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.
All of the issues raised by the reviewers are now addressed.
Once the minor issues identified by the third reviewer are addressed, the manuscript will be ready for publication.
I think the author has addressed all the issues raised last time.
The experimental design is reasonable.
The statistical method is correct and the conclusion is reliable.
no comment
no comment
no comment
I would like to express my sincere congratulations on the revised version of your manuscript. The improvements made in response to the reviewers' comments have significantly enhanced the clarity and depth of the work. The manuscript now presents a well-organized, rigorous, and insightful contribution to the field.
I particularly appreciate the thoroughness with which you have addressed the concerns raised during the initial review, and your responsiveness has clearly strengthened the scientific merit of the paper. Your study provides valuable insights into [specific topic or area], and I believe it will be a significant resource for researchers and practitioners working in this area.
Thank you for your diligent efforts in refining this work. I commend you for your contributions, and I look forward to seeing the final published version in PeerJ.
I would like to thank the authors for their thorough revisions. Overall, the manuscript has improved significantly. However, I still have a few concerns:
Figure 1
In the response letter, the authors clarified "We have carefully reviewed both Figure 1 and the manuscript, and we would like to clarify that Figure 1 is consistent with the text. Both the figure and the manuscript describe a total of 12 risk factors. " However, upon examining Figure 1 (specifically A and B at the top), it appears that the numbering begins at 11, suggesting that the model was supplied (and capable of selecting) 11 total predictors. This discrepancy might cause confusion and could benefit from additional clarification or revision.
Line 106
The text reads, “We received a waiver of the need for informed consent from participants of your study.” This should be corrected to “our study.”
I appreciate the revisions and responses addressing the issues in this part.
The revisions addressing causal language are greatly appreciated. However, regarding the data and code, the authors mentioned “We have now corrected this by updating the input file to the correct .txt format, as indicated in the code.” At this time, it appears that only the .xlsx file is still available in the submission, and the .txt file is not visible. Could the authors clarify where to find this file? Without access to the .txt file, it is difficult to comment on whether the code, analysis, and figures are properly aligned.
Please address each issue raised by all of the reviewers in your revision.
[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services if you wish - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Your revision deadline is always extended while you undergo language editing. #]
The manuscript demonstrates clear and unambiguous professional English throughout, ensuring that the content is accessible and comprehensible to an international audience.
The literature references are well-integrated, providing sufficient background and context to support the study's relevance and significance in the field of colorectal cancer research.
The article is structured professionally, adhering to academic standards, with well-organized sections that facilitate understanding. Figures and tables are relevant, high-quality, and appropriately labeled, enhancing the presentation of data and findings.
Additionally, the study is self-contained, presenting relevant results that directly address the hypotheses posed, thereby contributing meaningfully to the existing body of knowledge in the field.
Overall, the manuscript meets the criteria for clarity, context, structure, and relevance, making it a strong candidate for publication.
The manuscript presents original primary research that falls well within the Aims and Scope of the journal, focusing on the development of a LASSO-derived Nomogram Prediction Model for Lymph Node Metastasis in Colorectal Cancer (CRC).
The research question is clearly defined, relevant, and meaningful, addressing a significant issue in CRC management. The authors articulate how their research fills an identified knowledge gap regarding the prediction of lymph node metastasis, which is crucial for improving patient outcomes and guiding treatment decisions.
The investigation is conducted rigorously, adhering to high technical and ethical standards, which is essential for ensuring the validity and reliability of the findings.
Furthermore, the methods are described in sufficient detail, providing the necessary information for replication. This includes a comprehensive explanation of the data collection process, statistical analyses, and the development of the prediction model, ensuring that other researchers can reproduce the study's results.
The novelty of this study is good. All underlying data have been provided, demonstrating robustness and statistical soundness. The data collection and analysis methods are controlled, ensuring the reliability of the results presented. The conclusions drawn in the study are well articulated. This clarity reinforces the study's contributions and implications for clinical practice in colorectal cancer management。
I suggest adding an introduction about the differences between MSS and MSI-H CRCs in the Discussion section.
