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 authors correctly handled the requests by the reviewers and therefore I can recommend this article for acceptance.
[# PeerJ Staff Note - this decision was reviewed and approved by Mehmet Cunkas, a PeerJ Section Editor covering this Section #]
The reviewers generally appreciated the articles and its recent changes, but there are still some issues left to fix. I invite the authors to address them.
The authors have addressed my concerns to the best of their abilities.
-
-
-
-
-
- Enhance the captions of the study, including those for figures and tables. For example, Figure 3.
- Avoid the use of em-dashes, as they are often indicators of AI-generated writing.
- Highlight the reasons why accuracy differs from balanced accuracy. Report sensitivity and specificity in Table 2.
- Report sensitivity and specificity in Table 5.
- Add concise captions and labels to Figure 1.
- Figure 3 must not be a figure. It should be presented as a textual algorithm or converted into a flowchart, as it is not readable in its current form.
- Figure 4 must not be a figure. It should be presented as a textual algorithm or converted into a flowchart, as it is not readable in its current form.
- Conduct a performance-based comparison between your study and related studies.
- Include a clear justification for the research to strengthen the rationale behind the study.
- Explicitly state what distinguishes the current study from related research to emphasize its uniqueness.
- Discuss the limitations of the current study to provide a balanced perspective on its scope and applicability.
- Incorporate recent citations from 2023 to 2025 to ensure the manuscript reflects the latest advancements and developments in the field.
- Include a table of abbreviations in the revised manuscript to improve reader comprehension, especially for those unfamiliar with all the terms used.
- Introduce two new subsections: (1) Privacy and Ethics, which discusses the ethical considerations and privacy safeguards relevant to your study, and (2) Medical Relevance, which highlights the clinical or practical implications of your work.
- The authors must conduct a new experiment using another dataset from the literature to validate their proposed framework.
-
-
**PeerJ Staff Note:** Please ensure that all review and editorial comments are addressed in a response letter and that any edits or clarifications mentioned in the letter are also inserted into the revised manuscript where appropriate.
**Language Note:** The review process has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff
Abstract
The authors should avoid using camel case for algorithm names, conditions, and techniques. While the abstract highlights the results well, it would be beneficial to clearly articulate the contributions and novel aspects of this specific work, particularly in terms of methodology.
Manuscript Structure
The structure of the manuscript is quite disorganized. Sections and subsections appear to be introduced arbitrarily. For example, the Introduction section begins at line 26, but a subsection is already numbered at line 27.
Moreover, Section 2 is missing entirely the manuscript jumps directly from Section 1 (Introduction) to Section 3 (Related Work). The authors should review the structure carefully and ensure consistency and completeness in section numbering and hierarchy.
Content Organization
The sections covering the problem statement, research questions, and contributions should be integrated into the Introduction as coherent paragraphs. Additionally, the discussion of the research gap and research questions would be more appropriately placed at the end of the Related Work section to provide context for the proposed approach.
Related Work
The Related Work section is severely underdeveloped. It is implausible that the entire body of related literature can be summarized in a single paragraph. This section should be significantly expanded to include 6-7 paragraphs summarizing recent and relevant studies, highlighting their contributions, limitations, and how this manuscript advances or differentiates from them.
There are two separate sections labeled as Methodology (lines 121 and 230). This redundancy should be resolved to improve clarity.
The role of feature selection in this study is unclear. Considering the small dataset with a limited number of features, it is questionable whether feature selection is necessary at all. The authors should clarify this aspect and explain its relevance within the context of the work.
The evaluation section is lacking in depth. Given that the dataset used is imbalanced, additional evaluation metrics, should be included to better reflect performance under these conditions. Statistical significance should also be established
A comparison with several state-of-the-art optimizers would also strengthen the manuscript by providing a baseline against which the performance of the proposed PSO-based optimization can be meaningfully assessed.
The findings appear to be within the realm of possibility; however, more thorough evaluations are necessary. In particular, the authors should establish statistical significance to support their claims and ensure the robustness of the results.
Overall Quality
The manuscript appears rushed and lacks thorough proofreading. While the contributions are potentially interesting, they do not sufficiently engage with recent literature. Several recent works have applied optimization algorithms for hyperparameter and architecture tuning in neural networks, and these should be acknowledged and discussed.
The work is worth publishing since there is a contribution, the research topic is of interest; however, the manuscript deserves a thorough revision since there are various parts that need improvement.
Check section numbers. The related work section appears as section number three; however, it should be section two.
The first paragraph in section 1 (Introduction) was assigned a section number as if it were a section title.
I consider that “i” in equation (1) should be subindex for the case of position “xi” and velocity vector “vi”. Since velocity, position and global best positions are vectors, all variables should be in boldface.
I consider that “1” and “2” in equation (1) should be subindex for the case of constants “c1” and “c2” and for random numbers “r1” and “r2”.
Section PSO provides with an algorithm listing, where “p_i” and “v_i” stand for position and velocity. For consistency, use the same notation as in equation 1.
Equation 5 uses variable “xid” for position. For consistency, use the same notation as that in equation 1.
What does “v” stand for in equation 4?
In general, the methodology section needs a thorough revision to reach consistency and clarity.
Revise conclusions. “AdaBoostClassifiers” must be written as a three-word term and “BaggingClassifier” must be written as a two-word term.
No comments
The results of the proposed method should be compared with those from other methods that used heuristic techniques to select the best feature subset and the model hyper-parameters. This can be done by introducing a Table in the Discussion section.
No comments
Improve the quality and detail of figures and their captions, especially Figure 1.
Convert the algorithms in Figures 3 and 4 into formatted text, not images.
The numbers in Figure 2 are unclear. For example, the first two rows are difficult to read. Either round the numbers or modify the font size.
Table 10 is a duplicate of Figure 6. Remove the table and include the values directly on the figure.
Report all metrics to four decimal places.
Table 9 appears to have an issue. The BAC and ROC/AUC values (3rd and 4th columns) are identical in every row, which is unlikely.
Table 11 contains incorrect calculations. You report TP=193, TN=215, FP=8, FN=4. Based on this, recall should be 97.97% and precision should be 96.02%. Rerun the experiment and update the results.
It appears you are calculating metrics per class and then averaging them. If this is true, it will misrepresent results in a binary classification task. In such cases, sensitivity and specificity will appear identical.
In Table 1, move the reference column to the first position and include author names in the format "XX et al. [XX]".
Remove all bullet points from the manuscript. Convert them to tables where applicable. If a table exists, delete the corresponding bullet points.
Refine the package references in Section 6. For example, group sklearn.metrics and sklearn.preprocessing under Scikit-Learn.
Describe all equations clearly and in detail.
Include a table of abbreviations to support reader understanding.
Include a table of symbols if mathematical notation is used.
Add citations to support uncited statements.
Review and correct all typographical errors.
Add recent citations from 2022 to 2025 to reflect current work in the field.
State the novelty of your proposed approach. Explain how it advances the state of the art.
Clearly define the research question and gap to clarify the study's objective.
Justify the research to support its purpose and relevance.
Provide more technical and methodological details to strengthen your proposed approach.
Clearly state how your study differs from related work to emphasize its contribution.
Refer to "Basic reporting" section.
Refer to "Basic reporting" section.
Refer to "Basic reporting" section.
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.