Machine learning model based on radiomics features for AO/OTA classification of pelvic fractures on pelvic radiographs

Jun Young Park; Seung Hwan Lee; Young Jae Kim; Kwang Gi Kim; Gil Jae Lee

doi:10.1371/journal.pone.0304350

Peer Review History

Original SubmissionJanuary 7, 2024
8 Mar 2024 Decision Letter - Barry Kweh, Editor PONE-D-23-42660Machine Learning Model Based on Radiomics Features for AO/OTA Classification of Pelvic Fractures on Pelvic RadiographsPLOS ONE Dear Dr. Kim, 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 Apr 22 2024 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, Barry Kweh 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. Thank you for stating the following financial disclosure: "This work was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711196789, RS-2023-00252804)." 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. 4. Thank you for stating the following in the Acknowledgments Section of your manuscript: "This work was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711196789, RS-2023-00252804)." 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 was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711196789, RS-2023-00252804)." Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 5. In the online submission form, you indicated that the data used to support the findings of this study are available upon request from the corresponding authors. All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. Uploaded as supplementary information. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval. Additional Editor Comments: A study which attempts to use machine-learning in the radionomic classification of pelvic fractures. The authors have utilized X-Rays to classify fractures rather than computed topography which should be justified. A broader review of the literature in a tabulated and written format of using fracture line and morphological features would also be useful to the audience. [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: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: 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: No Reviewer #2: 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 ****** 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 paper titled "Machine Learning Model Based on Radiomics Features for AO/OTA Classification of Pelvic Fractures on Pelvic Radiographs" presents a study aimed at developing a machine-learning algorithm based on radiomics for quick diagnosis and classification of pelvic fractures in X-ray images. The study involved analyzing pelvic anteroposterior radiographs from 990 adults with pelvic fractures and 200 normal subjects. A total of 93 features were extracted and analyzed using various machine learning models and feature selection methods. I have a few concerns The authors state the aim is to develop radiomics-based machine-learning algorithm to rapidly diagnose fractures in pelvic X- ray images and classify pelvic instability. The results of the study do not support this aim. 2. How was the ROI defined, the extent and the software used? 3. There are 3 classes described and ROC is provided as the metric for model performance. Are the results supporting One vs Rest or One vs One class? 4. How was the radiomics models better than the clinician's decision? 5. Please do a thorough check before submission that only tables and figures included are cited appropriately. Reviewer #2: This article describes the performance of machine learning models using radiomic features in classifying pelvic fractures on radiographs. The model using RFE method of feature selection and SVM classifier performed with the highest AUC of 0.75 +/- 0.06. Most models using RFE feature selection performed with AUC between 0.73 and 0.74, other methods of feature selection performed with variable AUC between 0.59 and 0.73. The importance values of features were also described. It is the first study to evaluate the performance of machine learning models in classification of pelvic fractures and describe the significant radiomics features. Other studies have used machine learning models to classify hip fractures with high accuracy. ****** 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.0304350.r001
Revision 1
22 Apr 2024 Author Response Editor 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. Answer As the editor mentioned, it appears that the format of this paper did not fit the requirements defined by PLOS ONE. Therefore, the authors revised and supplemented the overall format of the paper by referring to the PDF files mentioned by the editor in the email. Thanks to the editor's comments, the completeness of the paper has improved. Thank you. 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. Answer As the editor mentioned, we believe there was a lack of submissions supporting the results of this study. Evidence that supports research results is essential and can improve the reliability of experimental results. Therefore, the authors uploaded the entire code and virtual environment used in the experiment to GitHub. Please refer to the path below. https://github.com/user-dynamite/biomedical-engineering/tree/master 3. Thank you for stating the following financial disclosure: "This work was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711196789, RS-2023-00252804)." 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. Answer Thank you for providing funding and for carefully reviewing and confirming the details of the paper. The funders who provided funding for this paper had no role in the preparation of the manuscript. A description of the role of the funder was included in the cover letter. Please confirm. 4. Thank you for stating the following in the Acknowledgments Section of your manuscript: "This work was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711196789, RS-2023-00252804)." 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 was supported by the Korea Medical Device Development Fund grant funded by the Korea government (the Ministry of Science and ICT, the Ministry of Trade, Industry and Energy, the Ministry of Health & Welfare, the Ministry of Food and Drug Safety) (Project Number: 1711196789, RS-2023-00252804)." Please include your amended statements within your cover letter; we will change the online submission form on your behalf. Answer We are fully aware of the failure to carefully check the details of the funds statement in the PLOS ONE form. Thanks to the Editor's comments, we were able to check and review the matter in detail. All text related to funds was deleted from the manuscript. The contents of the fund statement were revised and supplemented and written in the cover letter. 