PONE-D-22-31964Machine learning models of healthcare expenditures predicting mortality: A cohort study of spousal bereaved Danish individualsPLOS ONE

Dear Dr. Katsiferis,

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.

==============================

ACADEMIC EDITOR:This manuscript provides an in depth analysis to investigate if temporal patterns of healthcare expenditures can improve the predictive performance for mortality for individuals who loose their spouses. Overall, results indicate a pattern where healthcare expenditures improved mortality predictions the most. The following comments might help the authors with some clarity on the manuscript:

1. What method of adding predictors to the model was used?

2. How was the affluence index created?

3. Cite the Brier score and explain it as well

4. Why was it significant/important to stratify the analysis by gender

5. P-values should be included in the tables 2 and 3 or any other measure of statistical significance to observe the statistical difference between the groups. Please ensure that your decision is justified on PLOS ONE’s publication criteria and not, for example, on novelty or perceived impact.

For Lab, Study and Registered Report Protocols: These article types are not expected to include results but may include pilot data. 

==============================

Please submit your revised manuscript by Jul 08 2023 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,

Amna Tariq, PhD

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 in the Acknowledgments Section of your manuscript:

“This work is supported by The Novo Nordisk Foundation (https://novonordiskfonden.dk/) Challenge Programme for the project Harnessing the Power of Big Data to Address the Societal Challenge of Aging (NNF17OC0027812). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.”

We note that you have provided funding information that is not currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form.

Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows:

“This work is supported by The Novo Nordisk Foundation (https://novonordiskfonden.dk/) Challenge Programme for the project Harnessing the Power of Big Data to Address the Societal Challenge of Aging (NNF17OC0027812). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.”

Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

3. 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. 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: Yes

Reviewer #3: Yes

**********

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

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

**********

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: Please see the comments.

• Conclusion should be clearly and concisely answered the main research question

• Briefly and precisely refer to the summary of the important results

• What was the of participation rate in the present study?

• Table 1: provide a p-value column for comparison of variables among gender subgroup

• Please explain more in detail about Affluence Index Group in methods section also insert a source as citation

• Table 1: Distribution of socio-demographic variables of the study sample should be report by Test and Trained samples

• Table 2: the column of p-value should be added.

Reviewer #2: The authors have presented a well-written and concise study of predicting mortality using machine learning models with features such as age, sex, sociodemographic factors, and healthcare expenditures. The authors conclude that adding healthcare expenditures as features to age and sex improves mortality predictability more than adding sociodemographic factors. During my review of the paper, I highlighted the following areas for improvement -

1. The authors have presented confidence intervals for AUC and Brier scores. From my understanding of the methodology, the authors have only 1 holdout set with 25% of the data. In this case, how are the confidence intervals computed since there would be only one AUC value and Brier score per model for the holdout set?

2. It would be helpful to add whether the holdout set was created using a stratified train-test split given the label imbalance (~6% mortality rate).

3. AUC is a good metric to measure model performance when the labels are fairly balanced. However, in this case, the large proportion of negative labels can result in very low false positive rates, thus affecting the AUC calculations. The author’s conclusions would be bolstered by including the comparisons of average precision (which is the area under the precision-recall curve) across the different models due to the imbalanced labels.

4. The authors have presented true positive rate in Fig 5 but did not provide the false negative rates of the models. Since the goal is to predict mortality, it would be suitable to understand the models’ performance on false negative rates. A model with high false negative rate would incorrectly predict no mortality for individuals with observed mortality and hence may be less suitable as a decision support tool.

5. Line 306 - It was not clear how raw weekly expenditures were used as features. For example, were the feature values equal to expenditure in each week starting on Jan 1, 2011? In this case, what were the feature values after an individual’s death?

6. Fig 4 - The definitions of observed mortality proportion and predicted 1-year mortality risk could not be ascertained. Please describe the axes, similar to Fig 5.

7. Line 122 - duplicated “date of”

Reviewer #3: The manuscript appears to be technically sound and the data presented support the conclusions drawn by the authors. The study is well-designed and the analysis methods used are appropriate. The authors provide a detailed description of the data and their methods, as well as the results obtained, which are presented in a clear and concise manner. The results are discussed in the context of the existing literature, and the limitations of the study are acknowledged. Overall, the manuscript appears to be a well-executed study that provides important insights into the prediction of all-cause mortality following spousal bereavement.

The research text describes a study aimed at comparing prognostic models of all-cause mortality risk based on healthcare expenditures data. The study uses Danish population registers data and analyzes healthcare expenditures of Danish citizens aged 65 years and above, who had been residents of Denmark for at least 5 years before their date of death, from January 1st, 2011, to December 31st, 2016. The study population is restricted to those who suffered spousal bereavement during the time window 2013-2016. The authors computed various Dynamic Indicator of Overall Risk (DIORs) based on different properties of the underlying dynamic process of healthcare expenditures. The DIORs were used as predictors in XGBoost tree-based models to predict all-cause mortality risk.

The research provides sufficient information on the study population, data sources, and analytical methods. The use of national population registers to obtain a large study population with a unique personal identifier for each citizen is a strength of the study.

The section describing healthcare expenditures and knowledge discovery provides a clear explanation of the computation of the DIORs.

The section describing the statistical methods is well-written and provides clear information on the XGBoost tree-based algorithm, the selection of hyperparameters, and the assessment of the models. The use of a 5-fold cross-validated dataset of the initial training set and a holdout set to validate the models' generalization ability is a strength of the study.

Overall, the study provides a clear description of the methods used to analyze the healthcare expenditures data and predict all-cause mortality risk. However, the lack of presentation of mathematical formulas for DIORs is a potential gap.

**********

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: Vineet Gupta

**********

[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.

Machine learning models of healthcare expenditures predicting mortality: A cohort study of spousal bereaved Danish individuals

PONE-D-22-31964R1

Dear Dr. Katsiferis,

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,

Amna Tariq, PhD

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments: