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 been improved and reviewers' comments have been addressed. The manuscript is ready for Accept.
The authors have addressed the reviewers' comments and improved the whole manuscript. I believe the manuscript is ready for acceptance.
Meanwhile, I do have minor comments which I would like the authors to consider in their final version as follows.
- Reduce the Keywords to 5 only, preferable.
- Update the statistics of COVID-19 cases according to the recent release.
- Double-check the language and grammatical errors. I still can see some places which need improvements.
[# PeerJ Staff Note: The Academic Editor has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at copyediting@peerj.com for pricing (be sure to provide your manuscript number and title) #]
- If possible, update the reference list to include the very recent works.
This survey represents a bibliometric analysis for the recent machine learning methods to combat the COVID-19 pandemic which became a great issue, globally. The manuscript is of immense significance to researchers in AI field. However, the manuscript received mixed reviews and I believe it needs a major revision before being recommended for acceptance. I invite you to carefully address the comments of Reviewers 2 and 3 in your rebuttal.
[# 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/ #]
[# PeerJ Staff Note: PeerJ journals do not consider bibliometric/scientometric analyses for peer-review in their own right. A bibliometric analysis will only be considered if it forms part of a literature review or a research article, where it serves to identify the knowledge gap that is addressed by the research. Please see https://peerj.com/about/policies-and-procedures/#discipline-standards for details.) #]
No comment
No comment
No comment
Machine learning is one important technique tool to fight the COVID-19 pandemic. As done in this manuscript, to give a early survey with bibliometric analysis is necessary and meaningful. It has not been done previously. The contents in this manuscript are rich. The representations are logical and structured. The listed challenges and future research opportunities are insightful.
There are several comments.
1. The title of Section 6. General Discussions is not appropriate. This part should be the main contents or results of this manuscript. I suggest use the title of "Survey and the bibliometric analysis".
2. Some references are missing.
[1] D. Dong, Z. Tang, S. Wang, et al., The role of imaging in the detection and management of COVID-19: a review. IEEE Reviews in Biomedical Engineering, 2020, DOI: 10.1109/RBME.2020.2990959.
[2] F. Shi, J. Wang, J. Shi, et al., Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19, IEEE Reviews in Biomedical Engineering, 2020, DOI: 10.1109/RBME.2020.2987975.
[3] Rahaman, Md Mamunur et al. ‘Identification of COVID-19 Samples from Chest X-Ray Images Using Deep Learning: A Comparison of Transfer Learning Approaches’. 1 Jan. 2020 : 1 – 19.
The paper presents a review for COVID19 detection and diagnosis techniques. The manuscript however lacks readability criterion. There are plenty of information that is not required which makes the reader inconclusive about the study. Therefore, it is suggested for authors to reconsider the approach in order to make it more readable and significant for the research community.
The whole manuscript requires a thorough proof reading. There are plenty of punctuation and grammar mistakes. For example sentence on line 83 to 88 is a one big sentence. It needs to be divided into small and simpler sentences. Moreover the “COVID-19” is repeated 9 times in the same sentence.
The structure of the survey presented in Figure 1 need to be more concise. For example what is the difference in data source in second column and the one mentioned in fifth column.
Figure 2. What is exclusion criteria for exclusion
What is significance of bibliographic coupling in fight against COVID 19.
What is difference between a literature survey and bibliometric analysis. How it gives a better prospective than a literature survey as mentioned in line 103.
In the methodology section, there is a lot of redundant information. The keywords are already mentioned in abstract why need to present as a separate section. Similarly, article selection and bibiliometric protocols are irrelevant as the review is about COVID-19 not on data mining techniques. The authors if they want should present a simple criteria like selecting only from indexed journals such as PubMed, Google Scholar, MEDLINE, Science Direct, Springer, and Web of Science databases and just mention the search terms.
Also the theoretical literature explaining the ANN ,CNN and LSTM is widely discussed so no need to add mathematical theory .One section about theoretical background that discusses the application of there machine learning algorithms will be sufficient.
In section 4.1 line 331 what are the classes 4,3, and 2 present?.
In section 6 the subsection 6.2 that discusses the trends of publication, bibliometric analysis, authors prolific analysis etc. seems irrelevant. Instead authors should focus on critical analysis of disease itself.
The COVID-19 detection challenges and how authors have dealt them from the presented literature should be discussed as a summary .From the whole presented literature a more precise summary of analysis should be included.
In summary although the authors have prepared a quiet lengthy review article, but there is a lot of information that is not required. As main objective of any survey is to provide readers an up to date literature and a clear comparative picture in terms of results as well as challenges faced and way forward to solve these problems. It is highly recommended to revisit the approach in this paper and follow a simple criteria to present most relevant and useful analysis.
In introduction, authors should clearly mention the motivation and address it during the paper. Why is the "bibliometric analysis" important? why authors consider this analysis in this paper.
CNN methods did not describe with details.
The conclusion is not satisfactory and cannot convince reader that which methodology is suitable for covid dataset. you should provide that more detailed CNN architecture for each dataset.
1- Authors should provide more details in Table 3 such as: CNN Architecture, number of patients, and database (e.g. type of preprocessing, name of institute).
2- There are several CNN method for analysing CT and X-ray scans. Authors must introduce the best architectures in this database or Covid19 case. They only mentioned that CNN methods have a better performance compare to traditional machine learning methods. It is not clear which type of CNNs are suitable for Covid-19.
3- Quality of some Figures are low, Fig.3 and Fig. 14.
4- It is not clear how many cases are used for training and test in Table 3.
5- In conclusion section, I want to read the author's point of view regarding suitable and successful methods in Covid-19 specifically not generally (CNN methods).
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.