PONE-D-21-32708A machine learning approach to evaluate the state of hypertension care coverage: From 2016 STEPs survey in IranPLOS ONE

Dear Dr. Farzadfar,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has  some merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Specifically, please address all comments made by the reviewers. Be sure to:

• Indicate what is the added value of the study and its contribution to the field
• Address all concern in its method (design/analysis)

Please submit your revised manuscript by Jan 17 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Amir Radfar, MD,MPH,MSc,DHSc

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at 

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and 

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, all author-generated code must be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse.

3. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match. 

When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section.

4. We note that you have indicated that data from this study are available upon request. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For more information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. 

In your revised cover letter, please address the following prompts:

a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent.

b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings as either Supporting Information files or to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories.

We will update your Data Availability statement on your behalf to reflect the information you provide.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Partly

Reviewer #2: No

Reviewer #3: Partly

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: N/A

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: The publication "A machine learning approach to evaluate the state of hypertension care coverage: From 2016 STEPs survey in Iran" by Tavolinejad et al. tackles an important problem of development and progression of hypertension, moreover it is driven by the low- to middle-income country data. The authors consider hypertension to be defined as blood pressure ≥ 140/90 mmHg), or reported use of anti-hypertensive medications, or a previous hypertension diagnosis. The four steps of care considered for the analysis included screening, diagnosis, treatment, or control. Using machine learning approach (random forest), the authors estimated that from 30.8% of population with hypertension, 89.7% were screened, 62.3% received diagnosis, 49.3 were treated, and 7.9% achieved control. The random forest analysis indicated that younger age, male sex, low wealth, and unmarried/divorced status were associated with a lower probability of receiving care. As this work represents a high educational value to the populations affected by hypertension as well as may serve a the learning about detection and consequences early, this potential is diminished by several major issues related to the following aspects:

1. Although the statistical data is rich and presented clearly (Table 1), the figures in the main manuscript are not readable. On the other hand, the figures in the supplementary files are clear and of high quality. The analyses are performed with a good technical standard and are described in sufficient detail however I disagree with the usage of the word "novel" toward the random forest application in these population data.

2. The authors used random forest to evaluate the features importance for each of the stages, while the post analyses of random forest include other valuable applications that I highly recommend to the authors. To do that, the authors should move beyond feature importance or probability distribution within. The study will benefit the audience if the authors consider:

- plotting/analyzing the probability data in higher dimension to seek for hidden relationships and patterns between e.g., age, education, status, gender, etc, i.e., patterns not limited to the conclusions that are expected from linear analysis of individual data (young single male with low income having lower care). Using the four figures to support the findings seems as a very good start to more advanced analyses and more informative conclusions. In addition, potential relationships with the biological class of features (BMI, diabetes, smoking) would start showing to play a role in only a particular cohort.

- how do the classifiers cluster (clustering) or relate (PCA) to one another among population?

- building a predictive model from the data, perhaps for the remaining large cohort of the population not associated with hypertension.

3. It is unclear if step "screening" is associated with HP when introduced in the abstract.

4. Lines 90-91: is condition (I) considered when "SBP and DBP" or "SBP or DBP" are present?

5. Line 99: the term "screening" still doesn't explain clearly if the BP measured was ever related to HP.

6. Line 117: it is unclear what authors mean by "Random forest is an ensemble model that handles categorical variables AS THEY ARE"?

7. Lines 118-119: authors should expand on: "...it provides appropriate and competitive predictive accuracy compared to other algorithms". It is recommended that authors make an explicit comparison of their analyses with other machine learning approaches before stating that random forest is the best choice for it.

8. Line 119: definition of "hyper-parameters" should be put early for the readers.

9. Line 131: it is unclear what authors mean by knowledge in: "...tools were used to extract knowledge".

10. Line 161 and further: the class of "white collar" should be specified as either clerks or workers for consistency.

11. Lines 184-185: The sentence "Very low (MPP=0.86) and low (MPP=0.87) wealth indices were associated with a decreased probability of being screened." is unclear.

12. It is suggested that, given the longitudinal data/steps present, the authors should analyze the longitudinal data on additional level; one idea could be to look at the trends in features' importance while moving along the 4 steps. More informative analysis could include population models for the subpopulations pre-classified with the machine learning tools.

In summary, the study should be enhanced by computational analyses and graphical representation of the results, including, yet not limited to those suggested in #2 and #12. If these additional analyses are added, the manuscript could be submitted to the follow-up review.

Reviewer #2: The manuscript presents a Random Forest based machine learning approach to evaluate the state of hypertension care coverage through a population-based data from Iran. Unfortunately, the paper falls short in bringing any fresh insights to the readers. Most of the causes and recommendations made by the authors are already known to the community, and it is unclear what new insight machine learning is offering, if any. Bulk of the paper is dedicated to reporting what the tool running the Random Forest model outputs, without adequate deeper dive. There is little detail on handling the data itself, as what was done to pre-process, normalize and standardize the data prior to feeding it to the machine learning model. Given the understandable lack of availability of the dataset in public domain, it is useful to create credibility around the analysis through rigorous statistics and figures. The paper lacks to explain as what the predictions mean in context of the data as well as the field itself. On what could be a very valuable dataset to analyse, I am afraid that there is a need for extended analysis and deeper interpretation of results, both in terms of machine learning model as well as for the hypertension care coverage.

