Help seeking behavior by women experiencing intimate partner violence in india: A machine learning approach to identifying risk factors

Nabamallika Dehingia; Arnab K. Dey; Lotus McDougal; Julian McAuley; Abhishek Singh; Anita Raj

doi:10.1371/journal.pone.0262538

Peer Review History

Original SubmissionJuly 8, 2021
1 Sep 2021 Decision Letter - Yukiko Washio, Editor PONE-D-21-21691 Help seeking behavior by women experiencing intimate partner violence in India: a machine learning approach to identifying risk factors PLOS ONE Dear Dr. Dehingia, 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. Please submit your revised manuscript by Oct 16 2021 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: http://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, Yukiko Washio, Ph.D. 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. Thank you for stating the following financial disclosure: “This study was funded under a grant from the Bill and Melinda Gates Foundation (Grant number OPP1179208; PI: Anita Raj)” Please state what role the funders took in the study. If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." If this statement is not correct you must amend it as needed. Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. 3. In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available. For more information about our data policy, please see http://journals.plos.org/plosone/s/data-availability. Upon re-submitting your revised manuscript, please upload your study’s minimal underlying data set as either Supporting Information files or to a stable, public repository and include the relevant URLs, DOIs, or accession numbers within your revised cover letter. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories. Any potentially identifying patient information must be fully anonymized. Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Please see our guidelines for more information on what we consider unacceptable restrictions to publicly sharing data: http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access. We will update your Data Availability statement to reflect the information you provide in your cover letter. 4. We note you have included a table to which you do not refer in the text of your manuscript. Please ensure that you refer to Table 2 and 3 in your text; if accepted, production will need this reference to link the reader to the Table. [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: Yes Reviewer #2: Partly ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: No ****** 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 ****** 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 ****** 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: Overall, the article is clearly written (some minor editing/grammatical errors that can be addressed with an additional review), engages with the literature, and establishes the gap in the literature which it is attempting to address. Minor Comment: In line 115 the authors indicate that emotional violence is not considered as an outcome. The rational for this could be brought upfront as well rather than only including it in the limitations section. Reviewer #2: This paper aimed to examine correlates of help-seeking from anyone (e.g. family, friends, police, doctor etc.), as well as help-seeking from any formal sources. To perform analysis, authors used data from a nationally-representative health survey conducted in 2015-16 in India, and included all variables in the dataset (~6000 variables) as independent variables. Two machine learning (ML) models were used- L-1, and L-2 regularized logistic regression models. Indeed, using ML to identify broad themes associated with help-seeking behavior is a very important technique. If authors can perform the ML appropriately, it would be unique and the results could be very informative. However, this manuscript doesn’t show the application of ML in the targeted aims. 1) In the “analysis” section, authors only listed some of introduction about ML methods, focusing on LASSO, L-1, L-2, and ITA. Authors didn’t outline the procedure of conducting the analysis. 2) In the “results” section, it is not clear that how the results were obtained from the methods based on the analysis. What’s results were based on LASSO, L-1, L-2 and ITA applied? 3) More importantly, λ and k values were not reported in the results section. AUC and other model measure metrics were not reported or event mentioned. 4) One of the important features based on ML is to rank the importance of the variables after variable selection, but the paper did not even touch the work. In summary, this paper should be majorly revised ****** 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 [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. https://doi.org/10.1371/journal.pone.0262538.r001
Revision 1
15 Oct 2021 Author Response We thank the reviewers for their relevant and useful comments, which has helped to make the manuscript stronger. Below we respond to each reviewer comment. Reviewer #1: Overall, the article is clearly written (some minor editing/grammatical errors that can be addressed with an additional review), engages with the literature, and establishes the gap in the literature which it is attempting to address. Minor Comment: In line 115 the authors indicate that emotional violence is not considered as an outcome. The rational for this could be brought upfront as well rather than only including it in the limitations section. Thank you for the comment. We have revised the Materials and Methods section to clarify the exclusion of emotional violence from the analysis. Our study does not cover emotional violence as an outcome, given that emotional intimate partner violence (IPV) is often not as agreed upon as physical and sexual IPV, as indicative of abuse and hence requiring help-seeking. Our study focusses on help-seeking for women experiencing sexual and/or physical IPV only- the forms of violence that are recognized more consistently by service organizations, as well as the criminal justice system. Reviewer #2: This paper aimed to examine correlates of help-seeking from anyone (e.g. family, friends, police, doctor etc.), as well as help-seeking from any formal sources. To perform analysis, authors used data from a nationally-representative health survey conducted in 2015-16 in India, and included all variables in the dataset (~6000 variables) as independent variables. Two machine learning (ML) models were used- L-1, and L-2 regularized logistic regression models. Indeed, using ML to identify broad themes associated with help-seeking behavior is a very important technique. If authors can perform the ML appropriately, it would be unique and the results could be very informative. However, this manuscript doesn’t show the application of ML in the targeted aims. 1) In the “analysis” section, authors only listed some of introduction about ML methods, focusing on LASSO, L-1, L-2, and ITA. Authors didn’t outline the procedure of conducting the analysis. Thank you for this important feedback. We have revised the Materials and Methods section to elaborate the procedure for using the two machine learning models in the study. We have also added a flowchart as supplementary information, that makes the different steps of the analysis clear and easy to interpret. The following text is included in the Analysis section: "We used a process of iterative categorization of results from two