5. In the online submission form, you indicated that the data used to support the findings of this study are available upon request from the corresponding authors. All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. Uploaded as supplementary information. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval. Answer Sharing data used in research, such as the editor's comments, increases the possibility of further research and future development. This research team is fully aware of the content and believes it is important. However, it is impossible for Gachon University Gil Hospital, which received the patient data, to disclose the patient data in a public repository. If you contact the corresponding author individually, the corresponding author can share data personally with institutional approval. We ask for the Editor’s generous understanding regarding this content. Reviewer 1 The paper titled "Machine Learning Model Based on Radiomics Features for AO/OTA Classification of Pelvic Fractures on Pelvic Radiographs" presents a study aimed at developing a machine-learning algorithm based on radiomics for quick diagnosis and classification of pelvic fractures in X-ray images. The study involved analyzing pelvic anteroposterior radiographs from 990 adults with pelvic fractures and 200 normal subjects. A total of 93 features were extracted and analyzed using various machine learning models and feature selection methods. 1. The authors state the aim is to develop radiomics-based machine-learning algorithm to rapidly diagnose fractures in pelvic X- ray images and classify pelvic instability. The results of the study do not support this aim. Answer As the reviewer commented, this paper developed a radiomics-based machine learning learning model and achieved a performance of about AUC 0.75. In this paper, pelvic instability was expressed in quantitative numbers based on the features selected as important. Recent studies have achieved AO/OTA pelvic fracture classification performance of up to Sensitivity 75.7%, Precision 83.6%, and Accuracy 85.0% using ResNeXt50, RNN, and 3D-ResNet50 in CT images [1]. By using Inception-V3 on in this way, the type of fracture was classified by learning a deep learning model, but it was not expressed in quantitative numbers. They did not perform any better than medical specialists. The field is developing artificial intelligence models in various aspects to assist medical professionals in their diagnosis. The authors also believe that if additional research is conducted based on the selected characteristics, it will be able to assist medical professionals in their diagnosis. Thank you for mentioning important points to improve the completeness of this paper. References [1] Dreizin, David, et al. "An automated deep learning method for tile AO/OTA pelvic fracture severity grading from trauma whole-body CT." Journal of Digital Imaging 34 (2021): 53-65. [2] Lee, Changhwan, et al. "Classification of femur fracture in pelvic X-ray images using meta-learned deep neural network." Scientific reports 10.1 (2020): 13694. 2. How was the ROI defined, the extent and the software used? Answer As the reviewer commented, I felt that this paper lacked mention of this topic. In this study, the ROI corresponding to the pelvic region was defined by referring to the findings of pelvic AP X-rays and CT images by a trauma surgeon with more than 10 years of experience. Additionally, the defined ROI includes the left and right ilium, pubic bone, and ischium. The software used to obtain ROI was the commercial software AVIEW (Corelinesoft, Seoul, Republic of Korea). This content has also been added to the paper. Thank you for leaving a comment to improve the completeness of this paper. Modified and supplemented contents - Page 5, line 3~7 3. There are 3 classes described and ROC is provided as the metric for model performance. Are the results supporting One vs Rest or One vs One class? Answer This paper classified the models into four classes (Type A, Type B, Type C, Normal) and compared the performance between models by obtaining AUC values from the ROC curve. The results of this study support One vs Rest. One vs Rest turns a multi-class problem into several binary classification problems, and a binary classifier is learned by treating one class as 1 and the remaining classes as 0. This method can achieve higher performance than One vs One. In the case of One vs One, the data is split into two different classes and trained with a binary classifier. This means that as the number of classes increases, the classifier increases and becomes more sensitive to imbalances between classes. We chose One vs Rest to achieve higher performance with fewer classifiers. Added information about using One vs Rest. Thank you for improving the completeness of this paper by leaving a comment regarding the shortcomings of this paper. Modified and supplemented contents - Page 7, line 24~26 4. How was the radiomics models better than the clinician's decision? Answer This paper conducted a study to classify pelvic instability using a model learned based on radiomics. The results provided in this paper do not compare or analyze the decisions of medical experts and the model's predicted results. Conventional medical specialists had standards for classifying pelvic instability, but there were no quantitative figures for instability classes. In the results of this paper, 10 radiomics features were selected as relatively important features, as shown in Figure 8. Through the results of the study, we were able to obtain quantitative figures for the class. We also found that the research results were highly reproducible. If we study multi-center data and conduct additional research in the future, we believe it will be at a level that can assist medical specialists in their diagnosis. 5. Please do a thorough check before submission that only tables and figures included are cited appropriately. Answer All tables and figures included in this paper are cited to support the content of the paper. Figure 1 is a pelvic AP X-ray image and an ROI mask image designating the pelvic region. Figure 2 shows an actual AP X-ray image of the pelvis where the pelvic area is not clearly visible due to organs or gas. These cases were excluded because they could be a hindrance when extracting radiomics features. Figure 3 is the result of performing the Histogram Equalization algorithm to make somewhat blurry pelvic AP X-ray images clear. The horizontal axis of the graph below in Figure 3 represents the contrast value of the image, and the vertical axis represents the frequency with which that contrast value is used. Figure 4 shows a flow chart for extracting radiomics features of the pelvic region from pelvic AP X-ray images. A total of 93 radiomics features were extracted. Figure 5 includes the statistical analysis of the machine learning model prediction results from the feature selection method algorithm