PONE-D-24-15603Automatic time in bed detection from hip-worn accelerometers for large epidemiological studies: The Tromsø StudyPLOS ONE

Dear Dr. Weitz,

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 Aug 10 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,

Vitor Barreto Paravidino

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. We note that you have indicated that there are restrictions to data sharing for this study. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For more information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. 

Before we proceed with your manuscript, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see

https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible.

We will update your Data Availability statement on your behalf to reflect the information you provide.

3. In the online submission form, you indicated that [The data of the Tromsø Study cannot be shared publicly because of the risk of potential reidentification, but can be obtained upon application to the Data and Publication Committee for the Tromsø Study: https://uit.no/research/tromsostudy. The ActiGraph/Oura/Polar validation dataset can be obtained from A.He. (andre.henriksen@uit.no) upon reasonable request.]. 

All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. Uploaded as supplementary information.

This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval. 

[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: Partly

**********

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

Reviewer #1: No

Reviewer #2: No

**********

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

**********

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: This paper presents an algorithm aiming at discriminating time in bed and time out of bed based on hip-worn accelerometry data. While hip-worn accelerometry data focused on physical activity, such an algorithm would enable to reuse this data to get other outputs related to sleep. This algorithm is based on an augmentation data process and machine learning models of type Long-Short Term Memory networks (LSTM). This study has potential because the procedure used well-known algorithms applied in similar contexts and some techniques to add noise or take into account potential misuse of devices (flipped sequence, Gaussian noise), but there are weaknesses that need to be revised before publication.

Plos one questions

1. Is the manuscript technically sound, and do the data support the conclusions?

Partly. Please consider for instance my comments / questions regarding data augmentation, the different methods you used to label the data.

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

No. I wanted to answer “partly” but I cannot… Please consider my comments / questions regarding the use of additional indicators for the results section. In my point of view, providing accuracy is good but not enough.

3. Have the authors made all data underlying the findings in their manuscript fully available?

No. Data is not available but could be accessed on “reasonable request”.

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

Yes. I am not an English speaker but I think it is clear. Some typos are highlighted at the end of my comments.

General comments

As you mentioned in the paper, wearing hip-worn accelerometers during 24h can be a burden for participants, especially during sleep hours (“wrist-placement has been considered less obtrusive and thus leads to fewer non-wear days”; “To decrease study participant burden, many early study protocols comprised the removal of the device during sleep”). This fact might explain the lack of data appropriate for this kind of study. I think you should discuss the potential of using hip-worn accelerometers in behavior monitoring, maybe in future studies. In addition, it is probably a limit to the study, not so much a scientific limit as a functional one. It should be mentioned.

In your process, you use many types of data but it is unclear from the description how this data is used in the procedure. For instance in the procedure, it is not clear which dataset was used to train the models. Is it the “Tromsø Study TiB dataset”, “the Tromsø Study accelerometer dataset” or a mix of both? Please clarify the function of each dataset you used.

I am a bit skeptical about the use of ActiGraph/Oura/Polar dataset. Only 15 (16 – 1) participants provide “relevant information”. Moreover, it seems there is a confusion between sleep duration and time in bed (please consider my comments / questions related to the procedure section).

You mentioned that “data augmentation” improved the model generalization. How this technique improved the model. There is no comparisons with and without data augmentation. I don’t understand how you can make such a claim. Additional information is needed, please consider my comments / questions related to the discussion section.

Specific comments for corrections / clarifications

Abstract

The method description should be improved in the abstract. For instance, you wrote “We introduced new and accelerometer specific data augmentation methods”: could you briefly describe these new methods?

“the trained model significantly over- or underestimated time in bed.”: could you add numeric indicators showing this over or underestimation?

Materials and methods

“To ensure data quality, only participants with an intersection over the union (IoU) score of over .9 between the two annotations were included in this study.” (l 91): Please clarify this sentence. For instance, what are “the annotations”? Are they the annotators’ labeling? How was computed the score?

“Each participant was maximally included once in this subset.” (l 101): What was the criterion for choosing one of the 5 days (7 – 2 days) for each participant?

Procedure

It seems that you use two different methods to label time in bed minutes. On one hand, you use Actiwave Cardio data from the “Tromsø Study TiB dataset” to label the TiB minutes from the ActiGraph sensor data. On the other hand, you use ActiGraph data from the “Tromsø Study accelerometer dataset” to label the TiB minutes from the ActiGraph sensor data.

• Why don’t you use the same method to label the ActiGraph sensor data? It should be explained. It is important to show that no bias could result from the use of two different methods, or at least that this provide a gain in your study.

• What is the discrepancy between the two methods? This could be an important information to add in supplementary materials if you explain and highlight the importance in using these two different methods.

“Also with 50% likelihood, the sequence got reversed.” (l 126): Why did you reverse the sequence? What do you expect to simulate with this?

