BACK-to-MOVE: Machine learning and computer vision model automating clinical classification of non-specific low back pain for personalised management

Thomas Hartley; Yulia Hicks; Jennifer L. Davies; Dario Cazzola; Liba Sheeran

doi:10.1371/journal.pone.0302899

Peer Review History

Original SubmissionSeptember 12, 2023
20 Feb 2024 Decision Letter - Adrian Pranata, Editor PONE-D-23-28397BACK-to-MOVE: Machine Learning and Computer Vision Model Automating Clinical Classification of Non-Specific Low Back Pain for Personalised Management.PLOS ONE Dear Dr. Sheeran, 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 05 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, Adrian Pranata, 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. Note from Emily Chenette, Editor in Chief of PLOS ONE, and Iain Hrynaszkiewicz, Director of Open Research Solutions at PLOS: Did you know that depositing data in a repository is associated with up to a 25% citation advantage (https://doi.org/10.1371/journal.pone.0230416)? If you’ve not already done so, consider depositing your raw data in a repository to ensure your work is read, appreciated and cited by the largest possible audience. You’ll also earn an Accessible Data icon on your published paper if you deposit your data in any participating repository (https://plos.org/open-science/open-data/#accessible-data). 3. 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. 4. We note that you have indicated that there are restrictions to data sharing for this study. 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. Before we proceed with your manuscript, 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 identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). 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 to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible. We will update your Data Availability statement on your behalf to reflect the information you provide. 5. When completing the data availability statement of the submission form, you indicated that you will make your data available on acceptance. We strongly recommend all authors decide on a data sharing plan before acceptance, as the process can be lengthy and hold up publication timelines. Please note that, though access restrictions are acceptable now, your entire data will need to be made freely accessible if your manuscript is accepted for publication. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If you are unable to adhere to our open data policy, please kindly revise your statement to explain your reasoning and we will seek the editor's input on an exemption. Please be assured that, once you have provided your new statement, the assessment of your exemption will not hold up the peer review process. Additional Editor Comments: Thank you for your patience with the review process. This study is a good step forward in the assessment of movement in people with low back pain. Please address the reviewers' comments on the technical aspect of the study's machine learning algorithm. Thank you for your submission. [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: No 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 has few issues that need further clarifications as follows: - It is not clear how to validate or ensure data MI and MCI at the beginning before this data fed to feature extraction process. - The structure of the CNN is not very clear such is the dimension of the input and output. - Table 5 shows set of optimal input feature yielding the highest classification performance. Instead of using 'X' the actual metric such as classification should be used. Moreover, how to ensure the value is optimal. Also, few input features such as variance, minimal (full spine flexion angle), VAS, ODI, TSK PCS, PSEQ and CSQ do not show as optimal feature. This need to be clarified. - Since the paper proposed using CNN, there is no information about the training of the CNN; how to avoid overfitting issue, how to ensure each of the training parameter of the CNN is optimal. - Please explore whether the result is statistically significant. Reviewer #2: This study aimed to develop and evaluate a machine learning model called "BACK-to-MOVE" for classifying non-specific low back pain (NSLBP) using standard video data, spinal motion data, and patient-reported outcome measures. The model utilized a Convolutional Neural Network architecture for effective pose estimation from video data. Results showed that the "BACK-to-MOVE" model successfully differentiated motor control impairment (MCI) and movement impairment (MI) classes with 93.98% accuracy, demonstrating strong criterion validity. The study concludes that automated classification of NSLBP using computer vision and machine learning could expedite personalized NSLBP rehabilitation management, potentially benefiting patients and healthcare services. Experiment: lack comparison among multiple CNNs performance on human pose detection (CrowPose, DensePose, PoseNet, UniPose, HigherHRNet), better provide a simple comparison. Discussion: Table 6, the model performance decreases when adding PROMs, this requires more in-depth discussion and ablation study to illustrate that whether this is caused by model. That is whether design a good model the results will change. Minor error: Line 76: MDC classification -> MDC, since C means classification. The label of x and y-axis in Fig. 3 are too vague. ****** 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.0302899.r001
Revision 1