after radiomics feature extraction. Figure 6 is a Heatmap graph obtained by obtaining the AUC of each combination using 7 machine learning models and 4 feature selection method algorithms. You can check the AUC of the combination in color and number at once. Figure 7 is the ROC curve for each combination of RFE feature selection method and each machine learning model. The ROC curve was obtained by selecting only the RFE feature selection method because RFE showed relatively high performance compared to other feature selection methods. Figure 8 shows the average feature importance value of each machine learning model combination for the 10 features extracted using the RFE feature selection method. Figure 9 shows the feature importance values of each machine learning model combination for the 10 features extracted using the RFE feature selection method. Table 1 shows pelvic AP X-ray images obtained from 2015 to 2020 by type. Table 2 is the distribution of Train set and Test set for each type. There are a total of 11 figures and tables, which may seem a bit large, but they are all written to support the content of the paper. Thanks to the reviewer's comments, we were able to thoroughly check and review the figures and tables cited in the paper. The completeness of the paper has been improved thanks to the reviewer's comments. Thank you. Reviewer 2 This article describes the performance of machine learning models using radiomic features in classifying pelvic fractures on radiographs. The model using RFE method of feature selection and SVM classifier performed with the highest AUC of 0.75 +/- 0.06. Most models using RFE feature selection performed with AUC between 0.73 and 0.74, other methods of feature selection performed with variable AUC between 0.59 and 0.73. The importance values of features were also described. It is the first study to evaluate the performance of machine learning models in classification of pelvic fractures and describe the significant radiomics features. Other studies have used machine learning models to classify hip fractures with high accuracy. Answer First, thank you very much for leaving a positive comment on this paper. In this paper, we developed a radiomics-based machine learning model to classify pelvic instability. Using the prediction results, performance was evaluated and important radiomics characteristics were analyzed and explained. As the reviewer commented, our researchers believe that this is the first study to classify pelvic instability based on radiomics features. I think it is meaningful as a first-of-its-kind study, and I think the extracted important radiomics features can be used as biomarkers in the future. Thank you. Attachments Attachment Submitted filename: Response to Reviewers.pdf https://doi.org/10.1371/journal.pone.0304350.r002
25 Apr 2024 Decision Letter - Barry Kweh, Editor PONE-D-23-42660R1Machine learning model based on radiomics features for AO/OTA classification of pelvic fractures on pelvic radiographs.PLOS ONE Dear Dr. Kim, 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 Jun 09 2024 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, Barry Kweh 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. Additional Editor Comments: A well written article which has clarified its methodology in response to the reviewers. A further refinement is a broader discussion of the literature and a tabulated as well as written summary of existing radiomic features and key pelvic fracture findings should be provided to authors to further strengthen the authors' findings. [Note: HTML markup is below. Please do not edit.] [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.0304350.r003
Revision 2
7 May 2024 Author Response Journal Requirements 1. 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. Answer It is important to write references completely and accurately as required by the journal. We, the authors, fully agree with the journal's requirements, as the references are what support the research in the paper. We have checked and reviewed them thoroughly. We have reviewed the references of the papers and none of them have been retracted. Thank you for your comments to improve the quality of the paper. Additional Editor Comments 1. A well written article which has clarified its methodology in response to the reviewers. A further refinement is a broader discussion of the literature and a tabulated as well as written summary of existing radiomic features and key pelvic fracture findings should be provided to authors to further strengthen the authors' findings. Answer First, thank you for your positive comments on this paper. Thanks to the editors and reviewers, the quality of the paper seems to have improved a lot. Additionally, as the editor comment, a more extensive discussion of the paper and existing radiomics features and findings of major pelvic fractures would have strengthened the results. We completely agree with the editor's opinion. We have included a full discussion of the paper and a summarized version of the broader results in the final paragraph of Results and Discussion. We believe that it is essential to define the presentation of preexisting pelvic fractures. Pelvic fracture classification was added to the data section of the Materials and Methods section, as shown in Table 1. Because this is the basis from which we got our data. Table 1 is based on reference [12]. However, in our review, previous studies have not found radiographic features to classify pelvic fracture type. Thank you for mentioning important points to improve the paper. Modified and supplemented contents - Page 11, line 25~32 / Page 4, line 16~19 Attachments Attachment Submitted filename: Response to Reviewers.pdf https://doi.org/10.1371/journal.pone.0304350.r004
10 May 2024 Decision Letter - Barry Kweh, Editor Machine learning model based on radiomics features for AO/OTA classification of pelvic fractures on pelvic radiographs. PONE-D-23-42660R2 Dear Dr. Kim, 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 will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, 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, Barry Kweh Academic Editor PLOS ONE Additional Editor Comments (optional): An interesting article based on the radiomics of pelvic fractures. The discussion has been expanded and tables addressed. Reviewers' comments: https://doi.org/10.1371/journal.pone.0304350.r005
Formally Accepted
17 May 2024 Acceptance Letter - Barry Kweh, Editor PONE-D-23-42660R2 PLOS ONE Dear Dr. Kim, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, 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 customercare@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. Barry Kweh Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0304350.r006

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 .