Identifying Correlated Functional Brain Network Patterns Associated with Touch Discrimination in Survivors of Stroke Using Automated Machine Learning

Round 1

Reviewer 1 Report

The reviewers raised the following questions, and the authors are invited to carefully consider.

Comments for author File: Comments.pdf

The reviewers raised the following questions, and the authors are invited to carefully consider.

Author Response

Please find response to the editor and reviewers in the document attached. Responses for each reviewer are clearly indicated in the document and are organised relative to the main sections of the review and manuscript. We also provide a tracked version of the manuscript as well as a clean version.

Author Response File: Author Response.pdf

Reviewer 2 Report

Although the authors make a careful effort to explain the process they have taken in integrating machine learning tools. For a more transparent understanding of the underlying process, it is advisable to attach a flow chart that allows to understand the scaling of each of the resources used. The quality of the post-analysis graphs obtained is also a bit disappointing, with the tools used, a better presentation of the results could be made in order to understand the correlation between the manual valuation technique used and the predictive processes sought with the algorithm.

It is also important to specify the population included, how the test was developed, the times were comparable, the duration of the test is assimilable among participants, how the scores were obtained?

Apart from these precisions, it is very important to finally establish the specificity of the findings according to the model and the possible predictive candidates. 

Author Response

Please find response to the editor and reviewers in the document attached. Responses for each reviewer are clearly indicated in the document and are organised relative to the main sections of the review and manuscript. We also provide a tracked version of the manuscript as well as a clean version.

Author Response File: Author Response.pdf

Reviewer 3 Report

Authors in the proposed study interrogated and compared a suite of automated machine-learning approaches to identify patterns of brain activity associated with clinical outcomes. The study is well done overall, but I have minor concerns regarding the description of certain paper segments.

Abstract:

[1] Ln 11-14: It is necessary to show concrete evidence based on which you conclude that there is potential for automated machine learning to provide new insights into brain network patterns

[2] It is necessary to explain how you determined the importance of features (Figure 2)

[3] It is necessary to clarify how you calculated AUC and RMSE, in this context what represents true positive (TP), etc.

[4] Due to the clarity of the text, I strongly recommend avoiding abbreviations such as 23_LightGBM_GoldenFeatures_SelectedFeatures, hill_climbing_1, hill_climbing_2, etc., and use some useful notations.

[5] Labels in the axis of Figure 1 and Figure 2 should use sampler notations.

Author Response

Please find response to the editor and reviewers in the document attached. Responses for each reviewer are clearly indicated in the document and are organised relative to the main sections of the review and manuscript. We also provide a tracked version of the manuscript as well as a clean version.

Author Response File: Author Response.pdf

Reviewer 4 Report

The manuscript uses machine learning to identify brain activity patterns linked to stroke recovery. It aims to understand how functional connectivity networks predict touch discrimination outcomes in stroke survivors. Four golden features patterns were identified, involving resting state connectivity between various brain regions. These findings demonstrate the potential of automated machine learning to provide new insights into brain network patterns in stroke recovery.

The paper is interesting. However, some issues need to be dealt with, as follows:
    

1.    In the introduction section, please explain the importance and innovation of the proposed solution. In addition, please clearly state the main contribution of the manuscript.

2.    The literature review appears to be somewhat limited. Adding a separate section for literature review and expanding the review to include recent advancements in this field would strengthen the manuscript's relevance and contextual grounding.

3.    English is non-standard in some parts of the manuscript; I strongly recommend having the paper proof checked by a native English speaker before resubmitting.

4.    The paper design needs to be reconstructed.

5.    compare your proposed work with other recent papers in a suitable table.

6.    In the introduction section should mention the structure of the manuscript

7.    It is recommended that the authors add a separate section for the conclusion and expand this section to include a detailed discussion of the limitations of this work.

 English is non-standard in some parts of the manuscript; I strongly recommend having the paper proofchecked by a native English speaker before resubmitting.

Author Response

Please find response to the editor and reviewers in the document attached. Responses for each reviewer are clearly indicated in the document and are organised relative to the main sections of the review and manuscript. We also provide a tracked version of the manuscript as well as a clean version.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The author has made extensive revisions to the manuscript, and the current manuscript presents the basic requirements for SCI research. Further efforts are needed to enhance the innovation of the research, and there are still some doubts about the analysis of the conclusions that have emerged. The expression is not particularly clear, and the manuscript still has certain shortcomings in terms of research value.

The quality of English has improved, and it is necessary to carefully check the accuracy of some of the words used.

Author Response

Thank you for your further review of our manuscript. Attached is a detailed response to your comments.

Author Response File: Author Response.pdf