Reviewer #3: The authors present a very well-written and important paper that helps assess the reasons for the discontinuation in the care pathway through the diagnosis, treatment and control of hypertension in Iran. For that they use the random forest algorithm and conclude that younger adults, men, unmarried or divorced people and those with lower socio-economical status are more at risk to not receive treatment and achieve control of their blood pressure.

Overall the paper was clear and presented the findings in an understandable fashion. I have two main suggestions to be discussed with the authors in two different domains.

(A) Guideline Selection and Phenotyping Algorithm

1. Firstly, I would like to understand the reason for the selection of the older AHA guideline (2017) since in 2020 there was the release of a new version. The new guideline document can be found in the following weblink: https://www.ahajournals.org/doi/10.1161/HYPERTENSIONAHA.120.15026. In it, there are some different recommendations for the essential and optimal control of blood pressure.

2. Also, according to the author's phenotyping algorithm, hypertensive patients had SBP >= 140 and DBP >= 90 and controlled hypertensive SBP < 130 and DBP < 80. This leaves a gap in the participants who had SBP in between 130-139 and 80-89 (the new guideline covers that gap). I suggest that a closer look is taken into that.

3. Again, regarding the guideline, usually blood pressure is measured in more than one encounter or with out-of-office techniques to discard white coat and masked hypertension. I do understand the cross-section nature of the STEPs study and the lack of longitudinal data. However, I believe this should be mentioned in the limitations as well.

(B) Algorithm Selection and Hyper-Parameter Tuning

1. The use of the random forest algorithm is quite interesting and it is indeed powerful. However, there is another class of ensemble algorithms that usually outperforms random forest called gradient boosting machines (examples are XGBoost and LightGBM) which generally use decision trees. In that aspect, I would like to hear from the authors the reason for opting for random forest instead of one of those algorithms.

2. Lastly, it was not clear to me how the hyper-parameter tuning was executed. This is a very important step and it is good practice to have a separated validation set for that. It would be beneficial to understand the methodology used by the authors and have it thoroughly explained in the paper or in the supplement for better judgment of the results and also increased reproducibility.

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: Yes: Ariane Sasso

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

PONE-D-21-32708R1A machine learning approach to evaluate the state of hypertension care coverage: From 2016 STEPs survey in IranPLOS ONE

Dear Dr. Farzadfar,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

 Specifically,please address point B from the reviewer #3 which is still missing.

Please submit your revised manuscript by Jul 22 2022 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Amir Radfar, MD,MPH,MSc,DHSc

Academic Editor

PLOS ONE

Journal Requirements:

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #1: All comments have been addressed

Reviewer #3: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #3: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #3: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #3: No

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #3: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Thanks to the Authors for addressing all the comments and explaining the unclear statements. The article is now recommended for publishing.

Reviewer #3: I have one last point that needs addressing. Overall the paper was clear and presented the findings in an understandable fashion. Most of the recommendations from the previous review were followed.

1) Guideline Selection and Phenotyping Algorithm

Items A and C were answered satisfactorily. However, point B is still missing:

B. Also, according to the author's phenotyping algorithm, hypertensive patients had SBP >= 140 and DBP >= 90 and controlled hypertensive SBP < 130 and DBP < 80. This leaves a gap in the participants who had SBP between 130-139 and 80-89 (the new guideline covers that gap). I suggest that a closer look is taken into that (check lines 91-95).

2) Algorithm Selection and Hyper-Parameter Tuning

All the items were answered satisfactorily. In the future, the implementation of algorithms such as XGBoost and LightGBM is currently as easy as RF (there are open-source packages and libraries in Python), and they could potentially be tried out.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #3: Yes: Ariane Sasso

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

A machine learning approach to evaluate the state of hypertension care coverage: From 2016 STEPs survey in Iran

PONE-D-21-32708R2

Dear Dr. Farzadfar,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Amir Radfar, MD,MPH,MSc,DHSc

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation.

Reviewer #3: All comments have been addressed

Reviewer #4: All comments have been addressed

**********

2. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #3: Yes

Reviewer #4: Yes

**********

3. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #3: Yes

Reviewer #4: Yes

**********

4. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #3: No

Reviewer #4: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #3: Yes

Reviewer #4: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #3: Dear Authors,

Thank you very much for the great work and for addressing all the comments in detail. I am sorry this review process took so long, and I am to blame for not meeting the deadlines as I wished. Hopefully, your paper will be published soon. I wish you much success!

Reviewer #4: Thank you for this well written article. I believe this manuscript will add to the body of literature.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #3: Yes: Ariane Sasso

Reviewer #4: Yes: Irina Filip

**********