machine learning models, to identify themes correlated to IPV help-seeking. This process combines quantitative (machine learning models) and qualitative methods. The qualitative efforts include coding of results from statistical machine learning models, into different related and relevant themes. A flowchart depicting the different steps of the process is included in the Supplementary Information files. According to the ITA process, we first ran a lasso regression model on the training dataset with IPV help-seeking as the outcome, and all eligible variables in the DHS dataset as the independent variables. As noted above, lasso is often used for data reduction; it shrinks coefficient values of irrelevant variables to zero. Since our analysis included a large number of independent variables, our goal with lasso was thus to get rid of the 'noise', or variables completely unrelated to our outcome. Next, we drop all variables with coefficient value zero in the lasso model. We then run a ridge regression model, with the remaining variables as independent factors and IPV help-seeking as the outcome. The results from this ridge regression model constituted the findings from the first round of the ITA process. The coefficient values of all variables were sorted from high to low, and the values were then plotted to identify the point of maximum curvature (using kneed library in Python). Similar to the prior study using this approach, the variables with coefficient values higher than the knee point, or the point where the coefficient curve becomes flat, were extracted as the relevant correlates of the outcome. Two researchers reviewed the results from the ridge regression model separately, and coded the variables into different themes. A theme referred to a group of variables that were related to each other in terms of topical similarity. For example, variables 'social class', 'religion', and 'age' could be categorized as one theme- socio-demographics. We observed over 95% agreement between the two coders for this process of qualitative thematic categorization (measured as percentage of variables coded as same themes by the coders). Once the thematic categorization was completed, we proceeded to the next round of the ITA process. We identified the theme which had the maximum variance, i.e., the theme with the variable that has the highest coefficient value. All variables from this theme were dropped from the dataset, and the process of lasso, followed by ridge and qualitative coding was carried out. We continued to repeat this process until no new themes were identified for three consecutive rounds, or no new variables identified for any consecutive round. For each round of ITA, the machine learning models were tested for accuracy and error rates. The resulting output from this process was thus a group of themes or topics that are correlated to IPV help-seeking from anyone." 2) In the “results” section, it is not clear that how the results were obtained from the methods based on the analysis. What’s results were based on LASSO, L-1, L-2 and ITA applied? Thank you for this comment. The section on the Iterative thematic analysis (ITA) clarifies and elaborates the different steps through which the results were identified. The final results were obtained after an iterative process of running the lasso model, followed by an L2 regression model, and a qualitative coding of the list of variables with coefficient value higher than a specific threshold (the knee point, explained in the prior response). The response to the prior comment includes the description of these steps in detail. 3) More importantly, λ and k values were not reported in the results section. AUC and other model measure metrics were not reported or event mentioned. Thank you for the comment. We used 5-fold cross validation (k=5) for our analysis. The λ values from the validation for the multiple models of L1/lasso and L2, ranged from 1 to 10^6. The Results section includes a figure that indicates the accuracy estimates, as measured by AUC, and the balanced error rates for each round of the ITA. 4) One of the important features based on ML is to rank the importance of the variables after variable selection, but the paper did not even touch the work. Thank you for the comment. In our analysis, we used an iterative approach where we ran lasso/L1 followed by a L2 regression model. The L2 model was run with those variables that had a non-zero coefficient value from lasso- a measure used to get rid of 'noise' or irrelevant variables. The results from the ridge models were then ranked based on the coefficient values. We used the knee point of the coefficient values as the threshold to select relevant variables for the next steps of the ITA process used in our study. The knee point was calculated based on the mathematical definition of curvature for a continuous variable. For any continuous function f, there is a standard closed-form that defines its curvature at any point as a function of its first and second derivative. And, the maximum curvature of this function indicates the levelling off effect. Thus, beyond the knee point, or the point of maximum curvature, the curve for the function becomes flat. We sorted all the coefficient values of the variables from the L2 regression models from high to low. These values were then plotted and assessed to identify the point of maximum curvature or knee point. The variables with coefficient value higher than the knee point were selected as our relevant results. These details have been added to the Materials and Methods section. Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0262538.r002
28 Dec 2021 Decision Letter - Yukiko Washio, Editor Help Seeking Behavior by Women Experiencing Intimate Partner Violence in India: A Machine Learning Approach to Identifying Risk Factors PONE-D-21-21691R1 Dear Dr. Dehingia, 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, Yukiko Washio, Ph.D. 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 #2: All comments have been addressed Reviewer #3: 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 #2: Yes Reviewer #3: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #2: 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 #2: Yes Reviewer #3: 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 #2: 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 #2: The authors have adequately addressed my comments and suggestions raised in a previous round of review. I think that this manuscript is now acceptable for publication. Reviewer #3: Based on the original reviewers' comments and feedback and the authors' responses, it seems like all comments were adequately addressed. Overall this paper was really interesting to read and presenting an interesting take on machine learning. ****** 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 #2: No Reviewer #3: No https://doi.org/10.1371/journal.pone.0262538.r003
Formally Accepted
24 Jan 2022 Acceptance Letter - Yukiko Washio, Editor PONE-D-21-21691R1 Help Seeking Behavior by Women Experiencing Intimate Partner Violence in India: A Machine Learning Approach to Identifying Risk Factors Dear Dr. Dehingia: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. 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. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Yukiko Washio Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0262538.r004

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .