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 submitting your revised manuscript. The authors have addressed all the editorial concerns. I am pleased to inform you that it has been accepted for publication.
Thank you for submitting your revised manuscript, diligently addressing the comments.
I agree that the manuscript has been significantly improved. However, some minor revisions are still required before we can proceed with publication. These primarily involve addressing a few remaining comments and ensuring the manuscript adheres to our formatting guidelines.
Please carefully review the attached document. Formatting and typographical errors have been highlighted using Track Changes.
We look forward to receiving your final manuscript.
Dear Authors,
Thank you for your diligent efforts in addressing the first round of revisions. The content updates are well done. However, I have some remaining concerns, primarily regarding the clarity and formatting of the manuscript:
Paragraph Flow and Formatting: The current paragraph structure hinders readability. Please revise the text to ensure a smoother, more logical flow. Consider breaking down long paragraphs, using clear topic sentences, and improving transitions between ideas.
Results Section Clarity: The results section needs further clarification. While you present data effectively, you assume reader familiarity with the tools and scoring interpretations. Please explain the implications of high or low scores within the results section. This will make the findings more accessible and meaningful to a broader audience.
Title Justification: While other studies may have used "questions" in their titles, I believe "keywords" is more appropriate for this study as it accurately reflects the data input method (keywords entered in chat). Please revise the title accordingly.
Table Clarity: The tables still lack clarity regarding data presentation. Please explicitly label median values and clarify the meaning of bracketed numbers (presumably minimum and maximum). Additionally, you mention p-values for categorical data; please ensure the statistical analysis aligns with the data type. If all variables are continuous, using p-values designed for categorical data would be inappropriate.
I appreciate your attention to these matters.
Dear Authors,
We have carefully considered your manuscript, “Assessing the Readability, Quality and Reliability of Responses Produced by ChatGPT, Gemini, and Perplexity Regarding Most Frequently Asked Questions about Low Back Pain” and have decided that it requires major revision before potential acceptance for publication PeerJ.
While the topic of your research is timely and potentially impactful, we believe that the manuscript requires significant improvement in several key areas.
We also agree with many of the valid points raised by the two reviewers, and we urge you to carefully consider their suggestions.
Specific Comments:
1. English and References:
• Please carefully review the manuscript for grammatical errors and typos. We have identified some unclear passages, particularly in lines 290-297, which may be due to a language translation issue. Please review and revise these sections to improve clarity and readability.
• Many sentences do not have a clear reference. For example” It is stated that the point prevalence of LBP that limits activity is 7.3% and 540 million people 69 suffer from this complaint at some point in their lives. Not only that, it is emphasized that LBP is 70 the number one cause of disability globally. (Hartvigsen et al., 2018). Are both sentences coming for the same reference. This recurs in many areas of the text.
• Please ensure that the entire manuscript is written in clear and concise English.
2. Introduction:
• The introduction should be more focused on the specific topic of using AI for patient education, particularly in the context of low back pain.
• A significant portion of the current discussion section, which reviews the existing literature on AI chatbots should be moved to the introduction (lines 347 – 383, a long paragraph)
• The introduction should clearly state the research gap that the current study aims to address.
3. Study Design:
• The study design needs to be more detailed and transparent. The design should be clear so that any other researcher can replicate the study.
• Please clarify the following:
o Who were the different users involved in generating keywords? Were they research assistants or authors especially those that used different accounts for different keywords? Was a different user assigned to each keyword? Were fake accounts used?
o What specific questions were asked of ChatGPT? Please provide examples of the keywords and the corresponding questions. The title mentioned common questions about low back pain, the design talks about keywords.
• Provide more details about the tools used in the study, including their validity and reliability metrics.
4. Results:
• In the statements where you mention there is a difference between one platform and another; it would be good to mention which one was better.
• There are very small sections or paragraphs that can be combined. No need to include every single result in the table in the text.
• A clearer description of the study design will help us assess the validity and reliability of the results
6. Discussion:
• The discussion should follow a clear and logical narrative. Begin by briefly summarizing the study's key findings.
• Then, delve into a discussion of the implications of these findings, comparing and contrasting them with existing literature.
• Conclude the discussion by highlighting the practical implications of the study and suggesting directions for future research.
7. Abstract
• Please revise the abstract after your major revision
Please note that the final decision regarding the manuscript's acceptance will depend on the quality of the revisions and the clarity of the study design.
1.The study would benefit from a brief explanation of why the authors selected these three specific AI chatbox, which would strengthen the readers' understanding of the methodological choices.
2. Ensure consistent citation formatting throughout the manuscript. For instance, citations should be placed before the period in several locations, such as on lines 70 and 190.
3. Grammar issues need to be addressed for improved readability. It may be beneficial to request a senior author or professional editor review the text. Specific examples include:
Lines 211-213: “Frequency 212 data included numbers and percentages for categorical variables and medians with ranges 213 (minimum-maximum). for continuous variables. ”
Lines 215-217: “Intraclass correlation coefficients (ICCs) were calculated for each formula, to assess the consistency of the calculators, Statistical significance was set at p < 0.05.”
The article includes measures for Readability, Quality, and Reliability, but it does not provide information on the validity of these measures. Including validity and reliability of measures would reinforce the credibility of the study's findings.
Conclusions are clearly stated and directly address the research question, limited to the findings of the study without overstating causation.
1. It would strengthen the manuscript to include a section on the practical implications of the findings. Discussing how the results may impact the field, inform future research, or contribute to practical applications would enhance the paper’s relevance and demonstrate the broader significance of the work. This addition can provide readers with a clearer understanding of how the findings apply beyond the study’s immediate context.
2. The format of Table 3 appears crowded and impacts readability. Consider reformatting it to improve clarity. Suggestions include adjusting column widths, using adequate spacing between rows, or breaking the information into separate tables if feasible. Improving the layout will make the data easier to interpret and enhance the overall presentation.
The article needs considerable improvement for enhancing its readability
In statistical analysis, (p<0.05) was considered significant but in reporting its mentioned p<0.001
Intra class correlation coefficient s can be corrected as ICC , in some places its kept ICCE
Please mention the title for tables
If possible include one or two important tables in the manuscript, placing them all in supplementary files may not be good for reader to understand about the study
1. p- values for each assessment criteria can be mentioned, its not uniformly described
2.In result section reliability and quality assessment - the language is not understandable, may be corrected
4. Future recommendations of the study can be provided as separate heading in discussion
5. Discussion can be made simpler and readable, some paragraphs looks complex and difficult to understand
6. Conclusion needs to be revised as its not matching with what is mentioned in the abstract
1. Whether the necessary permissions required were taken from the three AI chatbots used for the study or they are available as free open source?
2. Research gap, research question/ need of the study is lacking in the introduction. can be written well. Research question needs to be more specific like why these three AI chats were used to assess the low back pain. It can be addressed in introduction.
3. English needs to improved throughout the discussion.
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.