Design optimization of high-sensitivity PCF-SPR biosensor using machine learning and explainable AI

Mst. Rokeya Khatun; Md. Saiful Islam

doi:10.1371/journal.pone.0330944

Peer Review History

Original SubmissionMay 27, 2025
18 Jun 2025 Decision Letter - Yuan-Fong Chou Chau, Editor Dear Dr. Khatun, 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 Aug 02 2025 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. 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 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, Yuan-Fong Chou Chau 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, we expect all author-generated code to 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. 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. 4. 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? Reviewer #1: Yes 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 Reviewer #1: Yes Reviewer #2: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English??> Reviewer #1: Yes Reviewer #2: Yes ****** Reviewer #1: Comments to Authors Technical 1. Explain how the integration of machine learning regression techniques contributes to the optical property prediction in the proposed PCF-SPR biosensor and with the machine leaning approaches can you be precise in finalizing the final sensor parameters. 2. I suggest presents a detail about various AI based techniques that can be used in the sensor optimization. Follow the following article to presents details of various AI based techniques used in sensor optimization and cite the article. "Finite Element Method-Based Modeling of a Novel Square Photonic Crystal Fiber Surface Plasmon Resonance Sensor with a Au–TiO2 Interface and the Relevance of Artificial Intelligence Techniques in Sensor Optimization" 3. Discuss the significance of the broad RI detection range (1.31 to 1.42) in the context of biosensing applications, justify the RI range since any RI below 1.33 is considered superficial, I suggest add a sentence like claiming theoretical analysis. 4. How does the use of SHAP (SHapley Additive exPlanations) enhance the interpretability of the ML model used for sensor design optimization? 5. Analyze how the achieved performance metrics such as wavelength sensitivity and figure of merit reflect the sensor's capability for high-precision detection. 6. Are these any sensing parameters which cannot be predicted using ML models, and why, and how do these predictions benefit the overall sensor design process? 7. Critically evaluate the influence of design parameters like Au thickness and pitch on the sensor's performance, as revealed by the SHAP analysis. 8. Compare the advantages of the hybrid design approach combining conventional methods and ML/XAI with traditional sensor optimization strategies in terms of efficiency and computational cost. Some prominent sensor models having merger of IMD and EMD, merger of Quasi D shaped with EMD approach etc need to be included in the comparison section of the article. Add a short paragraph suggesting future application of the sensor for various applications. Following are suggested references including these features. https://doi.org/10.1007/s11468-024-02400-7 https://doi.org/10.1007/s11082-023-05016-z https://doi.org/10.1016/j.ijleo.2022.169892 https://doi.org/10.1016/j.measurement.2021.110513 9. Justify the suitability of the proposed biosensor for medical diagnostics and chemical sensing, particularly in the context of cancer cell detection, refer the following reference. https://doi.org/10.3390/bios15050292 Reviewer #2: Review for Authors 1. Explain how machine learning and artificial intelligence-based techniques can be used in the sensor design optimization and design. I suggest go through the following article and refer to various techniques used in the sensor modelling cite them too. https://doi.org/10.3390/photonics12060565 https://doi.org/10.3390/bios15050292 2. The SHAP (SHapley Additive exPlanations) technique do not enhance the sensor detection capability, it provides more results to conclude, these models are used to analyze the sensor for design optimization purposes only. 3. In Figure 3 and section 2.2 can you see the in the text you have used D1, D2, D3 but in the diagram d1, d2, and where is d3, thus correct the notation. These create confusion. 4. Provide reference to Eq 1, 2, 4, 7, 9 etc, without proper reference it seems like you have developed the equation. 5. In Fig 12,13, 14 can you increase the font size of the x- and y- labels of the figure. 6. Fig 16 don’t look correct, format it well, format all image well increase the font size of the x-label and y-label for all figures. 7. Mention the applications of the proposed biosensor in real time from medical to environment application. ****** 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: Yes: Dr. Ayushman Ramola, Ariel University, Israel ******** [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 Attachments Attachment Submitted filename: Review-25-28444.docx Attachment Submitted filename: PONE D-25 Comments.docx https://doi.org/10.1371/journal.pone.0330944.r001
Revision 1
