Round 1

Reviewer 1 Report

 

 

Dear Authors,

 

The manuscript is well-written, summarizes the use of AI in bladder cancer, and could be an interesting read for clinicians, medical researchers, and computational scientists.

 

Major comment:

 

The manuscript could be improved if the "introduction section between 4th and 5th paragrapgh" could briefly mention, how the use of AI in the different medical specialties has been changing over time. Similarly, the trends of FDA-approved machine learning and AI in bladder cancer could be briefly mentioned to generate curiosity among readers.

 

Authors could cite recent this paper that has summarized and updated the FDA-approved AI-based medical device up to 2022.

For eg: https://www.medrxiv.org/content/10.1101/2022.12.07.22283216v1

FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An updated 2022 landscape

 

“As of the latest update on October 5, 2022, FDA has listed 521 approved AI/ML-Enabled Medical Devices out of which 91 (about 17%) devices are approved by FDA in the year 2022.”

 

 

 

 

Minor comments:

 

It is recommended that the limitations of AI in the diagnostic application is clearly mentioned.

The author could include something similar as follows.

 

1.     Lack of availability of large datasets and heterogeneity of the clinical data are limitations in training AI models for better sensitivity and specificity.

 

2.     Renormalizabilty issue of machine learning and AI is one of the major challenges in its implementation.

Author Response

Dear Authors,

The manuscript is well-written, summarizes the use of AI in bladder cancer, and could be an interesting read for clinicians, medical researchers, and computational scientists.

Major comment:

The manuscript could be improved if the "introduction section between 4th and 5th paragrapgh" could briefly mention, how the use of AI in the different medical specialties has been changing over time. Similarly, the trends of FDA-approved machine learning and AI in bladder cancer could be briefly mentioned to generate curiosity among readers.

Authors could cite recent this paper that has summarized and updated the FDA-approved AI-based medical device up to 2022.

For eg: https://www.medrxiv.org/content/10.1101/2022.12.07.22283216v1

FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An updated 2022 landscape

 “As of the latest update on October 5, 2022, FDA has listed 521 approved AI/ML-Enabled Medical Devices out of which 91 (about 17%) devices are approved by FDA in the year 2022.”

 

Response:

We thank the Reviewer for this important suggestion. We improved our manuscript briefly mentioning AI applications in different medical specialities (Introduction, see lines 64-77, between previous 4th and 5th paragraph). In this regard, we focused on the current major uses in medical sciences to emphasize to the reader how this technology is already having a major impact on this field. We also added a paragraph to describe the current FDA-approved AI based medical device, mentioning the paper “FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An updated 2022 landscape” as you suggested (Conclusion and future perspectives, see lines 264-267). We thank the Reviewer for the commitment and the interesting insights given to our work.

Minor comment:

It is recommended that the limitations of AI in the diagnostic application is clearly mentioned.

The author could include something similar as follows.

1. 
       Lack of availability of large datasets and heterogeneity of the clinical data are limitations in training AI models for better sensitivity and specificity.
   
   2.     Renormalizabilty issue of machine learning and AI is one of the major challenges in its implementation.

 

Response:

We thank the Reviewer for this comment. We highlighted and stated the major limitations of AI in the diagnostic application to BCa in “Conclusion and future perspectives” section (see lines 265-270). We pointed out the lack of large datasets and heterogeneity of clinical data to train DL models, as you recommended. Moreover, we emphasized the lack of short-mid-long term oncological outcomes in patients diagnosed through computational technologies enhanced instruments.

Author Response File: Author Response.docx

Reviewer 2 Report

This is a fairly brief, but well written review of the use and potential of AI for diagnosing, treating, and studying bladder cancer. 

Author Response

We thank the reviewer for the kind comment

Author Response File: Author Response.docx

Reviewer 3 Report

It is my pleasure to review this paper entitled “Artificial Intelligence in Bladder Cancer Diagnosis: Current Applications and Future Perspectives”. The aim of this review is to analyse the most recent literature exploring current experiences and future perspectives on AI role in BCa scenario. The topic is very interesting. Overall article is well written English is fluently and adequate.

Please add strengths and limitation of the paper.

Author Response

It is my pleasure to review this paper entitled “Artificial Intelligence in Bladder Cancer Diagnosis: Current Applications and Future Perspectives”. The aim of this review is to analyse the most recent literature exploring current experiences and future perspectives on AI role in BCa scenario. The topic is very interesting. Overall article is well written English is fluently and adequate.

Please add strengths and limitation of the paper.

 

Response:

We thank the Reviewer for this comment. We highlighted the limitations and strengths as requested (Conclusion and future perspectives, see lines 254-258, 267-272). The main strength of our work is defined by its BCa diagnostic pathway-based architecture. Our paper has been developed aiming to bring the reader as close as possible to an idea of AI-enhanced clinical practice. We added a new paragraph on limitations.

 

We thank the Editor and the Reviewers for these suggestions and comments. We hope that our revisions will improve the manuscript.

Author Response File: Author Response.docx