PONE-D-23-38981Exploring Unsupervised Feature Extraction of IMU-Based Gait Data in Stroke Rehabilitation using a Variational AutoEncoderPLOS ONE

Dear Dr. Felius,

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 Apr 18 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,

Jongsang Son, Ph.D.

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 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. Thank you for stating the following financial disclosure:

"This study is independent research and was funded by: SIA-RAAK (RAAK.PRO.03.006). SMB was funded by a VIDI grant (016.Vidi.178.014) from the Dutch Organization for Scientific Research (NWO)."          

Please state what role the funders took in the study.  If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."

If this statement is not correct you must amend it as needed.

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

4. Your ethics statement should only appear in the Methods section of your manuscript. If your ethics statement is written in any section besides the Methods, please delete it from any other section.

5. 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.

[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: Yes

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: 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: COMMENTS TO THE AUTHORS

This study assessed the use of deep learning (VAE) applied to wearable data in the study of stroke patient gait.

Overall, I believe this work has value and I thank the authors for the opportunity to read their work. I have some comments, which I report below, and which I think the authors should consider.

SPECIFIC COMMENTS (line)

TITLE

The title would benefit from including the main finding of the study; for example, can the variational encoder represent movement features well enough?

ABSTRACT

(31-33) Is this the problem addressed? If so, it may help addressing my previous comment about the title. Also, what follows in lines 34-36 is not very clear to me, at least without reading the rest of the manuscript. It looks like you are attempting a classification task here (contrary to the unsupervised approach mentioned earlier and also in the title)? Or you are checking whether there is clustering that could be done and that can discriminate the healthy and pathological group? I suggest rephrasing and making it clearer. Similarly, it would be advisable to better specify what test-retest refers to (different sessions? split in dataset from same session?)

INTRO

(99) The introduction reads well and has a nice flow, leading the reader through the problem under analysis and the broader scope of the work carried out. However, when it comes to the statement of aim and objectives, I suggest more information is provided and more attention is paid to describing the items under investigation. For example, an overview of AE and perhaps most importantly of the distinguishing features of VAE (as opposed to AE) should be provided, as well as a brief discussion about why this architecture has been chosen over others.

Also, more detail would be beneficial re: (1) what type of reliability, (2) what reference for assessing reconstruction capability (is it on original timeseries?), and (3) the nature of the analysis of group (pathological/control) features and monitoring (see comment for Abstract).

METHODS

(110-111) Ditto. Is test-retest from 2 different sessions? How much time apart?

(125) Were 8gs enough to avoid clipping/saturation? Also, what was the rationale behind sensor location? Was it arbitrary, driven by specific reasons (practicality?) or informed by previous work, literature etc.? I appreciate the is no perfect choice and not much knowledge yet about best wearable locations… however it may be beneficial for the reader/other scientist attempting similar approached to know what the thought process was, leading to that selection.

(127) I guess it may not matter much anyway (given the scope of your work and the sample analysed), but I think it may be good to know how many samples of aided/unaided gaits from the same participant were collected (as % of the total). There may be an argument that the features of walking are different, but some characteristic features are carried over for the same individual.

(129) What assessment? Do you mean protocol? In any case, please include a summary here, as readers should not need to access another document to have they key information.

(139) Was 104 Hz imposed by the system used? Does it depend on the no. of units used?

(141-151) Please provide the key aspects of the step-detection algorithm, and its validation outcomes. What is the role of gait event detection in the separation of data? Were epochs 5.12 s long (and therefore included multiple steps/strides?) What is the scope of overlapping and why 50%? Why did not you scale to Z-scores directly? Overall a figure to give a visual description of the steps followed would be beneficial.

(163) Please describe the matrix more clearly. I guess the 6 layers are the 3D accelerations and 3D angular velocities? It is still unclear to me what data goes into the 512 columns, are those all datapoints from the same person? Figure 1 does not help in this sense, and probably should be revised to improve clarity about data input. Similarly, more information should be provided about the selection of the model architecture, and whether any hyperparameter optimisation has been carried out, for example to determine the best configuration of layers, number of nodes per layer, dropout, activation function and, perhaps more importantly, number of latent variables (why 12?). An argument (which I mentioned earlier) would be about the model used… one could ask why VAE? If any other test (other architectures or approaches) has been carried out, it would be good to mention it, so that the journey leading to what presented here is clear (which is informative per se).

(187) Do you mean when there was divergence in performance between training and validation?

(191) If I understand correctly, you are assuming that the differences in the healthy group reconstruction (i.e. real healthy – reconstructed healthy) generated from a model trained with the stroke data only are (or may be) the aspects distinguishing healthy from pathological gait? If so I think:

1) better info should be given since the start of the manuscript (see my previous comments, where I thought you were attempting a classification based on the latent features)

2) some discussion should be presented re: this assumption, as that difference may be the sum of the error from the reconstruction in general (i.e., how good the model is in representing a stroke patient gait) and of the difference between groups? Also, how variance within those two groups is taken into account?

If I have not understood well… then I apologise, but the description may need some change to improve clarity!

(195-200) I do not think this part of the processing is clear enough… and unfortunately Figure 2 does not help much… I suggest rephrasing to improve clarity and revising Figure 2.

RESULTS

(248-249) There is repeated info from methods here.

(251) Are these errors in standardised scores? It would be useful to have an idea of the reconstruction errors in the original units as well… to have a better idea of what they could mean from a biomechanical perspective

(279) The reference to gait speed comes out a bit unexpected, as it was not mentioned earlier in methods.

DISCUSSION

(318) Similarly to what observed for the Results section, it would be better to discuss what is meant for “high accuracy” and its interpretation from a biomechanical perspective (for example, are those differences meaningful when reconstructed as original quantities? What best and worst case scenario, beyond average across gait cycle and multiple people/strides?)

(322) “higher…than speed” between what conditions or groups?

(327-331) These arguments may need some further explanations/examples to make them more accessible to the wider readership

(340) Ok, but is your solution the best compromise? How can you demonstrate it? See previous question about model parameters/architecture and, more broadly the question of whether VAE are better than other dimensionality reduction techniques…

Reviewer #2: Overall, this is an interesting study that provides useful new information to researchers using the IMU technology in the field of stroke rehabilitation. I have a couple of major concerns related to the lack of explanation regarding a statistical analysis that the authors used and justification for 5-second epochs.

Major concerns

The authors did not provide any explanation regarding the statistical analysis that they used in the manuscript. A detailed explanation of their statistical analysis is necessary to be explained in the manuscript.

The data were segmented into 5-second epochs. Why was this segmentation necessary and why was 5-second? The justification for these aspects is necessary to be included in the manuscript.

Minor comments

Lines 99-101: The way you numbered seems confusing. Maybe another way looks better such as 1), 2), 3) or a), b), c).

Line 281: Explanation of abbreviations (L1-8) needs to be added to Table 2 legend.

Some figures missed explanations of abbreviations in their legend. Please double-check and add explanations if needed.

**********

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: Dr Ezio Preatoni

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.

Exploring Unsupervised Feature Extraction of IMU-Based Gait Data in Stroke Rehabilitation using a Variational AutoEncoder

PONE-D-23-38981R1

Dear Dr. Felius,

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,

Jongsang Son, 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: Yes

Reviewer #2: 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: Yes

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: Thank you for addressing all my comments.

Nice work, it was a very interesting reading, so I congratulate the team for the research carried out.

Reviewer #2: The authors have addressed all comments appropriately. I don't have further comments. The manuscript is ready to be published.

**********

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: Yes: Dr Ezio Preatoni

Reviewer #2: No

**********