5 Aug 2025 Author Response Responses to reviewers: The authors would like to thank the reviewers for their precious time and valuable suggestions. We have carefully addressed and updated all the changes in the original manuscript. The following section provides point-by-point responses corresponding to all review comments. #Reviewer 1 1. Explain how the integration of machine learning regression techniques contributes to the optical property prediction in the proposed PCF-SPR biosensor and with the machine leaning approaches can you be precise in finalizing the final sensor parameters. Response: We have revised the manuscript to provide a more detailed explanation of how machine learning (ML) regression techniques contribute to the prediction of optical properties in the proposed PCF-SPR biosensor. A new paragraph has been added in the Section 2.6 (ML Algorithms). 2. I suggest presents a detail about various AI based techniques that can be used in the sensor optimization. Follow the following article to presents details of various AI based techniques used in sensor optimization and cite the article. "Finite Element Method-Based Modeling of a Novel Square Photonic Crystal Fiber Surface Plasmon Resonance Sensor with a Au–TiO2 Interface and the Relevance of Artificial Intelligence Techniques in Sensor Optimization" Response: In response, we have added a detailed discussion on various AI-based techniques used in sensor optimization, including Artificial Neural Networks (ANNs), classical machine learning models, ensemble methods, and deep learning approaches. Their applications in real-time prediction, inverse design, and performance enhancement have been highlighted. The recommended article has been thoroughly reviewed and cited appropriately in the revised manuscript see Section 2.5 (AI Techniques for PCF-SPR Sensor Optimization). 3. Discuss the significance of the broad RI detection range (1.31 to 1.42) in the context of biosensing applications, justify the RI range since any RI below 1.33 is considered superficial, I suggest add a sentence like claiming theoretical analysis. Response: We have explained the reason for choosing the RI range (1.31–1.42) in Section 2.1. The lower part of the range (below 1.33) is included to cover some theoretical cases and very light or low-density samples. 4. How does the use of SHAP (Shapley Additive exPlanations) enhance the interpretability of the ML model used for sensor design optimization? Response: We thank the reviewer for emphasizing the importance of model interpretability. To address this, we have added a clear explanation in Section 2.8 on how SHAP enhances the transparency of the ML model by identifying the impact of each input feature on the predicted optical properties. This helps to guide sensor design decisions and improves overall optimization. 5. Analyze how the achieved performance metrics such as wavelength sensitivity and figure of merit reflect the sensor's capability for high-precision detection. Response: We have now included a detailed explanation in the revised manuscript in Section 4 (Discussion) to highlight how the achieved wavelength sensitivity and figure of merit (FOM) substantiate the high-precision detection capability of the proposed PCF-SPR biosensor. The newly added text elaborates on their implications in practical biosensing applications. 6. Are these any sensing parameters which cannot be predicted using ML models, and why, and how do these predictions benefit the overall sensor design process? Response: We have addressed this point in Section 4 (Discussion) by discussing which sensing parameters are well-suited for ML prediction and which still require traditional simulation or experimental validation. This addition helps clarify the role of ML in the overall sensor design process and its practical limitations. 7. Critically evaluate the influence of design parameters like Au thickness and pitch on the sensor's performance, as revealed by the SHAP analysis. Response: We have included a focused discussion in Section 4 (Discussion), based on SHAP analysis that critically evaluates the influence of design parameters such as gold thickness and pitch. Their respective impacts on key performance metrics like wavelength sensitivity and confinement loss are now clearly highlighted in the revised manuscript. 8. Compare the advantages of the hybrid design approach combining conventional methods and ML/XAI with traditional sensor optimization strategies in terms of efficiency and computational cost. Some prominent sensor models having merger of IMD and EMD, merger of Quasi D shaped with EMD approach etc need to be included in the comparison section of the article. Add a short paragraph suggesting future application of the sensor for various applications. Following are suggested references including these features. https://doi.org/10.1007/s11468-024-02400-7 https://doi.org/10.1007/s11082-023-05016-z https://doi.org/10.1016/j.ijleo.2022.169892 https://doi.org/10.1016/j.measurement.2021.110513 Response: Thank you for the valuable feedback. In response, we have expanded the comparison in Section 3.3 (Comparison with Previous Works) of the manuscript to highlight the advantages of our hybrid design strategy combining FEM-based simulation, machine learning (ML), and explainable AI (XAI) techniques over conventional sensor optimization methods. Additionally, we have included comparisons with prominent sensor architectures integrating IMD-EMD and Quasi D-shaped designs, as referenced. A paragraph outlining future real-time applications has also been added in Section 4 (Discussion). 