The use of professional English is precise, clear, and formal throughout the article. The terminology is consistent and well-defined.The background and context has offered a comprehensive overview of the current state of research on colorectal cancer (CRC) and lymph node metastasis (LNM). The article structure is logically organized.The article has maintained focus on the central hypothesis throughout the study.
no comment
no comment
The paper develops a model that predicts lymph node metastasis (LNM) in colorectal cancer (CRC) patients based on common clinicopathological data, providing support for clinical decision-making. In particular, by constructing a clinical nomogram, the prediction results are made intuitive and easy to apply. Additionally, the model's performance is evaluated using ROC curves, calibration curves, and decision curve analysis. However, there are two areas for improvement:
1. Please provide a detailed description of the algorithm used for random allocation of patients.
2. Please perform correlation analysis, such as Pearson Correlation Coefficient or Spearman Rank Correlation, to examine whether there is a correlation between the variables, and present the results in a heatmap.
Overall, the paper is well-organized and clearly structured. The figures and tables serve their purpose effectively and are helpful in conveying the results. However, there are several areas for improvement:
1. English Presentation:
The manuscript's English could be improved to enhance readability. Several sentences are unclear or confusing. For example: Lines 100 – 101, line 103, line 209 to line 212.
2. Model Presentation:
The description of the logistic models could be enhanced by including mathematical formulations. Presenting the relationships between the outcome and predictors in a mathematical format would provide more precision and clarity than using only descriptive language.
3. Table Typos:
There are typographical errors in the tables. For example, the total number in Table 1 appears to be incorrect.
4. Figure Consistency:
Figure 1 seems inconsistent with the text. The manuscript mentions that 12 risk factors were used in the LASSO regression, but the figure starts with 11 predictors.
5. Figure Quality:
Figures 3 and 4 have low resolution, making it difficult to discern the details. These should be updated with higher-resolution versions.
The overall approach of using logistic models for prediction is well-conceived. The division into a training set and validation set is sound, and the use of multiple criteria to assess prediction performance in the validation set is commendable. However, there are significant concerns that should be addressed:
1. Variable Selection Flaws:
The variable selection process appears to have fundamental issues:
o The authors use the “comparative analysis” as the first step in the training set (abstract & line 122 - 130) to pick 12 potential risk factors, and then use the LASSO regression followed by stepwise logistic regression.
o The authors use "comparative analysis" as the initial step to identify 12 potential risk factors. However, this approach is problematic because the dataset may not be powered to find variables that differs significantly in two LNM groups. Variables that are not significantly different could still be valuable predictors.
o Following LASSO regression with stepwise logistic regression is not advisable. LASSO regression simultaneously selects variables and fits the model, and it is typically used as the final step in model building.
Suggestion:
Consider using a dimension reduction technique, such as Principal Component Analysis (PCA), to preprocess predictors before applying either LASSO regression or stepwise regression—but not both in sequence.
2. Training/Validation Set Ratio:
The rationale for using a 1:1 ratio for the training and validation sets is not explained since an 80/20 split is more commonly used.
Collaborating with a statistician might help refine the methodological approach and strengthen the paper.
The data provided appears to be legitimate, but there are concerns regarding the interpretation of the model and the code provided:
1. Causal Language:
Many statements about predictor effects suggest causation, which is not supported by the analysis performed. For instance, lines 141–154 use causal language. The authors should revise to describe associations rather than causation.
2. Code Discrepancies:
There are inconsistencies between the code provided and the analysis described in the manuscript, e.g.:
o The data file name in the code does not match the name of the file provided.
o The code suggests that 28 predictors (29–2+1) were used in the LASSO regression, but the manuscript states that only 12 predictors were included.
3. Code and Figures:
I am not certain whether the code provided can reproduce the figures in the manuscript. This raises doubts about the reproducibility of the results. Ensuring the code aligns with the analysis and figures is critical for transparency.
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.