: Yes Reviewer #3: I Don't Know ****** 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 ****** 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 ****** 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 very much for addressing the reviewers queries and concerns. I believe it would be suitable in the updated form. Reviewer #3: This is a preprint paper from https://www.medrxiv.org/content/10.1101/2023.08.21.23294364v1 This is a preprint paper from https://www.medrxiv.org/content/10.1101/2023.08.21.23294364v1 ****** 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: hazim alhiti ******** [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.0316402.r003
Revision 2
8 Nov 2024 Author Response Dear PLOSOne editorial team Thank you for assessing our submitted manuscript. We understand that reviews feel that questions have been addressed, but here seems to be an issue with the fact that the manuscript has previously been submitted as a preprint. To formally adhere to the review phases, please find a point-by-point response to comments below. Thank you again for the opportunity to resubmit our manuscript. On behalf of the authors Martin Sillesen MD, PhD Assoc. Prof. of Surgery Dep. of Organ Surgery and Transplantation Copenhagen University Hospital, Rigshospitalet Denmark Martin.Sillesen@Regionh.dk Reviewers' comments: Reviewer's Responses to Questions Comment #1 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 Reviewer #3: All comments have been addressed Response: Thank you Comment #2 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 very much for addressing the reviewers queries and concerns. I believe it would be suitable in the updated form. Reviewer #3: This is a preprint paper from https://www.medrxiv.org/content/10.1101/2023.08.21.23294364v1 This is a preprint paper from https://www.medrxiv.org/content/10.1101/2023.08.21.23294364v1 Response: It is indeed true that this manuscript has previously been submitted as a preprint, which we believe is in accordance with PLOSOne guidelines. This seems to be more of a comment pertaining to the fact this this has been presented as a preprint, rather than a request for edits from the side of the reviewer. However, from conversations with the editorial office, we understand that there is a request from the editorial office for “…authors to make more improvements from the version in the preprint. Please revise to show more improvements.”. The original preprint version was submitted in August 2023, whereas the present version was substantially edited based on the reviewer’s comments. As such, the preprint and the current manuscript is less than 80% identical to the preprint, indicating that 20% of the text has been updated/altered compared with the preprint. Furthermore, based on the reviewers inputs, we have updated the manuscript with new tables and data, added new modelling approaches including benchmarking with SVMs and included parameter optimization . We have, as per reviewers suggestions, included Net Index Classification and Shapley insights into driving factors as well as performed a general editing of the manuscript text. As such, we would respectfully argue that the current version of the manuscript is indeed very different from the preprint version. While we are of course open to performing other changes to the manuscript, we find it difficult to make changes to a manuscript that is already significantly different from its preprint version both in terms of text, data, figures, tables and methods without more specific instructions on where the editors see the need for improvements specifically. Attachments Attachment Submitted filename: Reponse to reviwers 2nd round.docx https://doi.org/10.1371/journal.pone.0316402.r004
10 Dec 2024 Decision Letter - Robert Jeenchen Chen, Editor ASSESSING THE VALUE OF DEEP NEURAL NETWORKS FOR POSTOPERATIVE COMPLICATION PREDICTION IN PANCREATICODUODENECTOMY PATIENTS PONE-D-23-30439R2 Dear Dr. Sillesen, 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, Robert Jeenchen Chen, MD, MPH, ChFC®, EA, CLU 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 #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 #3: (No Response) ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #3: 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 #3: 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 #3: 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 #3: hard work well done congratulations my final decision is acceptable ‎ my final decision is acceptable ‎ ****** 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 #3: Yes: Hazim Alhiti ******** https://doi.org/10.1371/journal.pone.0316402.r005
Formally Accepted
15 Dec 2024 Acceptance Letter - Robert Jeenchen Chen, Editor PONE-D-23-30439R2 PLOS ONE Dear Dr. Sillesen, 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. Robert Jeenchen Chen Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0316402.r006

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 .