“As for the ActiGraph/Oura/Polar validation dataset only total sleep duration data was available, we calculated the total TiB from the predictions of our model on all fully recorded days.” (l 137): If I well understand, this means that you compared the sleep duration from ActiGraph/Oura/Polar with the time in bed from your model predictions, but these features (i.e. sleep duration and time in bed) are generally different. I think this is an important bias when using the ActiGraph/Oura/Polar validation dataset. This may explain the highlighted discrepancy in your results. Have you considered deriving total sleep time to time in bed or the reverse before proceeding the comparison?

Adding a flow figure showing the procedure and how the different datasets were used would be helpful for the reader.

Results

You provided the accuracy in your results, but what about the sensitivity and specificity?

Similarly, you provided the accuracy related to the “Tromsø Study TiB dataset” and the “Tromsø Study accelerometer dataset”, and what about the TiB labeled, TiB detected, etc.? Additional indicators (average of minima, maxima or means, etc. for instance; you could consider root mean square errors as well…) used to compare the output and the expected results would be relevant.

Discussion

Please, consider these two sentences “It remains also an open question to which extent our results generalize to the detection of sleep, which we could not test within the scope of this study as no appropriate data from hip-worn accelerometers is currently available.” (l 181) and “A crucial strength of this paper is to provide an opportunity to estimate TiB from already collected data. With this, we anticipate the chance for longitudinal analyses of sleep and TiB-related research question in settings where these questions only recently got into focus, but prior data exists.” (l 219) I am a bit confused. There seems to be a contradiction between these two statements about the availability of data on which to apply your method. Could you clarify what you mean?

“Another important contribution of this study is the introduction of accelerometer-specific data augmentation as a tool to improve model generalization.” (l 230): I am not sure that the reader well understands the point of using this technique in the procedure. As this is not the purpose of the article, could you please add a table in supplementary materials showing the quantified gain in accuracy between model basically trained and a model trained with data augmentation?

Figure S1

It would be helpful in Figure S1 to show which participant met the requirements fixed in your study, and for those retained, to describe (for instance, with another color and a thick, continuous line) which parts were considered as time in bed according to your criteria.

Figure S4

What are the characteristics of the machines: desktop and laptop (processor, RAM, 64 or 32 bits)?

Typos

Introduction (l 21): descriptopn -> description

Results (l 148, 152): hyperparamter -> hyperparameter

Discussion (l 207): over -> offer?

Discussion (l 246): a algorithm -> an algorithm

Best of luck for your paper submission.

Reviewer #2: The present study examined an important topic in the literature - the use of accelerometer to evaluate sleep. The development of an algorithm using the information of hip-worn accelerometer data would allow the exploration of a high amount of data that previously used accelerometer in the hip. Despite an important topic, the study has some important caveats that should be addressed. See my following comments that should be addressed:

ABSTRACT

The authors should better provide the rationale of the study - what is the potential advantage of measuring time in bed using hip-worn accelerometer? The objective of the study is not clear. The authors should provide more detailed results in the abstract.

METHODS - Datasets

The authors should provide a more clear and detailed description of the datasets used in the study. Why the authors choose these three different datasets?

In the Tromso Study TiB dataset, where the accelerometers were placed?

Line 79 - Why did the participants in the Tromso Study TiB dataset wear the accelerometers only during 24-hours?

Is the ActiGraph monitor cited in the Tromso Study accelerometer dataset the same than the used in the Tromso Study TiB dataset? This is not clear in the manuscript.

The idea of evaluating the accuracy of information comparing with consumer-wearable data is good. However, the very limited information of this validation dataset (n=16) is a reason of concern.

Procedure: It is not clear how the performance of the model was assessed.

A more detailed description of the Van Hees et al. method is required in the manuscript.

RESULTS

Description is poor, without presenting most of statistical estimates.

**********

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.

Automatic time in bed detection from hip-worn accelerometers for large epidemiological studies: The Tromsø Study

PONE-D-24-15603R1

Dear Dr. Weitz,

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,

Julio Alejandro Henriques Castro da Costa

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

**********

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

**********

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

Reviewer #1: 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

**********

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

**********

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: Is the manuscript technically sound, and do the data support the conclusions?

Yes.

Has the statistical analysis been performed appropriately and rigorously?

Yes.

Have the authors made all data underlying the findings in their manuscript fully available?

No. However, the authors explained why in the dedicated section.

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

Yes. I am not an English speaker but I think it is clear.

Review Comments to the Author

General Comments

The current manuscript is much clearer than the first one. The authors adequately addressed the comments I previously raised.

I only have a last suggestion regarding lines 181, 182, 186: Please write specificity and sensitivity in percentages (like accuracy for homogeneity).

All the best in the process.

**********

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

**********