9. Justify the suitability of the proposed biosensor for medical diagnostics and chemical sensing, particularly in the context of cancer cell detection, refer the following reference. https://doi.org/10.3390/bios15050292 Response: We have added this in Section 4 (Discussion), to further elaborate on the medical and chemical sensing relevance of the proposed PCF-SPR biosensor, with a focus on its applicability in cancer diagnostics. The suggested reference has been reviewed and appropriately cited to support our explanation. #Reviewer 2 1. Explain how machine learning and artificial intelligence-based techniques can be used in the sensor design optimization and design. I suggest go through the following article and refer to various techniques used in the sensor modelling cite them too. https://doi.org/10.3390/photonics12060565 https://doi.org/10.3390/bios15050292 Response: Thank you for the valuable suggestion. We have revised the manuscript to include a detailed overview of how ML and AI techniques contribute to PCF-SPR sensor optimization. This has been added under Section 2.5 (AI Techniques for PCF-SPR Sensor Optimization), along with relevant insights and citations from the suggested references. 2. The SHAP (SHapley Additive exPlanations) technique do not enhance the sensor detection capability, it provides more results to conclude, these models are used to analyze the sensor for design optimization purposes only. Response: We agree with the reviewer’s observation. The manuscript has been updated in Section 2.8 (Explainable AI (XAI)) to clarify that SHAP does not directly improve sensing performance but helps interpret ML outputs, identify key design parameters, and support informed sensor optimization decisions. 3. In Figure 3 and section 2.2 can you see the in the text you have used D1, D2, D3 but in the diagram d1, d2, and where is d3, thus correct the notation. These create confusion. Response: Thank you for pointing out the inconsistency. The notations in Figure 3 and Section 2.2 have been corrected for consistency. All diameter labels now uniformly use the same format (D1, D2, D3), and the missing label (D3) has been added to the figure to avoid confusion. 4. Provide reference to Eq 1, 2, 4, 7, 9 etc, without proper reference it seems like you have developed the equation. Response: References for Equations 1, 2, 4, 7, 9, and others have been added in the revised manuscript to clearly indicate their original sources and avoid any confusion regarding authorship. 5. In Fig 12, 13, 14 can you increase the font size of the x- and y- labels of the figure. Response: Thank you for the suggestion. The font size of the x- and y-axis labels in Figures 12, 13, and 14 has been increased to improve readability. 6. Fig 16 don’t look correct, format it well, format all image well increase the font size of the x-label and y-label for all figures. Response: Thank you for pointing this out. Figure 16 has been reformatted for better clarity, and the font sizes of the x- and y-axis labels have been increased. Additionally, all other figures in the manuscript have been reviewed and formatted accordingly to ensure visual consistency and improved readability. 7. Mention the applications of the proposed biosensor in real time from medical to environment application. Response: Thank you for your valuable suggestion. Real-time applications in medical diagnostics and environmental monitoring have been added in Section 4 (Discussion) to emphasize the sensor’s practical relevance. Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0330944.r002
8 Aug 2025 Decision Letter - Yuan-Fong Chou Chau, Editor Design optimization of high-sensitivity PCF-SPR biosensor using machine learning and explainable AI PONE-D-25-28444R1 Dear Dr. Khatun, 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. For questions related to billing, please contact billing support . 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, Yuan-Fong Chou Chau Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: https://doi.org/10.1371/journal.pone.0330944.r003
Formally Accepted
Acceptance Letter - Yuan-Fong Chou Chau, Editor PONE-D-25-28444R1 PLOS ONE Dear Dr. Khatun, 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 You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days 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. You will receive an invoice from PLOS for your publication fee after your manuscript has reached the completed accept phase. If you receive an email requesting payment before acceptance or for any other service, this may be a phishing scheme. Learn how to identify phishing emails and protect your accounts at https://explore.plos.org/phishing. 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. Yuan-Fong Chou Chau Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0330944.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 .