Evolution of hospitalized patient characteristics through the first three COVID-19 waves in Paris area using machine learning analysis

Camille Jung; Jean-Baptiste Excoffier; Mathilde Raphaël-Rousseau; Noémie Salaün-Penquer; Matthieu Ortala; Christos Chouaid

doi:10.1371/journal.pone.0263266

Peer Review History

Original SubmissionSeptember 30, 2021
8 Nov 2021 Decision Letter - Kanhaiya Singh, Editor PONE-D-21-30788Evolution of hospitalized patient characteristics through the first three COVID-19 waves in Paris area using machine learning analysisPLOS ONE Dear Dr. Excoffier, 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 Dec 23 2021 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, Kanhaiya Singh, Ph.D Academic Editor PLOS ONE Additional Editor Comments (if provided): Although the reviewers have found this study interesting, they have recommended revision to improve the clarity of the manuscript. Please provide codes and other details of the model as recommended by Reviewer 1. 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. Please see the following video for instructions on linking an ORCID iD to your Editorial Manager account: https://www.youtube.com/watch?v=_xcclfuvtxQ. 4. We note you have included a table to which you do not refer in the text of your manuscript. Please ensure that you refer to Table 1 in your text; if accepted, production will need this reference to link the reader to the Table. [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: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: I Don't Know Reviewer #2: I Don't Know ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy 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: No 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: 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: Summary: The article provides an interesting analysis of patient characteristics hospitalized due to COVID-19 at the Centre Hospitalier Intercommunal de Cr´eteil using logistic regression and boosted decision trees. I have comments that should be addressed for publication. I would ask the authors to provide more information on the boosted decision trees. Specifically, the number of nodes and leaves should be reported (preferably visualized), the model’s prediction outcomes for each wave should be reported in a confusion matrix, and accuracy vs loss plots for the K-fold cross validation provided. Major Issues: 1. Multiple authors work for/founded a private company, Kaduceo (https://kaduceo.com/, https://www.linkedin.com/company/kaduceo/), focused on explainable artificial intelligence for healthcare applications. Given the emphasis on the value of services provided by this company, why is this not disclosed in the Conflict of Interest section? Were any of the authors paid to perform this work? 2. The code should be provided in the supplement. Given the restrictions on the data this is necessary to verify the methodology. 3. Please provide a confusion matrix, or similar graphic, in the supplement for the prediction outcomes of the model for each wave. Accuracy vs Loss plots should be provided for the k-fold cross validation for each wave. 4. The report of cardiovascular conditions providing a protective influence on severe COVID cases appears to be in conflict with a recent report by Banerjee et al 2021 (https://doi.org/10.1093/eurjpc/zwaa155). Can the authors provide additional rationale to distinguish the findings between these studies? 5. Line 216 needs to be rephrased. “Bluer” and “redder” are visualization aids, not data descriptors. The authors obviously understand this given figure 3’s caption, but this should be reflected in the main text. Similarly, lines 262 and 263 need to be rephrased to provide a proper description rather than “big redder points” and “other big points.” Minor Issues: 6. Image resolution must be improved for publication. 7. Figure colors should be adapted for colorblind readers (https://adasitecompliance.com/ada-color-contrast-checker/). 8. The descriptor that this is a large study should be changed (line 265). This study has value but the scope is relatively narrow compared to similar studies (https://doi.org/10.1016/j.scitotenv.2021.145650, https://doi.org/10.1016/j.scitotenv.2020.142810, https://doi.org/10.1016/j.chaos.2020.110058). 9. Please provide citations for lines 98, 105, and 122. 10. Please review for grammar and typos (lines 13, 20, 24, 58, 74, 78, 188, 193, 199, 234, 240, 277, 279, 300, 315, 327). Reviewer #2: Ref: PONE-D-21-30788 In the present article entitled "Evolution of hospitalized patient characteristics through the first three COVID-19 waves in Paris area using machine learning analysis," Jung et al. have used machine-based learning to analyze the trends in risk factors associated with COVID-19 through peaks in the pandemic in Paris. The study design is well conceived and the results are well supported by the data. Especially liked the fact that the authors have noted the limitations of the study in the manuscript. However, some points need to be addressed to make the study robust for publication. Major: Abstract mentions.. 'Data was prospectively collected from a University Hospital in Paris area, over..' it appears that the data was collected retrospectively from a prospectively maintained database.. Methodology: The authors should clarify the Inclusion criteria section to avoid confusion… for example: The inclusion criteria of the study appear to be as per the accepted WHO' Case definition': [WHO reference number: WHO/2019-nCoV/Surveillance_Case_Definition/2020.2] It would help to know what exact criterion of either WHO or national French guidelines were followed at the hospital for admission. Especially with regards to the confirmation of clinically symptomatic cases: eg. Nucleic Acid Amplification Test (NAAT)/ positive OR SARS-CoV-2 Antigen-RDT AND meeting either the probable case definition Kindly define the 'Primary patient catchment area for the University hospital'. Since it looks like a referral hospital, a good number of patients might have been referred at the peak of pandemic from smaller centres with Severe disease form directly to ICU, leading to a bias in the cohort analyzed in the present study. Please justify if any measures were taken into consideration during the analysis. Minor: Please translate French to English while describing the references for the readers easily. References: 3,20,21 Line 11: 'Based on this surveillance system...' since the antecedent has multiple systems mentioned can change to '....these surveillance systems...' line 285: genetic factors in the singular might sound more appropriate. Also, it would help to mention the 'biological factors' with examples affecting the pneumonia progression. Overall, a good and relevant study. Best regards, ****** 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.] 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.0263266.r001
