PANDAS: Paediatric Attention-Deficit/Hyperactivity Disorder Application Software
Round 1
Reviewer 1 Report
Authors have proposed a novel software to identify ADHD kids. I am unable to access the quality of the paper as there is not much information on the software and also features used for classification.
Please provide more details on software.
Provide more information on the features used.
Did the authors rank the features
In Figure 3, what are the three output classes?
I feel that, introduction is shallow. Please include latest papers related to this topic. Author may read recent review on this topic "Diagnosis of attention deficit hyperactivity disorder using imaging and signal processing techniques"
Provide the tuning parameters of the classifier.
Discussion: This section is too weak. Discuss the relation between the features and ADHD
Highlight the advantages and disadvantages of your method.
Compare the performance with other methods
What is the future work?
The number of subjects used is too few.
Did the authors seek the ethical approval for this study. Please mention it.
Table 3 and 4 needs more explanation.
Author Response
Thank you very much for your comments, please refer to my reply attached below
Author Response File: 
Author Response.pdf
Reviewer 2 Report
This manuscript presents a study to gather real-time user data during a tablet-based game-play and to train a linear binary support vector machine (SVM) for differentiating an ADHD individual from a non-ADHD individual. The authors may want to address the following comments prior to consideration for publication.
1. Line 6-7: The email and tel info is incomplete: "[email protected]; Tel.: +xx-xxx-xxx-xxxx".
2. There are only two rows/columns labeled in Fig. 3. How about the other row/column?
3. Is there any other method to detect ADHD other than the clinical diagnosis mentioned on page 1? If yes, how does the result presented in this study compare with them?
4. As stated, the sample size in the current study was fairly small. Have the authors done a power analysis to design the experiment?
Author Response
Dear Reviewer:
Thank you very much for your comments, please refer to my reply attached below.
Author Response File: Author Response.pdf
Reviewer 3 Report
1. Methodology-related comments
1.1. In Subsection 3.4., a list of the features used in the experiments should be provided; alternatively – a clear description enabling a potential reader to reproduce all of the features. What are the statistical features? What are the morphological features? Unfortunately, the description provided in lines 119–123 is not enough.
1.2. In regard to the feature selection: how was the “combined” set of features, mentioned in the third row of Table 3., constructed? Moreover, the procedure of the “manual” feature selection has to be described. Which features were chosen? What was the rationale behind selecting some specific features?
1.3. How was the test set – comprising seven children – constructed? Why the proportion between the boys and girls was 2/5? Some explanations are needed.
2. Other comments
2.1. I would suggest investigating whether the Principal Component Analysis (PCA), used as a means to feature selection, affects the classification results.
2.2. The game presented to the children may be perceived as an action game. I think that the games of this kind are more attractive to boys who may be more interested in and focused on playing, and therefore the methodology of experimentation, proposed by the Authors, may be more accurate in predicting the ADHD among the boys. Is there a chance that a more girlish game could bring more accurate results of the classification among the girls?
Author Response
Dear Reviewer:
Thank you very much for your comments, please refer to my reply attached below.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The authors have addressed my prior comments.
Author Response
Thanks
Reviewer 3 Report
Since the Authors have answered all of my comments, and introduced some essential changes to the manuscript, I recommend accepting the manuscript for publication.
Author Response
Thanks
