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.
Thank you for addressing all of the previous comments from the reviewers, we are pleased to accept the manuscript for publication.
No further suggestions/comments.
No further suggestions/comments.
No further suggestions/comments.
Thank you for taking the time to diligently consider my comments. All my comments have been adequately addressed either through additional analysis or revisions in text. The paper adds to our knowledge of COVID-19 impacts on tuberculosis. I have no further suggestions.
The reviewers have highlighted some aspects of your experimental design that require clarification, as well as recognising a potential limitation to your approach that has not been discussed in the manuscript.
Please read all of the comments from both reviewers.
[# PeerJ Staff Note: It is PeerJ policy that additional references suggested during the peer-review process should *only* be included if the authors are in agreement that they are relevant and useful #]
The figures could be improved by providing additional detail:
o Figure 2C: what does each line represent?
o Figure 3/5: What do the dashed blue lines represent?
o Figure 6/7: What do the shaded grey areas represent? Are they prediction intervals? Why does the LSTM model have no prediction interval?
Several other studies have evaluated the change in TB cases during the COVID-19 pandemic before (see citations). While it is valuable to know that the Prophet model has good predictive power, I think the biggest contribution of the paper is the rebound of TB cases in 2023. This is something that has been under researched and I think should be emphasized more. To do so, is it possible to assess the difference in predicted and actual TB cases by year? This could provide a measure of COVID-19 impact by year and assess potential rebound in 2023 to pre-pandemic trends.
https://pubmed.ncbi.nlm.nih.gov/35871653/
https://pubmed.ncbi.nlm.nih.gov/37824176/
https://pubmed.ncbi.nlm.nih.gov/38816699/
https://pubmed.ncbi.nlm.nih.gov/34173601/
https://pubmed.ncbi.nlm.nih.gov/38911260/
The methods are robust and statistically sound
An important limitation that should be added is the inability of the study to know whether the decrease in reported cases is owing to disruptions in TB services or to decreases in TB transmission.
1. The Abstract section gives the novelty of the research conducted
2. The introduction contains the reasons for choosing the SARIMA, prophet, and LSTM models in the study to be compared.
3. An introductory section containing time series techniques, statistics, and Deep Learning approaches is included in the background section and related works. This will make it easier for readers to find information about the model that has been used in the time series prediction problem and compare the results.
4. At the end of the introduction, the author should add the research contribution to the previous research, so that it will be a novelty to the author's research.
5. The introduction adds a paper organizer to make it easier for readers to identify the points written in this article.
6. There is no research flow yet, this research is not clear how to do it. It is necessary to add a structured research flow or workflow to explain the stages of research that are carried out.
7. Give a conclusion from the comparison results in Figure 7 Table 4 about the results of the model comparison based on the results of the tests carried out, which model is more than all the models tested.
8. Figure 7 of tables 4 and 3, it says that the predictive performance of the model is improving, explains what causes the performance of the model to improve.
8. More clarifications and highlights about the research gaps in the related works section. I suggest to discuss the following studies:
• sediyono, e., wahyuni, s.n. and sembiring, i., 2024. Optimizing the long short-term memory algorithm to improve the accuracy of infectious diseases prediction. Iaes international journal of artificial intelligence, 13(3), pp.2893–2903. [url]Https://doi.org/10.11591/ijai.v13.i3.pp2893-2903[url].
• Sembiring, i., wahyuni, s.n. and sediyono, e., 2024. Lstm algorithm optimization for covid-19 prediction model. Heliyon, [online] 10(4), p.e26158. [url]Https://doi.org/10.1016/j.heliyon.2024.e26158[url].
• Wahyuni, s.n., sediono, e., sembiring, i. And khanom, n.n., 2022. Comparative analysis of time series prediction model for forecasting covid-19 trend. Indonesian journal of electrical engineering and computer science, 28(1), pp.600–610. [url]Https://doi.org/10.11591/ijeecs.v28.i1.pp600-610[url].
1. The topic is very interesting, and the problem is well-defined. The proposed algorithms are slightly modified versions of existing ones. The scientific contribution is not significant enough.
No comment
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.