4 Apr 2024 Author Response To PLOS1 Editor: 1. We note that you have indicated that there are restrictions to data sharing for this study. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. Our response: Data sharing: Ethical restrictions exist related to the nature of the data (videos) containing potentially identifying and sensitive information (e.g. tattoos, birth marks, sex, ethnicity, unique movement characteristics etc) with no possibility to de-identify, add noise, or block portions of the dataset and still preserve the usefulness of the dataset to replicate the study results. Unfortunately, our institution (Cardiff University) does not have an established point of contact to field external requests for access to sensitive data. Reviewer #1: 1. It is not clear how to validate or ensure data MI and MCI at the beginning before this data fed to feature extraction process. MI/MCI classification is described in methods (clinical classification process lines 147-158). In short, MI/MCI was performed using clinical judgement-based MDC method, which is the only available method and considered as the gold standard. In our study, two MDC-trained expert clinicians independently classified the participants into MI and MCI following a process shown to have above 90% inter-examiner agreement [reference 15 and 27 in reference list]. We added additional detail to clarify the independent confirmation by the 2 experts (line 157). 2. The structure of the CNN is not very clear such is the dimension of the input and output. The structure of the HigherHRNet CNN, along with a detailed comparative analysis of HigherHRNet performance with that of alternative CNNs for human pose estimation and an ablation study, has been described previously and is referenced in our study [reference 47]. As the architecture of HigherHRNet is not the subject of this study, we limit ourselves to citing this work in our article. Nonetheless, to ensure clarity we added a sentence (line 199-201) referring readers to this detail. 3. Table 5 shows set of optimal input feature yielding the highest classification performance. Instead of using 'X' the actual metric such as classification should be used Moreover, how to ensure the value is optimal. Also, few input features such as variance, minimal (full spine flexion angle), VAS, ODI, TSK PCS, PSEQ and CSQ do not show as optimal feature. This need to be clarified. The features were optimal in the sense of producing the highest F1 measure value among all possible permutations of features, so using a numerical value against a single feature would not be possible as it is a metric for a feature subset. We added a sentence in the article (line 345-6) and a legend to Table 5 (line 387) to clarify the meaning. 4. Since the paper proposed using CNN, there is no information about the training of the CNN; how to avoid overfitting issue, how to ensure each of the training parameter of the CNN is optimal. As already detailed in the manuscript (line 220-24) we utilised a CNN model (the selection of which is covered in our response to your comment 2 above) that was pre-trained on the MS-COCO dataset with fine-tuning not pursued given its superior performance and to prevent excessive overfitting. 5. Please explore whether the result is statistically significant. Thank you for your comment. The aim of this study was to test the performance of the proposed classifier against a clinical judgement classification using MDC method as the ‘gold standard’. The conventional method for this form of performance evaluation is a calculation of accuracy, sensitivity and specificity, and F1-measure (Taha et al 2015, referenced in manuscript). There is no other model against which our proposed model could be benchmarked using statistical testing. However, to respond to your question, we explored the statistical significance of our results following a method outlined by Combrisson et al 2015 [reference 57 added], which showed that our results would reach statistical significance (p-value <0.001) for accuracy of 87.5% and higher. We added this detail and a reference in the article (added lines in methods 350-364, and results 405-407). Reviewer #2: 1. Experiment: lack comparison among multiple CNNs performance on human pose detection (CrowPose, DensePose, PoseNet, UniPose, HigherHRNet), better provide a simple comparison. Thank you for your comment. A detailed comparative analysis of the performance of HigherHRNet with that of alternative CNNs for human pose estimation and an ablation study is described in detail in reference [47]. As CNNs performance comparison was not the aim of this study, we limit ourselves to referencing it [47] in our article. Nonetheless, to ensure clarity we added a sentence (line 199-201) referring readers to this detail. 2. Discussion: Table 6, the model performance decreases when adding PROMs, this requires more in-depth discussion and ablation study to illustrate that whether this is caused by model. That is whether design a good model the results will change. Thank you. In response to your comment, further text has been added to elaborate on the possible reasons for the limited discriminate ability of PROMs (line 463-70). In summary, PROMs in this study measure levels of pain intensity, disability, and psychological distress that vary according to different levels of pain intensity and duration. As participants with LBP > 3 months with pain intensity not precluding them from performing the movements were included, PROMs scores were unlikely to vary across the subgroups. Nevertheless, given the multi-factorial nature of LBP, we felt it was still important to explore any such variation as highlighted in the discussion section. 3. Minor error: Line 76: MDC classification -> MDC, since C means classification. Thank you, ‘classification’ has now been removed. The label of x and y-axis in Fig. 3 are too vague. Figure 3 has been re-generated with Y axis titled as ‘Base of the neck vertical coordinate (pixels) and X axis titled ‘Base of the neck antero-posterior coordinate (pixels) for improved clarity. Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0302899.r002
16 Apr 2024 Decision Letter - Adrian Pranata, Editor BACK-to-MOVE: Machine Learning and Computer Vision Model Automating Clinical Classification of Non-Specific Low Back Pain for Personalised Management. PONE-D-23-28397R1 Dear Dr. Sheeran, 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, Adrian Pranata, Ph.D Academic Editor PLOS ONE Additional Editor Comments (optional): Dear Liba, Thank you for addressing the comments from the reviewers and your patience. Research using AI in low back pain clinical management is scant. This study will add to the emerging area of AI for movement assessment and ultimately, management of people with low back pain. Thank you for your contribution in this important area of research. Kind regards, Adrian Reviewers' comments: https://doi.org/10.1371/journal.pone.0302899.r003
Formally Accepted
29 Apr 2024 Acceptance Letter - Adrian Pranata, Editor PONE-D-23-28397R1 PLOS ONE Dear Dr. Sheeran, 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. Adrian Pranata Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0302899.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 .