Revision 1
16 Dec 2021 Author Response Dear Reviewers and Editors, First of all, we greatly thank editors and reviewers for their careful reading, valuable advice and positive evaluations of our work. Here are our responses for each review. Journal requirements We based our manuscript on a PLOS One template for LaTex, including the plos2015.bst style sheet for BibTex. Still, we would gladly make any changes if needed. Code for model construction and validation was shared on a public GitHub repository so that anybody can check soundness and viability of the implementation. ORCID of the corresponding author was entered on the PLOS One editorial manager. Reference to Table 1 was added. Reviewer 1 Conflict of Interest section was modified so as to specify that indeed three of the authors are employees of Kaduceo, but the study did not receive any specific grant. As said above, code was shared on a public GitHub repository. Accuracy and AUC ROC Score were added for the Machine Learning model for each wave in a new table (Table 4), and also discussed in the Discussion section. Reported performances were rather low due to the low number of features used (age, gender and comorbidities). Nevertheless, the solid model construction and validation allowed to take into account the full discriminative power potential of the features to perform a robust and useful analysis of feature effects. Indeed our findings about the cardiovascular problem being a protective factor for the first wave is in contradiction with other studies. As written in the Discussion section, this could come from the fact the hospital in this study (CHI Créteil) does not have a large cardiology department, suggesting that some patients with heavy cardiovascular problems were redirected to other hospital centers because of the stressful context of the first wave. We provided a correct description of values (such as young or old age) along with the color indicator (blue or red). Original images (tiff format) respected the PLOS One Figure File Requirements. We guess it is the automatic PDF generator that blurred images, but we could provide image with a better resolution if still needed. Indeed this study was not large compared to some other studies, but covered a longer period of over one year. In consequence, we remove the word ‘large’ at the beginning of the Discussion section. We checked that the colormap used is colorblind friendly, for example using site such as ColorBrewer (https://colorbrewer2.org/#type=diverging&scheme=RdYlBu&n=10). References were added concerning ensemble tree models and their performances.� Typos were corrected. Reviewer 2 Indeed, data was rather collected retrospectively from a prospectively maintained database. Abstract was modified in consequence. We clarified inclusion criteria in the Study population and design subsection in the Patients and Methods section. It consisted of every patient with a positive NAAT test or a chest tomography scan showing findings suggestive of COVID-19 disease. Despite the hospital of this study (CHI Créteil) being a large hospital center, it was not considered as a referral hospital of its area, notably because of the proximity of another larger center (CHU Henri-Mondor). Moreover, the CHI Créteil had a small Intensive Care Unit to be considered a referral hospital. French title of certain references were translated into English. We indeed changed ‘surveillance system’ into plural form. ‘Genetics factors’ was changed into ‘genetic factors’. In the Discussion section, we added some biological factors considered by the literature to have a significant impact on COVID-19 condition and aggravation, such as C-Reactive Protein (CRP) and Eosinophils. We also put appropriate references to support this claim. Best Regards, The authors Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0263266.r002
17 Jan 2022 Decision Letter - Kanhaiya Singh, Editor Evolution of hospitalized patient characteristics through the first three COVID-19 waves in Paris area using machine learning analysis PONE-D-21-30788R1 Dear Dr. Excoffier, 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 for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, 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, Kanhaiya Singh, Ph.D 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: All comments have been addressed 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: I Don't Know Reviewer #2: 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 #1: No 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: (No Response) 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: Yes:** Tejas Nikumbh https://doi.org/10.1371/journal.pone.0263266.r003
Formally Accepted
10 Feb 2022 Acceptance Letter - Kanhaiya Singh, Editor PONE-D-21-30788R1 Evolution of hospitalized patient characteristics through the first three COVID-19 waves in Paris area using machine learning analysis Dear Dr. Excoffier: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. 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 plosone@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. Kanhaiya Singh Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0263266.r004

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 .