This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIRx Med, is properly cited. The complete bibliographic information, a link to the original publication on https://med.jmirx.org/, as well as this copyright and license information must be included.
The authors of this research [
Authors should read the authors’ guidelines at https://www.jmir.org/content/author-instructions. I suggest that they adapt their manuscript to the templates offered by JMIR; the title does not match the format proposed by the journal, the appendices do not have a caption, the tables can go in the manuscript, etc.
In relation to the content of the manuscript, there is no exhaustive bibliographic review in which existing studies applied to a classification problem such as the one the authors present are mentioned. Because of this, the justification for the development they propose is quite weak and can be improved upon.
Authors indicate that they separated the data sets by
It would be enlightening to show the matrix of confusion as well as to indicate in a table a comparison of the measures of precision and accuracy on random forest with different hyperparameters.
To search for the best hyperparameters, I suggest using GridSearchCV or similar.
Finally, it is necessary to make a comparison between the proposed model and others that already exist.
Authors are requested to upload their code and the models to a repository to guarantee their reproducibility.
I thank the authors for their work in improving this manuscript. They have responded correctly to all my suggestions, and I consider that the manuscript has improved in quality and can be considered for publication in this journal.
None declared.