PONE-D-22-25188The Impact of Electronic Health Record Discontinuity on Prediction ModelingPLOS ONE

Dear Dr. Lin,

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

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

ACADEMIC EDITOR: Please revise and resubmit the manuscript. . 

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

Please submit your revised manuscript by Feb 10 2023 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,

Kathiravan Srinivasan

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

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. 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: Partly

Reviewer #4: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: 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: No

Reviewer #2: No

Reviewer #3: Yes

Reviewer #4: No

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: It is not clear from the manuscript if you used EHR data (from Medicare) that was coded or did you somehow extract it from free text. Also, please explain the data in some more detail, including the fields used for the ML algorithms.

Reviewer #2: This paper is well organized and clearly written. The methodology and analysis are comprehensive, and the final conclusion is clearly summarized. The following issues should be addressed:

1. In the methodology, the data processing needs to be clarified: i.e., how to deal with categorical data and numerical data? One-hot vectors or binned numbers? These should be described in the Method or written with Table 1 when presenting the data features.

2. Though AUC scores are given, some insights are missing. For example, what features are causing such AUC difference? The chosen ML models may provide different weights to the input features, it is possible to show such analysis in the Discussion.

3. It may be possible to add bar charts instead of tables for better results presenting.

Reviewer #3: This paper applied machine learning algorithms based on EHR data in order to prove that when predicting outcomes like mortality, CV/bleeding events etc., patients with low EHR continuity consistently had worse performance than those who have high EHR continuity. The statement is demonstrated with logical supportive details. There are some problems need to be addressed to offer more clear presentation to readers.

1) From table 2, it seems that either lower or higher 50% of the events only have around 2000 event cases, compared to the cohort like like 32K in training, 20K in validation, which means your dataset is extremely imbalanced. It is better to show in details how did you use SMOTE to adjust that imbalance. Also, in the evaluation part, ROC AUC have weakness in showing true performance of imbalanced classification task, it's strongly recommended to add precision recall AUC and show AUC difference between high/low EHR continuity.

2)It's not clearly described that how EHR features are formatted in the predictive models. For example, whether dummy variables are generated for categorial predictors? In the medical history, in addition to indicators of diagnosed diseases, whether there are other information can be extracted? Like time interval between diagnosis and events? Also, whether there are treatments or drug use details can be used as predictors?

3)2007 to 2017 is a very wide time range, what time periods are the training and validation cohort data are obtained specifically? Also, it is better to show the patient duration distribution in training/validation like minimal/median/maximum time that a patient can be tracked in the dataset.

4)More introduction can be added to explain the definition and extent of EHR-continuity.

Reviewer #4: The authors examine the impact of EHR continuity on the performances of machine learning algorithms to predict three widely investigated clinical outcomes. The authors used an existing model to classify if a patient experienced EHR discontinuity, and the training set was split into two parts, which have either high EHR continuity or low EHR continuity. Then ML models are trained separately using these two parts to report and compare results on an external validation set. The experimental setup of the study is commendable and the statistical analysis is sound, presenting sufficient details to support its conclusion on the impact of EHR continuity on ML models. I have two major comments.

1. EHR continuity was predicted using an off-the-shelf algorithm. I think a bit more detail on the evaluation of this algorithm would better inform the readers. The algorithm can also be viewed as a filter, and we see improved downstream performances after removing the “noisy” half of the training data using the algorithm. This makes me wonder if any other factors might result in the difference. For example, is it possible that 50% of data with low EHR continuity also suffers from a higher level of data missingness? These two are obviously correlated but not equivalent since there could be other causes of data missingness other than EHR discontinuity. Maybe more descriptive statistics on the two datasets with varied EHR continuity would be helpful.

2. The authors developed models using two datasets with varied EHR continuity and evaluated them on the unified validation set. It may be worth considering also splitting the validation set into two parts according to EHR continuity, similar to the development set. Maybe some supplementary results here would better cast light on the impact of EHR continuity and whether the impact is consistent throughout training and testing. Intuitively, both models developed regardless of EHR continuity should perform better on the validation set with higher continuity than on that with lower continuity. But if the model developed using low EHR-continuity data also performs better on data with low rather than high continuity, then maybe distributional shift plays a more significant factor in the different modeling results. In other words, are the development and validation sets equally “continuous”? Would that matter?

One minor comment on data sharing: the authors should specify more explicitly the restrictions preventing them from sharing the data.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: No

Reviewer #4: 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.

The Impact of Electronic Health Record Discontinuity on Prediction Modeling

PONE-D-22-25188R1

Dear Dr. Lin,

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,

Kathiravan Srinivasan

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 #3: All comments have been addressed

Reviewer #4: 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: (No Response)

Reviewer #3: Yes

Reviewer #4: Yes

**********

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

Reviewer #1: (No Response)

Reviewer #3: Yes

Reviewer #4: 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: (No Response)

Reviewer #3: No

Reviewer #4: No

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: (No Response)

Reviewer #3: Yes

Reviewer #4: 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 #3: The authors have address all my previous comments. And it reads clearly to me now. The table layout and fonts are not consistent, hopefully it can be well addressed before publishing.

Reviewer #4: Thank you for addressing the raised the comments and updated the manuscript accordingly, which has been substantially improved.

**********

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 #3: No

Reviewer #4: No

**********