LASSO-Cox Modeling of Survival Using High-Resolution CT-Based Radiomic Features in a Cohort of COVID-19 Patients and Its Generalizability to Standard Image Reconstruction
, Lorenzo Spagnoli 2,†, Maria Francesca Morrone 2,†, Miriam Santoro 1,2, Francesca Coppola 3,4, Silvia Strolin 1, Rita Golfieri 3 and Lidia Strigari 1,*Round 1
Reviewer 1 Report
This paper applies the LASSO-COX model to the COVID CT images. The topic is very interesting but has several limitations as follows:
1. A very limited dataset 435 images have been used. It MUST include more CT images that are publicly available; for example
https://www.kaggle.com/datasets/plamene duardo/a-covid-multiclass-dataset-of-ctscans
2. The image resolution is very low and needs to improve
3. The writing needs to improve.
4. Authors must need to compare with other State of the art methods/ studies
Also, please find the attached for more corrections.
Comments for author File: 
Comments.pdf
Author Response
We would thank the Referee for his/her comments and suggestions. The point-by-point reply is reported in the pdf file.
Author Response File: Author Response.pdf
Reviewer 2 Report
1. Please re-write this statement "Lung volume semiautomatically delineated with SOPHiA RADIOMICS. 175 RFs per scan 19 were derived from 239 COVID-19 patients (training/test dataset) with high-resolution CT images 20 and 196 COVID-19 patients (validation dataset) with high-resolution and standard reconstruction 21 CT images".
2. What does "The training dataset was randomly split 100 times into training and test sets, using a 70/30 proportion" mean? Please re-word.
3. Please double check for the use of bracket for the reference in text.
4. SARS-CoV-2, for its fullname and abbreviation are explained twice, on paragraph 1 and 4.
5. It would be better if you give some information about SOPHiA DDM, mediastinum and parenchyma
6. More details are reported in [ref lorenzo]. Seems reference problem.
7. shrinks.glmnet cross-validation the dot is a typo??
8. Check the equation format
9. Figure 5 has no numbering unit
10. The result must be improved significantly
10. Please have a comparative study table in discussion chapter
Author Response
We would thank the Referee for his/her comments and suggestions. The point-by-point reply is reported in the pdf file.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
This manuscript may be publishiable. Still, the figure quality is not up to the mark. The table and figure captions are on different pages. This is unacceptable. Try to solve this.
Author Response
R1: This manuscript may be publishiable. Still, the figure quality is not up to the mark. The table and figure captions are on different pages. This is unacceptable. Try to solve this.
We would like to thank the Reviewer for the suggestions. We improved figure quality as suggested and moved the caption to be on the same page of the figure/table.
Reviewer 2 Report
I have no any comment.
Author Response
We would like to thank the Reviewer for the previous suggestions.
