Peer Review History

Original SubmissionOctober 15, 2019
Decision Letter - Giorgio F Gilestro, Editor

PONE-D-19-28848

Robust, automated sleep scoring by a compact neural network with distributional shift correction

PLOS ONE

Dear Mr. Barger,

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.

We would appreciate receiving your revised manuscript by Dec 21 2019 11:59PM. When you are 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.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter.

To enhance the reproducibility of your results, we recommend that if applicable you deposit your laboratory protocols in protocols.io, where a protocol can be assigned its own identifier (DOI) such that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

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). This letter should be uploaded as separate file and labeled 'Response to Reviewers'.
  • A marked-up copy of your manuscript that highlights changes made to the original version. This file should be uploaded as separate file and labeled 'Revised Manuscript with Track Changes'.
  • An unmarked version of your revised paper without tracked changes. This file should be uploaded as separate file and labeled 'Manuscript'.

Please note while forming your response, if your article is accepted, you may have the opportunity to make the peer review history publicly available. The record will include editor decision letters (with reviews) and your responses to reviewer comments. If eligible, we will contact you to opt in or out.

We look forward to receiving your revised manuscript.

Kind regards,

Giorgio F Gilestro, PhD

Academic Editor

PLOS ONE

Journal Requirements:

1. When submitting your revision, we need you to address these additional requirements.

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

http://www.journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and http://www.journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

[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

**********

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

Reviewer #1: 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

**********

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

**********

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: The manuscript by Barger and colleagues introduces a novel standardisation procedure to improve the performance of automated methods for sleep scoring, with a focus on rodent studies.

The manuscript is technically sound and has the potential to benefit the wider sleep community.

I only have some minor comments for the authors to address:

1) In order to use the propose method, manual labelling (scoring) of a few minutes of data (per subject) is needed. One potential issue is that the labeled data might not have the same class balance as the rest of the dataset. For instance, a user might label a portion of the data during which a subject is primarily awake, but thus may not represent the rest of the dataset. The authors should discuss to what extent this may be a problem, possibly quantify the impact of a mismatch between class distribution in labeled vs. unlabelled data, and introduce software-based measures to address this issue.

2) In Figure 1, it is not clear what feature of EMG activity are quantified and displayed in panel C.

3) From line 270 to line 315 the authors refer (in several instances) to Fig. 3C-D, while the correct reference is to Fig. 4C-D

4) I find Fig. 5 not clear enough. In particular, the legend should better help the reader in understanding how the bottom and top panels temporally relate to each other.

5) Does the software force to use 2.5 s epochs, or can an arbitrary epoch length be chosen?

**********

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

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files to be viewed.]

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 us at figures@plos.org. Please note that Supporting Information files do not need this step.

Revision 1

We thank the reviewer for their thoughtful comments, which were quite positive. In general, we took the comments to be requests for clarification. We have modified our manuscript based on the reviewer’s comments, and our responses to the comments are below. Page and line numbers refer to the updated version of the manuscript without tracked changes.

1) In order to use the proposed method, manual labelling (scoring) of a few minutes of data (per subject) is needed. One potential issue is that the labeled data might not have the same class balance as the rest of the dataset. For instance, a user might label a portion of the data during which a subject is primarily awake, but thus may not represent the rest of the dataset. The authors should discuss to what extent this may be a problem, possibly quantify the impact of a mismatch between class distribution in labeled vs. unlabelled data, and introduce software-based measures to address this issue.

We take the reviewer’s comment to stem from concern that if the labeled sample of data used in the mixture z-scoring process does not have the same balance of classes as does the full dataset, then the estimated standardization parameters (means and variances) will be biased away from the correct values.

The labeled sample of the data is used to estimate the means and variances of observations from each class individually. In other words, K separate samples (one per class) are being collected to estimate K sets of parameters. Therefore, it is not necessary for the class balance of the overall sample to resemble that of the full dataset--it is only necessary that its K constituent samples are large enough to provide good estimates of the parameters for each class.

We have updated the text to clarify this aspect of the algorithm: the paragraph beginning on line 276, page 8 now reads “Finally, we investigated the relationship between classification accuracy and the amount of labeled data used for mixture z-scoring. As described in the Methods section, mixture z-scoring requires labeled data from each subject in order to estimate a mean and variance for each data feature within each class. Though the class balance of the labeled sample has no direct effect on the estimation of these parameters, it is important to determine how many labeled epochs are required to required to attain accurate enough parameter estimates to support classification.”

