{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T05:47:37Z","timestamp":1782193657428,"version":"3.54.5"},"update-to":[{"DOI":"10.12688\/f1000research.161073.1","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000}},{"DOI":"10.12688\/f1000research.161073.2","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000}},{"DOI":"10.12688\/f1000research.161073.3","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000}},{"DOI":"10.12688\/f1000research.161073.4","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000}},{"DOI":"10.12688\/f1000research.161073.5","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000}}],"reference-count":34,"publisher":"F1000 Research Ltd","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["f1000research.com"],"crossmark-restriction":false},"short-container-title":["F1000Res"],"abstract":"<ns5:p>Background Breast cancer remains a significant global health concern, with over 7.8 million cases reported in the last five years. Early detection and accurate classification are crucial for reducing mortality rates and improving outcomes. Machine learning (ML) has emerged as a transformative tool in medical imaging, enabling more efficient and accurate diagnostic processes. Objective This study aims to develop a machine learning-based predictive model for early detection and classification of breast cancer using the Wisconsin Breast Cancer Diagnostic dataset. Methods The dataset, comprising 569 samples and 33 features derived from fine needle aspirate biopsy images, was pre-processed through data cleaning, normalization using the Robust Scaler, and feature selection. Five supervised ML algorithms\u2014Logistic Regression, Support Vector Classification (SVC) with linear and radial basis function (RBF) kernels, Decision Tree, and Random Forest\u2014were implemented. Models were evaluated using performance metrics, including accuracy, precision, sensitivity, specificity, and F1 scores. Results The SVC-RBF model demonstrated the highest accuracy (98.68%) and balanced performance across other metrics, making it the most effective classifier for distinguishing between benign and malignant tumors. Key features such as texture mean and area (worst) significantly contributed to classification accuracy. Conclusions This study highlights the potential of ML algorithms, particularly SVC-RBF, to revolutionize breast cancer diagnostics through improved accuracy and efficiency. Future research should validate these findings with diverse datasets and explore their integration into clinical workflows to enhance decision-making and patient care.<\/ns5:p>","DOI":"10.12688\/f1000research.161073.6","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T05:04:07Z","timestamp":1782191047000},"page":"164","update-policy":"https:\/\/doi.org\/10.12688\/f1000research.crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development of a machine learning predictive model for early detection of breast cancer"],"prefix":"10.12688","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0906-3350","authenticated-orcid":false,"given":"Rinsy","family":"Rahman","sequence":"first","affiliation":[{"name":"Department of Health Information Management, Manipal College of Health Professions Manipal Karnataka 576104 Manipal Academy of Higher Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0560-9109","authenticated-orcid":false,"given":"Dola","family":"Saha","sequence":"additional","affiliation":[{"name":"Department of Health Information Management, Manipal College of Health Professions Manipal Karnataka 576104 Manipal Academy of Higher Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5963-3230","authenticated-orcid":false,"given":"Winniecia","family":"Dkhar","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging Technology, Manipal College of Health Professions Manipal Karnataka 576104 Manipal Academy of Higher Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-4847","authenticated-orcid":false,"given":"Sathyendranath","family":"Malli","sequence":"additional","affiliation":[{"name":"School of Information Science Manipal Karnataka 576104 Manipal Academy of Higher Education"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Barnes Abraham","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging Technology, Manipal College of Health Professions Manipal Karnataka 576104 Manipal Academy of Higher Education"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2560","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"ref1","article-title":"Cancer site ranking.","year":"n.d"},{"key":"ref2","article-title":"Report of National Cancer Registry Programme, 2020 A scientific way to understand about Cancer.","year":"n.d"},{"key":"ref3","article-title":"Global Breast Cancer Initiative Implementation Framework Assessing, strengthening and scaling up services for the early detection and management of breast cancer.","year":"n.d"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-019-0111-2","article-title":"Breast cancer.","volume":"5","author":"N Harbeck","year":"2019","journal-title":"Nat. Rev. Dis. Primers."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1100-1115","DOI":"10.1002\/cac2.12215","article-title":"Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine.","volume":"41","author":"Z Chen","year":"2021","journal-title":"Cancer Commun."},{"key":"ref6","article-title":"Breast Cancer Detection using Machine Learning Techniques.","author":"S Bhise","year":"n.d"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"4-9","DOI":"10.1038\/s41416-021-01633-1","article-title":"Artificial intelligence in oncology: current applications and future perspectives.","volume":"126","author":"C Luchini","year":"2022","journal-title":"Br. J. Cancer."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2341-2356","DOI":"10.1007\/s10238-022-00895-0","article-title":"Mammography diagnosis of breast cancer screening through machine learning: a systematic review and meta-analysis.","volume":"23","author":"J Liu","year":"2023","journal-title":"Clin. Exp. Med."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"320-324","DOI":"10.1016\/j.icte.2020.04.009","article-title":"Breast cancer detection by leveraging Machine Learning.","volume":"6","author":"A Vaka","year":"2020","journal-title":"ICT Express."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRITO51393.2021.9596230","author":"G Gupta","year":"2021","journal-title":"2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2021."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s44163-025-00649-3","article-title":"Enhancing breast cancer detection accuracy through machine learning, deep learning and transfer learning techniques for clinical practice.","volume":"6","author":"J Ganesan","year":"2026","journal-title":"Discov. Artif. Intell."