All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
The manuscript has high standards to be published in PeerJ, after reading the new version, the response to the reviewers and reviewer #1's report.
[# PeerJ Staff Note - this decision was reviewed and approved by Paula Soares, a PeerJ Section Editor covering this Section #]
The corrections made are appropriate.
The description of the classification method used (neural network) has been improved.
With the approval of experts (authors of this article), research findings can be made available to researchers.
Thanks for the corrections. Valuable findings have been collected that can be used in other research by improving classifications and new features.
I saw scientific merit in your work, although there are some issues which you should address in a revised version of the text.
[# PeerJ Staff Note: Please ensure that all review comments are addressed in a rebuttal letter and any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate. It is a common mistake to address reviewer questions in the rebuttal letter but not in the revised manuscript. If a reviewer raised a question then your readers will probably have the same question so you should ensure that the manuscript can stand alone without the rebuttal letter. Directions on how to prepare a rebuttal letter can be found at: https://peerj.com/benefits/academic-rebuttal-letters/ #]
-The structure of the article is completely inappropriate. The introduction should be written more appropriately.
-Related works is not provided in the introduction and be reviewed
-Descriptions of tables, pictures and diagrams should be given in the text, not in the caption.
-The quality of images and diagrams should be appropriate (at least 200 dpi).
-References should be written in journal format.
-The subject of the article is in the journal scope.
-Research has collected and used appropriate data and features.
-Research in the hospital and laboratory has been done well.
-The need for research in the field of the article is not well explained.
-Research on classification and the use of deep learning networks is very poor.
-Laboratory methods are well described.
-Describing and using deep learning is not appropriate at all.
-No explanation is given about the network used and how the network is configured.
-The innovation of the research is only in the use of new diagnostic features that have been well collected.
-Research in the use of deep learning lacks any innovation.
-Due to the lack of description of the deep learning network used, the presented results have no validity in the field of classification and should be reviewed in this regard.
-The results of the deep learning network are not robust.
-The results of laboratory findings are appropriate.
The data collected is very valuable and the research done in the laboratory is appropriate. On the other hand, the results presented in the deep learning classification are invalid due to the lack of explanation of the network configuration. It is necessary to apply the general corrections mentioned below in the article:
-The structure of the article is completely inappropriate. The introduction should be written more appropriately.
-Related works is not provided in the introduction and be reviewed.
-Avoid generalizations and the materials used should be explained realistically and in detail.
-Descriptions of tables, pictures and diagrams should be given in the text, not in the caption.
-The quality of images and diagrams should be appropriate (at least 200 dpi).
-References should be written in journal format.
-Robust deep learning network should be used.
-The deep learning network used should be described in detail and complete metrics provided.
The structure of the manuscript is messed up and the tables and figures are not well-designed and it is hard for the reader to understand them.
The implemented deep model is extremely week and basic and so the achieved results are not reliable.
Not enough metrics for validation have been mentioned. In a valid evaluation, we expect the authors to mention Accuracy; Specificity; Sensitivity, and F1 score.
This manuscript is constructed of few fully connected layers and does not include a novelty that worth publishing in this journal.
The shared code shows the simplicity of their work. The model architecture clears this fact that the used model is the basic model of deep neural networks and has no innovation. The authors also did not mention enough metrics for evaluating their model like Accuracy; sensitivity or specificity.
For sure implementing a new deep neural network that is more advanced; will result in much higher accuracy than what the authors achieved.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.