In the AccuSleep software, we do enforce a requirement that at least three epochs of each class are present in the labeled sample. Our user manual encourages users to provide larger labeled samples when possible, which should increase the accuracy of the parameter estimation.

2) In Figure 1, it is not clear what feature of EMG activity are quantified and displayed in panel C.

We follow the convention that EMG activity is defined as the root-mean-square of the EMG signal. We have updated the caption for Figure 1 (p 2) to reflect this information: it now reads, “...C: example EEG spectrograms and root-mean-square EMG activity for each sleep stage.”

3) From line 270 to line 315 the authors refer (in several instances) to Fig. 3C-D, while the correct reference is to Fig. 4C-D

We have corrected the references to Figure 4 in the text on lines 273, 287 and 321.

4) I find Fig. 5 not clear enough. In particular, the legend should better help the reader in understanding how the bottom and top panels temporally relate to each other.

We have clarified the caption for Figure 5 to better explain the relationship between the two sets of panels in the software. It now begins: “The lower three panels display the EEG and EMG signals as well as the sleep stage labels for epochs surrounding the currently selected epoch. The upper three panels provide context by displaying the sleep stages, EEG spectrogram, and EMG power on a longer time scale. The red line below the first panel indicates the time span of the lower three panels, and the diamond indicates the location of the currently selected epoch.”

5) Does the software force to use 2.5 s epochs, or can an arbitrary epoch length be chosen?

Arbitrary epoch lengths can be chosen. However, the network used for classification should be trained on data with the same epoch length as the desired output. We provide networks trained on data scored at 2.5, 4, 5 and 10 second resolution with the software. For other epoch lengths, it is possible to use the software to train a new network. We have updated the text to reflect this information: the description of the sleep scoring workflow now includes the sentence (line 308, p 9), “Arbitrary epoch lengths can be used, provided that the neural network used for automatic scoring was trained on data scored at the same temporal resolution.”

Additionally, we made the following minor changes to the text to improve clarity:

1. In the Methods section, we now indicate the genotype (C57BL/6) of the mice used in our experiments (line 427, p 11).

2. In the caption for Figure 3 (p 7), we corrected the order of the panel descriptions.

3. In the description of our neural network, SS-ANN, we changed the wording on line 212, p 6 to better reflect the fact that spectrograms of the EMG signal are not used as inputs to the network, only the log-transformed root-mean-square measurement.

4. The line styles used in Figure 2 have been switched between subject I and subject II to improve the clarity of panels D and H. The caption (p 4) has been updated to reflect this change.

5. Since submitting the manuscript, we have made several improvements to the appearance and functionality of the software we describe. Figure 6, its caption (p 9), and the description of the sleep scoring workflow on line 301, p 8 have been updated to reflect these changes.

Attachments
Attachment
Submitted filename: Response to Reviewers.pdf
Decision Letter - Giorgio F Gilestro, Editor

Robust, automated sleep scoring by a compact neural network with distributional shift correction

PONE-D-19-28848R1

Dear Dr. Barger,

We are pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it complies with all outstanding technical requirements.

Within one week, you will receive an e-mail containing information on the amendments required prior to publication. When all required modifications have been addressed, you will receive a formal acceptance letter and your manuscript will proceed to our production department and be scheduled for publication.

Shortly after the formal acceptance letter is sent, an invoice for payment will follow. To ensure an efficient production and billing process, please log into Editorial Manager at https://www.editorialmanager.com/pone/, click the "Update My Information" link at the top of the page, and update your user information. 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 enable them to help maximize its impact. If they will be preparing press materials for this manuscript, you must inform our press team as soon as possible and 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.

With kind regards,

Giorgio F Gilestro, PhD

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Formally Accepted
Acceptance Letter - Giorgio F Gilestro, Editor

PONE-D-19-28848R1

Robust, automated sleep scoring by a compact neural network with distributional shift correction

Dear Dr. Barger:

I am 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 notify them about your upcoming paper at this point, to enable them to help maximize its impact. If they will be preparing press materials for this manuscript, 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.

For any other questions or concerns, please email plosone@plos.org.

Thank you for submitting your work to PLOS ONE.

With kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Giorgio F Gilestro

Academic Editor

PLOS ONE

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 .