Review Reports

Round 1

Reviewer 1 Report

The paper reports the machine learning and radiomics approach in lung cancer for predicting histological subtype. This is an interesting attempt for radiation research. However, The present quality of the manuscript is insufficient for publication, please consider the following suggestions that might help to improve the manuscript

Specific Comments:

1. Why used unenhanced CT scans in this study? if any specific reason? what does the author think is the innovation of this manuscript?
2. The authors are requested to discuss more about the dataset information in the manuscripts, in particularly other cancers group (n= 21). if any specific reason?
3. The order of experimental methods should be arranged.
4. The discussion and conclusion should be rewritten.
5. It is needed to improve the Figure 1. It is too small.

 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

• The design of the study should be specified in the Materials and Methods section.  • If ethics committee approval and informed consent are required for this study, it should be noted within the Materials and Methods section together with the relevant protocol number and date.  • The primary output/endpoint variable(s)/measurements of the study should be defined. 

• What are the inclusion and exclusion criteria in the study?  • Which randomization method was used in the distribution of the individuals included in the study to the groups?  • Which blinding (masking) method was used in the study?  • Data analysis or Statistical analysis sub-section title should be added to the Materials and Methods.  • How was the sample size determined? This information should be explained in the Materials and Methods section.  • Which sampling (probable or non-probable, etc.) method was used in the study?  • Statistical tests for hypothesis testing and their assumptions should be specified in the statistical analysis of the study in the Materials and Methods section.  • The details (version, license number, etc.) of the statistical package(s) or program(s) should be given in the section of "Data Analysis or Statistical Analysis".  • It should be explained how the qualitative and quantitative data are summarized under the sub-heading of Statistical Analyzes in the Materials and Methods section of the study.  • The exact P values should be added to the table(s) (p=0.25; p=0.03).  • Which methods are used to model relationships between variables?  • The descriptions and other descriptive values/data should be defined on the tables and shapes. • Are the data subjected to pre-processing?  • How were extreme/outlier values in the data determined and resolved? 

• What approaches were used to test the validity of the models? • Which metrics were used in the performance evaluation of the estimates of models/algorithms?  • How were the predictive models selected in this study?

• How was the most suitable cut-off point determined using the receiver operator characteristic (ROC) curve analysis?

• Which method(s) was/were used to optimize the hyperparameters of models/algorithms?

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Thanks to the authors for addressing all the comments and improving the manuscript.

Reviewer 2 Report

Acceptable