Next Article in Journal
The Effects of Service Quality of Medical Information O2O Platform on Continuous Use Intention: Case of South Korea
Previous Article in Journal
A Semi-Supervised Approach to Sentiment Analysis of Tweets during the 2022 Philippine Presidential Election
 
 
Article
Peer-Review Record

Predictive Modeling for the Diagnosis of Gestational Diabetes Mellitus Using Epidemiological Data in the United Arab Emirates

Information 2022, 13(10), 485; https://doi.org/10.3390/info13100485
by Nasloon Ali 1,*, Wasif Khan 2,3, Amir Ahmad 2, Mohammad Mehedy Masud 2,3, Hiba Adam 1 and Luai A. Ahmed 1,4
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Information 2022, 13(10), 485; https://doi.org/10.3390/info13100485
Submission received: 6 September 2022 / Revised: 29 September 2022 / Accepted: 3 October 2022 / Published: 10 October 2022

Round 1

Reviewer 1 Report

In this paper, the authors have proposed a technique to predict the diabetes in pregnant women. There are some issues which need to be handled by the authors.

1.      Abbreviations are repeated. For example- Gestational Diabetes Mellitus (GDM)

2.      Reference of Shapley 2016 is missing.

3.      Section 2 should be renamed. As materials and methods indicates that the authors have used some materials.

4.      Equaitons should be numbered and should be used in the proposed method.

5.      l(.), loss function, is not defined in the given equations.

6.      Write the proposed method in algorithmic form.

7.      Give reference of dataset used so that reader can observe it and use the same to enhance the research.

8.      Proposed method should be compared with existing methods.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The relationship among self reported GDM and education sholud be explored since those women that are uneducated perhaps do not understand they had allready GDM in previous pregnancies. A practical outcome of the issue should be pointed out- an app to estimate GDM  ?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

The manuscript is set up correctly. The experimentation is adequate and the results are clearly presented.

I have several concerns reviewing this article:

-          Paragraph 128-130 must be placed before the previous equation (line 127)

-          Paragraph 132-133 must be placed before the previous equation (line 131)

-          Table 1 must be more detailed (the table must explain its content):

o   Variables Primiparity and Physical activity prior to current pregnancy have no % after the values in the brackets

o   An endnote must specify that the continuous values are expressed as average+/-standard deviation

o   Using * and ** the authors must specify the Student or the Pearson tests even it is obvious

-          Lines 174-177: concerning the ROC validation for the models, authors must provide a p value in order to validate the AUCs

-          Concerning Figure 1

o   The figure must provide a square as it is a standard representation for the ROC curve

o   The GBM is very strange as shape, the representation is not discrete, authors must provide a good explanation for this shape

-          Figures 2 and 3 are mostly the same, can be reduced to only one figure

-          Line 200 I cannot find any pot in your article but I can find a plot… please correct

-        At the end of results, I expect from the authors to provide an equation of the best model with the calculated parameters.

-       Discussion and conclusions chapters must emphasize not only on the XGBoost algorithm but also on the importance of the medical selected parameters

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The paper is acceptable in current form.

Back to TopTop