Evaluation of Finger Movement Impairment Level Recognition Method Based on Fugl-Meyer Assessment Using Surface EMG

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper proposed a finger movement impairment level recognition method using sEMG signals and machine learning models. It can assist the doctor in making a proper judgment in an uncertain assessment condition. The manuscript is well-organized and of great interest to the audience. Therefore, it could be accepted after some minor revisions.

1.      The present study seems to compare only with the authors’ previous work. I suggest comparing it with some current related literature in the Discussion section.

2.      Generally, we use abbreviations when technical terms appear three or more times in the paper. We define an abbreviation when the technical term first appears. Then, we use the abbreviation in the following text. I noticed you defined abbreviations for FMA movements on line 64; however, they are repetitively defined on lines 118, 387 and 446.

3.      In Section 3, Proposed Method, I suggest providing the calculation formula for the recall score used as the evaluation metric.

 

4.      Overall, the paper needs proofreading. For example, on lines 263 and 397, periods are missing at the end of the sentence.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The current paper states that subjectivity appears to be an issue in the assessment of post-stroke finger movement impairment. To face that issue, the authors propose an objective methodology based on EMG. Compared to the state of the art, the innovative side of the method seems to be related to the number of channels and the sampling frequency of the EMG.

I believe the topic fits the scope of Applied Sciences Journal, and also specifically of the special issue on Human Biomechanics and EMG Signal Processing.

However the manuscript presents a continuation of a  previous study on movement impairment recognition, that may affect the strength of the innovative contribution of the presented work.
My overall opinion is that the authors revise the paper according to the notes of the reviewers, as in the current state it is not ready for publication. 

Here are my notes:

In the Introduction, the authors should clarify what is recognition research and why they use Fugl-Meyer assessment.

Applied Sciences is a multidisciplinary and interdisciplinary journal, so I believe the authors should make an effort in describing the background for a wider audience.

In that direction, a wider description of the issue, in terms of post-stroke effects and symptoms, may help to better understand the issue and therefore the proposed solution. 

In this regard, here are two references on the perception of movements and human reaction to that, that the authors should include.

Agata Marta Soccini. 2020. The Induced Finger Movements Effect. In SIGGRAPH Asia 2020 (SA '20). Association for Computing Machinery, New York, NY, USA, Article 3, 1–2. https://doi.org/10.1145/3415264.3425448

Sophie Jörg, Jessica Hodgins, and Carol O'Sullivan. 2010. The perception of finger motions. In Proceedings of the 7th Symposium on Applied Perception in Graphics and Visualization (APGV '10). Association for Computing Machinery, New York, NY, USA, 129–133. https://doi.org/10.1145/1836248.1836273

When describing the methodology, the authors should better underline what kind of benefit this approach provides towards the whole scientific discovery process, and in which extent they can state they recommend it.

Comments on the Quality of English Language

The paper is well written and easy to follow.
However, a proofread would be useful, and at some points, the acronyms seemed to be too frequent, especially for a multidisciplinary community.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The purpose of this research was to objectify using SEMG and machine learning algorithms the FMA for hand function. The introduction and extended background appeared to identify a problem and rationale for this research; a more explicit purpose statement for this research was not adequate. The methods section is very detailed but incoherent and somewhat redundant and needs to be significantly reorganized. The results section was well-organized. The discussion needs to better provide the reader with a clear explanation of the very detailed results section and contrast the value of the objectification of the FMA using EMG with the current clinical approach. There are numerous word choice and word tense errors, as well as English grammar errors. See detailed comments in the pdf.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Moderate revisions will be needed in consultation with an English grammar expert.

Author Response

Please see the attachment.

We entered the response to the reviewer's comments as the reply to the comment in the PDF file.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The authors responded to most of the notes provided.
However, it appears that they ignored the recommendations for missing citations, and did not include a related brief discussion, without explaining why.

After fixing this issue, I believe the paper will be ready for publication.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The revised manuscript demonstrates improvement but several word choice and word tense errors remain, and some areas of the methods and results require additional information. See comments in PDF.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

several remaining word choice and tense errors need to be corrected.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf