Prediction of Bladder Cancer Treatment Side Effects Using an Ontology-Based Reasoning for Enhanced Patient Health Safety

Round 1

Reviewer 1 Report

The authors should revise the paper:

• It would be better to remove the first line of the abstract or rewrite the front matter.
• I would like to see the conceptual ontology (concepts and reasoning rules) separately. The tool-generated diagrams (Figures 7, 8, and 9) are not enough to get into the concepts inside. A reference paper can be followed to present the ontology models and reasoning rules (tabular and other forms):

• OntCAAC: An Ontology-Based Approach to Context-Aware Access Control for Software Services. Comput. J. 58(11): 3000-3034 (2015)
• It would be better to add a few future research works, including the idea behind extending the proposed ontology in relevant directions.
• The authors should carefully check minor writing issues: knowledge-base, instead knowledgebase; OWL ontologies, instead owl ontologies; Please proof-edit the whole paper. 

Author Response

First, we wish to thank you for all your considerations and your valuable comments. Please find our responses in the following points (Please see the attachement).

Point 1: It would be better to remove the first line of the abstract or rewrite the front matter.

Response 1: Thank you for your comment. We have removed the first line of the abstract.

 

Point 2: I would like to see the conceptual ontology (concepts and reasoning rules) separately. The tool-generated diagrams (Figures 7, 8, and 9) are not enough to get into the concepts inside. A reference paper can be followed to present the ontology models and reasoning rules (tabular and other forms): OntCAAC: An Ontology-Based Approach to Context-Aware Access Control for Software Services. Comput. J. 58(11): 3000-3034 (2015).

Response 2: Thank you for your comment. We added a table (Table 6) in which we presented some examples of operator-defined reasoning rules from our rule-base given the large number of the rules within our system-model. Furthermore, we added a descriptive simplified conceptual model of our ontology with details on Pathology concept, as shown in (Figure 10) in the paper, as inspired by the work of Kayes et al.: “OntCAAC: An Ontology-Based Approach to Context-Aware Access Control for Software Services. Comput. J. 58(11): 3000-3034 (2015)”. We tried to manage the paper in a way to make all necessary updates and add complementary information.

Please refer to pages 17-18: Lines 670à677.

 

Point 3: It would be better to add a few future research works, including the idea behind extending the proposed ontology in relevant directions.

Response 3: Thank you for your comment. We have added some future research works in the conclusion section, including the concept of extending the suggested ontology in relevant directions.

Please refer to page 25: Lines 958à981.

“Extending our biomedical ontology will be a challenging task that can never be deemed to be complete because of the continuously increasing understanding of cancer behaviour and treatment advances. Extension can profit in particular from the automation of certain procedures and therefore allow specialists to concentrate on tougher concerns. We are working on a strategy to reinforce the automation of update and semantic capturing within ontology extension where the need is found for specific properties or concepts. We are planning to apply supervised learning over features of our current ontology. We will identify the concerns of prediction for our ontology evolution, and we will build a general framework for ontology extension and treatment side effects prediction. The idea is to help focus either manual or semi-automated extension methods on areas that need to be expanded into any other ontology. Moreover, help in reducing the risk of bias or confusion between diseases or treatments generating the same complications while compared to other type of cancer. This will help in increasing the availability of the data and enhance interoperability between health information systems. Hence, it reduces time and highlights resources investment. This extensibility aims to improve the interoperability among our domain’s growing number of ontologies and solve term redundancy among ontologies to avoid issues of achieving data. We will ensure the term reuse and the semantic alignment within our ontology and work on a community extensibility by application to more clinical trials and use cases in a broader community. To reinforce our algorithm and make extra certain that the approach is extremely reliable, we will compare the results to treatment standards and care labels, and we will carry out an automated text mining of the scientific literature.  The risk faced by future participants in the course of the first inhuman clinical trials might then be reduced and the risk for patients minimized if a treatment or a drug is approved by the FDA and enters clinical application.”

Point 4: The authors should carefully check minor writing issues: knowledge-base, instead knowledgebase; OWL ontologies, instead owl ontologies; Please proof-edit the whole paper.

Response 4: Thank you very much for your comment. We have revised the whole paper and rectified all the detected writing issues. All revisions to the manuscript were marked up using the “Track changes”function in MS, so that any changes can be easily viewed.

 

Author Response File: Author Response.pdf

Reviewer 2 Report

This is an interesting and robust method to provide decision-making support on bladder cancer treatment with ontological modeling.  The method is well organized and presented with a stepwise description of data acquisition and knowledge base construction. However, this method could be improved as follows.1)the section of related work ignored effort on current AI application on optimizing RT treatment planning, ontology-based decision making support systems in oncology, and existing approaches on prediction of side effects during cancer treatment; 2)how to map the severity grade of side effects to CTCAE if the paper did does not use CTCAE as grading standard? 3)instances of the patient class in the proposed ontology refers to an individual patient or a cohort population? 4) the case-based reasoning seems only rely on SWRL rules based on an absolute assumption, which means the world defined by theses rules is absolute binary world. But the actual world of these side effects rules is fuzzy and probabilistic. 5)the proposed method ignored the recommendation and limits from clinical practice guidelines on Bladder cancer treatment.

Author Response

First, we wish to thank you for all your considerations and your valuable comments. Please find our responses in the following points (Please see the attachment).

 

Point 1: This is an interesting and robust method to provide decision-making support on bladder cancer treatment with ontological modeling.  The method is well organized and presented with a stepwise description of data acquisition and knowledge base construction. However, this method could be improved as follows:

The section of related work ignored effort on current AI application on optimizing RT treatment planning, ontology-based decision making support systems in oncology, and existing approaches on prediction of side effects during cancer treatment;

Response 1: Thank you for your comment. Details and more works highlighting our approach and topic were added to the “Related Works” section. We mentioned studies about the current AI application on optimizing RT treatment planning, ontology-based decision-making support systems in oncology and existing approaches on prediction of side effects during cancer treatment. To each element we added corresponding references.

Please refer to page 04: Lines 151à164 for effort on current AI application on optimizing RT treatment planning:

“As mentioned by Wang et al., current artificial intelligence (AI) was employed for automating and improving several medical aspects such as RT [25].  Many algorithms in RT planning were created to support planners through automated planning and radiation dose optimisation. This featured automated rule-making and reasoning, prior knowledge modeling and optimisation of many criteria in clinical practice. New treatment planning solutions based on AI used knowledge-based and deep learning. In terms of efficiency and uniformity, this optimized treatment planning. AI models with data-driven approaches such as machine learning and deep learning are improving the clinical RT workflow. However, a lack of knowledge and of the AI models processing can prevent wide and comprehensive use in clinical practice. In a review carried out by Liesbeth et al., it was found that the implementation of AI models in the RT workflow and their quality assurance (QA) were supported by specific guidelines [26]. This measured treatment reliability through comprehensive patient safety monitoring. Commissioning, implementing, and case-specific QA are emphasized for the most used applications in RT.

 

25. Wang, C.; Zhu, X.; Hong, J.C.; Zheng, D. Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future. Technol Cancer Res Treat 2019, 18:1533033819873922.
26. Liesbeth, V.; Michaël, C.; Anna, M. D.; Charlotte, L. B.; Wouter, C.; Dirk, V. Overview of artificial intelligence-based applications in radiotherapy: Recommendations for implementation and quality assurance. Radiotherapy and Oncology 2020.”

 

Please refer to pages 04-05: Lines 189à216 for ontology-based decision making support systems in oncology:

“Many works shown below have examined the application of DSS for ontology cooperation in oncology. Shen et al., developed a DSS for cancers treatment and prognosis based on an existing Disease Ontology (DO) to improve the reasoning task of the DSS using a Case-Based Reasoning (CBR) [32]. This system estimated the stage of the cancer. The system searches results in CBR database as reference for future reasoning instead of using its own outputs. Moreover, this DSS still struggling with assisting doctors use drugs rationally according to the patient’s specific situation. Zhang et al., proposed an ontology-based DSS to solve some issues in multi-level integrative data analysis studies for oncology research, through a theory-based guidance for multi-level variables and data source selection; and a standardized documentation of the data selection and an ontology-based integration process [33]. Hence the approach enabled sharing reports among scientists. But the system still not automated and needs standardized framework for operational use. Redjdal et al., reported that the guideline-based DSS (GL-DSS) of the DESIREE project and OncoDoc are clinical DSS applied to breast cancer [34]. The team reused the OncoDoc multidisciplinary tumor board (MTB) RCTs. The approach included two different knowledge representation models and two formalisms. Therefore, a transformation sequence was proposed, involving synthetic patients, the DESIREE ontology impovment, and the abstraction of RCTs outcomes. Complex cases within the approach, that were not handled by guidelines, needed effective analyses. In a review carried out by Pavithra et al., clinical reasoning ontology (CRO)–based clinical DSS (CDSSs) in oncology were evaluated to identify and classify knowledge, reasoning concepts and properties within these ontologies [35]. The team found that ontology-based methods make inferences according to the relationships implicating EHRs too. Moreover, 16% used algorithms, 79% CDSSs used rule-based computation for inferencing, 5% used fuzzy logic, 58% used an ontology-based method and 8% used mechine learning and natural language processing. Other computational methods included probability, proximity-based, anchor-based, and ranking of weighted option. But more research is needed for high quality ontology-based CDSSs.

 

32. Shen, Y.; Colloc, J.; Jacquet-Andrieu, A.; Guo, Z.; Liu, Y. Constructing ontology-based cancer treatment decision support system with case-based reasoning. In International Conference on Smart Computing and Communication; Springer, Cham. 2017, 278-288.
33. Zhang, H.; Guo, Y.; Prosperi, M. An ontology-based documentation of data discovery and integration process in cancer outcomes research. BMC Med Inform Decis Mak 2020, 20, 292.
34. Redjdal, A.; Bouaud, J.; Guézennec, G.; Gligorov, J.; Seroussi, B. Reusing Decisions Made with One Decision Support System to Assess a Second Decision Support System: Introducing the Notion of Complex Cases. Studies in Health Technology and Informatics 2021, 281, 649-653.
35. Pavithra, I.; Tiago, K.; Colicchio, J. C. Using clinical reasoning ontologies to make smarter clinical decision support systems: a systematic review and data synthesis. Journal of the American Medical Informatics Association 2020, 27, 159–174.”

 

Please refer to page 03: Lines 134à149 for existing approaches on prediction of side effects during cancer treatment:

“Only few approaches were carried out on the prediction of SEs during cancer treatment. Isaksson et al., developed a machine learning-based model for toxicity outcomes’ prediction in Radiotherapy (RT) which was considered as a valid model [22]. But there are still loose ends on the clinical applicability of RT-induced toxicity models. However, an effective prediction strategy for SEs is necessary. Hirahara et al., carried out a study to predict postoperative complications and survival after laparoscopic gastrectomy using Risk Index in elderly gastric cancer patients and the Clavien-Dindo (CD) classification for SEs evaluation [23]. For statistical analysis they used the non-parametric Mann–Whitney U test, the Chi-squared test, the Kaplan–Meier method, the log-rank test and the Cox proportional hazards regression models within the retrospective cohort study. These methods and the risk index proved their reliability within this approach, but knowledge models still need to be implemented for a semantic prediction end. Jing et al., used a strategy that combines pharmacovigilance data and omics data, and assessed relationships between multi-omics factors and Immune-related adverse events (AEs) reporting odds ratio across different cancer types [24]. They identified a bivariate regression model that predicted complications through LCP1 and ADPGK biomarkers.

 

22. Isaksson, L. J.; Pepa, M.; Zaffaroni, M.; Marvaso, G.; Alterio, D.; Volpe Jereczek-Fossa, B. A. Machine learning-based models for prediction of toxicity outcomes in radiotherapy. Frontiers in oncology 2020, 10, 790.
23. Hirahara, N. ; Tajima, Y. ; Fujii, Y.Prediction of postoperative complications and survival after laparoscopic gastrectomy using preoperative Geriatric Nutritional Risk Index in elderly gastric cancer patients. Surg Endosc 2021, 35, 1202–1209.
24. Jing, Y.; Liu, J. ; Ye, Y. Multi-omics prediction of immune-related adverse events during checkpoint immunotherapy. Nat Commun 2020, 11, 4946.”

 

Point 2: how to map the severity grade of side effects to CTCAE if the paper did does not use CTCAE as grading standard?

Response 2: Thank you for your question. As a clinical routine approach, our research is based on the standard system to report side effects: the Common Terminology Criteria for Adverse Events and side effects (CTCAE) for grading the severity of possible complications and hazards. In our examples (Tables 3-5, lines 495-448-573), we mentioned the outputs with reference to CTCAE as a main standard to evaluate our outcomes. We also designed a CTCAE-based TreatmentSEStandard class to describe a standardized framework of guidelines and references (Page 11: lines 446-449). On the other hand, to better specify adverse events or cumulative side effects with time within clinical trials, they can be mapped according to their severity and seriousness. We used the CTCAE severity grade scale: mild = 1, moderate = 2, severe = 3, life-threatening = 4, and death = 5; to grade possible complications. However, statistically, these grades are logically related to (1 – probability of survival with quality of life). Elements that should be incorporated into hypothetical weights for grades 1 to 5 are: The impact on quality of life, recovery versus recovery with side effects, MedDRA classifications and CTCAE standard descriptions or indications compared to patient's symptoms.

Point 3: Instances of the patient class in the proposed ontology refers to an individual patient or a cohort population?

Response 3: Thank you for the question. Instances of the Patient class in our ontology refer to a cohort population of patients. Each instance of this class presents a patient that we extracted from the included clinical trials (Page 17: Figure 9). Moreover, every instance (individual) describes a specific bladder cancer patient case in both demographic and biophysical terms with the help of datatype properties and data-object properties. The Patient class is an extensible and feedable class through instances that could be added referring every new bladder cancer patient case extracted from new clinical trials to act as evidence for future reasoning.

Point 4: The case-based reasoning seems only rely on SWRL rules based on an absolute assumption, which means the world defined by these rules is absolute binary world. But the actual world of these side effects rules is fuzzy and probabilistic.

Response 4: Thank you for your comment. In our research, the case-based reasoning was applied within a knowledge-based system thanks to our ontology integrity and interoperability features, and this supported prediction reasoning to be more flexible and fluent. Rather than relying completely on general knowledge of bladder cancer treatment side effects or making associations along generalized relationships between problem descriptors and conclusions, we employed the specific knowledge of previously experienced, concrete situations that we identified as medical evidence. This offered incremental, sustained learning in that each time a problem is solved a new experience is retained and can be applied for future problems as shown in our results. We mainly used SWRL rules format (OWL-DL, OWL-Lite and RuleML) within the rule engine phase to model the real world of side effects rules in response to the fuzziness and probabilistic occurrence based on OWL 2 standard language and the semantic W3C features. Abstracting the real world of bladder cancer treatment side effects through ontology representation and OWL modelling helped to build specific rules with specific assumptions within our domain-ontology. Thanks to its intelligent inference mechanism, SWRL was used for the development and calculation of fuzzy ontology classes and properties. SQWRL was to inquire the results of the menu recommendation. SWRL rules were designed from valid relationships to detect complications from the given prediction indexes. Adding to that, we used SQWRL which provides SQL like querying functionalities. These languages query RDF schema and OWL model. Adding to basic query functionalities, SWRL and SQWRL provided a set of powerful operators supporting disjunction, counting and aggregation. The proposed rules provide explicit knowledge representation and semantic enrichment of side effects prediction outcomes, thus simplifying the understanding of the inferred knowledge. A SWRL rule is in the form of an antecedent and consequent, which can be interpreted in a way that whenever the conditions specified in the antecedent hold, then the conditions specified in the consequent must also hold. In this context, SWRL provides model-theoretical semantology and is closely related to OWL ontologies that allow the construction of complicated rules on individual reasoning in ontologies. Secondly, the usage of SWRL to construct rules is independent of rule implementation languages in the rule engine that have the benefits of flexible choice of regulating rule engine and the platform for inference. The protégé SWRL Query Tab gathered the obtained elementary SWRL results that were then compared to real reported side effects to statistically measure the relevance and reliability of the model.

 

Point 5: The proposed method ignored the recommendation and limits from clinical practice guidelines on Bladder cancer treatment.

Response 5: Thank you for your valuable comment. In the “Related Work” section, we added this content describing the recommendation and limits from clinical practice guidelines on Bladder cancer treatment and side effects. To each element we added corresponding references.

Please refer to page 05: Lines 217à236:

“Generally, BC therapy is based on international guidelines. A number of guidelines on BC were issued internationally, including the society of urologic oncology (SUO) [36], the national comprehensive cancer network (NCCN) [37], the Canadian urological association (CUA) [38], the national cancer institute (NCI) [39], the first international consultation on bladder tumors (FICBT) and consultation on bladder cancer (SIU-ICUD) [40], the PDQ bladder cancer [41], the American urological association (AUA) [42], the European society for medical oncology (ESMO) [43] and the European association of urology (EAU) [44]. This practice has the drawback of not necessarily, accurately or appropriately recommending the options and alternatives as mentioned in the abroad recommendations for local clinical practice or a specific cancer state. Recommendations based on international guidelines and other references are not always suitable for all cases, with some drugs and treatment techniques or technologies not licensed for use in some places.

A reasonably substantial number of BC RCTs have been included and been considered appropriate to improve these guidelines by our prediction results and evidence-based reasoning. This ontological guidance provides an overview of BC treatment in the individual clinical stages, followed by clinical questions that encounter issues in daily clinical practice. In a study conducted by Zhang et al., it was found that the quality of the current BC recommendations and guidelines are controversial. Moreover, these guidelines varied in different ways [45]. Despite many similarities, there were several inconsistencies in the recommendations.

 

36. Marilin, N.; Master, V. A.; Pettaway, C. A.; Spiess, P. E. Current practice patterns of society of urologic oncology members in performing inguinal lymph node staging/therapy for penile cancer: A survey study. In Urologic Oncology: Seminars and Original Investigations. Elsevier.
37. Dolan, D. P.; Polhemus, E.; Lee, D. N.; Gentilella, C.; Tsukada, H.; Bueno, R.; Swanson, S. J. Validation of National Comprehensive Cancer Network Guidelines (NCCN) at a single institution.
38. Bhindi, B.; Kool, R.; Kulkarni, G. S.; Siemens, D. R.; Aprikian, A. G.; Breau, R. H.; Kassouf, W. Canadian Urological Association guideline on the management of non-muscle invasive bladder cancer. Canadian Urological Association Journal 2021, 15.
39. Korde, L. A.; Best, A. F.; Gnjatic, S.; Denicoff, A. M.; Mishkin, G. E.; Bowman, M. NCCAPS Study Team. Initial reporting from the prospective National Cancer Institute (NCI) COVID-19 in Cancer Patients Study (NCCAPS).
40. Horiguchi, A. Acute Management of Urethral Stricture. A Clinical Guide to Urologic Emergencies 2021, 144-157.
41. PDQ Adult Treatment Editorial Board. Bladder Cancer Treatment (PDQ®): Health Professional Version. In: PDQ Cancer Information Summaries. Bethesda (MD): National Cancer Institute (US). 2021.
42. Woldu, S. L.; Ng, C. K.; Loo, R. K.; Slezak, J. M.; Jacobsen, S. J.; Tan, W. S.; Lotan, Y. Evaluation of the New American Urological Association Guidelines Risk Classification for Hematuria. The Journal of urology 2021, 205, 1387-1393.
43. Morgan, G.; Tagliamento, M.; Lambertini, M.; Devnani, B.; Westphalen, B.; Dienstmann, R.; Peters, S. Impact of COVID-19 on social media as perceived by the oncology community: results from a survey in collaboration with the European Society for Medical Oncology (ESMO) and the OncoAlert Network. ESMO open 2021, 6, 100104.
44. Rouprêt, M. ; Babjuk, M. ; Burger, M. ; Capoun, O. ; Cohen, D. ; Compérat, E. M. ; Shariat, S. F. European Association of Urology guidelines on upper urinary tract urothelial carcinoma. European urology 2021, 79, 62-79.
45. Zhang, J.; Wang, Y.; Weng, H. Management of non-muscle-invasive bladder cancer: quality of clinical practice guidelines and variations in recommendations. BMC Cancer 2019, 1054.”

 

Furthermore, in section “3.4. Building an ontology for BC Knowledge representation”, a TreatmentSEStandard class of our ontology was already described. This class concerns the Bladder cancer treatment standards and clinical guideline supporting our decisions and results as recommendation references to our reasoning. Moreover, the generated decisions and structured included clinical trials generate knowledge and new evidence to improve standards and recommendations. As follows, we updated the paragraph to make it more understandable and added some references about the used guidelines.

 

Please refer to page 05: Lines 446à449:

“The inferred results were supported by the TreatmentSEStandard class including texts and standards about treatment related SEs, extracted from the international standard CTCAE and the published guidelines of the international cancer research foundations with reference to BC treatment clinical practice guidelines [55,56,57,58,59,60].

 

55. Witjes, F.; Babjuk, M.; Bellmunt, J. EAU-ESMO consensus statements on the management of advanced and variant bladder cancer-an international collaborative multi-stakeholder effort: under the auspices of the EAU and ESMO Guidelines Committees. Eur Urol 2020, 77, 223-250
56. Horwich, A.; Babjuk, M.; Bellmunt, J. EAU-ESMO consensus statements on the management of advanced and variant bladder cancer-an international collaborative multi-stakeholder effort: under the auspices of the EAU and ESMO Guidelines Committees. Ann Oncol 2020, 77, 223-250
57. Chang, S.S.; Boorjian, S.A.; Chou, R. Diagnosis and treatment of non-muscle invasive bladder cancer: AUA/SUO guideline. J Urol 2020; 196, 1021.
58. Kulkarni, G. S.; Black, P. C.; Sridhar, S. S.; Kapoor, A.; Zlotta, A. R.; Shayegan, B.; Rendon, R. A.; Chung, P.; van der Kwast, T.; Alimohamed, N.; Fradet, Y.; Kassouf, W. Canadian Urological Association guideline: Muscle-invasive bladder cancer. Canadian Urological Association Journal 2019, 
59. Bhindi, B.; Kool, R.; Kulkarni, G. S.; Siemens, D. R.; Aprikian, A. G.; Breau, R. H.; Kassouf, W. Canadian Urological Association guideline on the management of non-muscle invasive bladder cancer. Canadian Urological Association Journal 2021, 15.
60. Monteiro, L.L.; Witjes, J.A.; Agarwal, P.K.; Anderson, C.B.; Bivalacqua, T.J.; Kassouf, W. ICUD-SIU International Consultation on Bladder Cancer 2017: management of non-muscle invasive bladder cancer. World J Urol 2019, 37, 51-60.”

 

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have addressed all comments. Response 2 has been referred as follows, without citing the paper. The paper should be included in the reference list along with in-text citations in the relevant places. 

Response 2: Thank you for your comment. We added a table (Table 6) in which we presented some examples of operator-defined reasoning rules from our rule-base given the large number of the rules within our system-model. Furthermore, we added a descriptive simplified conceptual model of our ontology with details on Pathology concept, as shown in (Figure 10) in the paper, as inspired by the work of Kayes et al.: “OntCAAC: An Ontology-Based Approach to Context-Aware Access Control for Software Services. Comput. J. 58(11): 3000-3034 (2015)”. We tried to manage the paper in a way to make all necessary updates and add complementary information.

Author Response

First, we wish to thank you for all your considerations and your valuable comments. Please find our response in the following point (Please see the attachment).

 

Point 1: The authors have addressed all comments. Response 2 has been referred as follows, without citing the paper. The paper should be included in the reference list along with in-text citations in the relevant places.

“Thank you for your comment. We added a table (Table 6) in which we presented some examples of operator-defined reasoning rules from our rule-base given the large number of the rules within our system-model. Furthermore, we added a descriptive simplified conceptual model of our ontology with details on Pathology concept, as shown in (Figure 10) in the paper, as inspired by the work of Kayes et al.: “OntCAAC: An Ontology-Based Approach to Context-Aware Access Control for Software Services. Comput. J. 58(11): 3000-3034 (2015)”. We tried to manage the paper in a way to make all necessary updates and add complementary information.”

 

Response 1: Thank you for your valuable comment. We included the referred paper in the reference list along with in-test citation in the relevant place.

Please refer to page 17: Lines 670à673:

“As inspired by the work of Kayes et al. [71], we present, in (Table 6), examples of operator-defined reasoning rules from our rule-base followed by a descriptive simplified conceptual model of our ontology with details on Pathology concept, as shown in (Figure 10).

71. Kayes, A. S. M.; Han, J.; Colman, A. OntCAAC: an ontology-based approach to context-aware access control for software services. The Computer Journal 2015, 58, 3000-3034.”

 

Author Response File: Author Response.pdf

Reviewer 2 Report

Thanks for author’s response. The author has clearly responded my concerns and added related work.

Author Response

First, we wish to thank you for all your considerations and your valuable comments (Please see the attachment).

 

Point 1: Thanks for author’s response. The author has clearly responded my concerns and added related work.

 

Response 1: Thank you for your thoughtful comments. We sincerely appreciate the time you spent reviewing our paper.

 

Author Response File: Author Response.pdf

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.