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1789-1799","DOI":"10.1080\/03772063.2021.1963861","article-title":"Machine Learning Model for Breast Cancer Data Analysis Using Triplet Feature Selection Algorithm.","volume":"69","author":"P Dhivya","year":"2023","journal-title":"IETE J. Res."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"308-322","DOI":"10.1007\/s44230-025-00111-8","article-title":"Interpretable Machine Learning Approach for Breast Cancer Classification.","volume":"5","author":"A Garba","year":"2025","journal-title":"Hum. Centric Intell. Syst."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"17943-17968","DOI":"10.1007\/s13369-025-10255-1","article-title":"A Multi-stage Optimization Architecture for Effective Breast Cancer Diagnosis Based on Deep Neural Networks.","volume":"50","author":"T Beghriche","year":"2025","journal-title":"Arab. J. Sci. Eng."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"337-355","DOI":"10.1016\/B978-0-443-27801-3.00008-9","author":"S Handa","year":"2026","journal-title":"Genetic Testing in Breast Cancer."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e0326221","DOI":"10.1371\/journal.pone.0326221","article-title":"Advancing breast cancer prediction: Comparative analysis of ML models and deep learning-based multi-model ensembles on original and synthetic datasets.","volume":"20","author":"K Ahmed","year":"2025","journal-title":"PLoS One."},{"key":"ref12","article-title":"Python reference manual. Centrum Voor Wiskunde En Informatica Amsterdam.","author":"G Van Rossum","year":"1995"},{"key":"ref13","article-title":"pandas-dev\/pandas: Pandas.","year":"2020","journal-title":"Zenodo."},{"key":"ref14","article-title":"SKPHKB, Haldane WPPJ-MSWAG. OR, Array programming with {NumPy}.","author":"M Harris","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"90-95","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment.","volume":"9","author":"J Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"seaborn: statistical data visualization.","volume":"6","author":"M Waskom","year":"2021","journal-title":"J. Open Source Softw."},{"key":"ref17","first-page":"2825-2830","article-title":"Scikit-learn: Machine learning in Python.","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","article-title":"Early Detection of Breast Cancer Using Machine Learning Techniques.","author":"M Tahmooresi","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"275-284","DOI":"10.2147\/MDER.S206973","article-title":"An automated mammogram classification system using modified support vector machine.","volume":"12","author":"A Kayode","year":"2019","journal-title":"Med. Devices (Auckl)."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"12495","DOI":"10.1038\/s41598-019-48995-4","article-title":"Deep Learning to Improve Breast Cancer Detection on Screening Mammography.","volume":"9","author":"L Shen","year":"2019","journal-title":"Sci. Rep."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1-11","DOI":"10.3390\/jpm10040211","article-title":"Automated breast cancer detection in digital mammograms of various densities via deep learning.","volume":"10","author":"Y Suh","year":"2020","journal-title":"J. Pers. Med."},{"key":"ref23","article-title":"EasyChair Preprint Breast Cancer Detection Using Image Processing Techniques and Classification Algorithms Breast Cancer Detection Using Image Processing Techniques and Classification Algorithms.","author":"H Viswanath","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3389\/fonc.2024.1343627","article-title":"Breast cancer risk prediction using machine learning: a systematic review.","volume":"14","author":"S Hussain","year":"2024","journal-title":"Front. Oncol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"79-97","DOI":"10.4028\/www.scientific.net\/JBBBE.42.79","article-title":"Classification of mammograms using texture and CNN based extracted features.","volume":"42","author":"T Debelee","year":"2019","journal-title":"J. Biomim. Biomater. Biomed. Eng."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"8407-8422","DOI":"10.1007\/s00521-022-08113-4","article-title":"Machine intelligence-driven classification of cancer patients-derived extracellular vesicles using fluorescence correlation spectroscopy: results from a pilot study.","volume":"35","author":"A Uthamacumaran","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref39","first-page":"35-38","article-title":"Hybrid Radial Basis Function and Support Vector Machine Model for Precise Breast Cancer Diagnosis.","author":"R Sharma","year":"2024","journal-title":"2024 International Conference on Computational Intelligence and Computing Applications (ICCICA)."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"257-269","DOI":"10.35882\/jeeemi.v8i1.960","article-title":"Impact of Different Kernels on Breast Cancer Severity Prediction Using Support Vector Machine.","volume":"8","author":"K Mahmudah","year":"2026","journal-title":"J. Electron. Electromed. Eng. Med. Inform."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"6084","DOI":"10.1038\/s41598-026-37247-x","article-title":"The impact of K selection in K-fold cross-validation on bias and variance in supervised learning models.","volume":"16","author":"T Abedin","year":"2026","journal-title":"Sci. Rep."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"104404","DOI":"10.1016\/j.inffus.2026.104404","article-title":"Is K-fold cross validation the best model selection method for machine learning?","volume":"135","author":"J Gorriz","year":"2026","journal-title":"Inf. Fusion."}],"container-title":["F1000Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/f1000research.com\/articles\/14-164\/v6\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/f1000research.com\/articles\/14-164\/v6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/f1000research.com\/articles\/14-164\/v6\/iparadigms","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T05:14:10Z","timestamp":1782191650000},"score":1,"resource":{"primary":{"URL":"https:\/\/f1000research.com\/articles\/14-164\/v6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":34,"URL":"https:\/\/doi.org\/10.12688\/f1000research.161073.6","relation":{"has-version":[{"id-type":"doi","id":"10.12688\/f1000research.161073.5","asserted-by":"subject"},{"id-type":"doi","id":"10.12688\/f1000research.161073.4","asserted-by":"subject"},{"id-type":"doi","id":"10.12688\/f1000research.161073.3","asserted-by":"subject"},{"id-type":"doi","id":"10.12688\/f1000research.161073.2","asserted-by":"subject"},{"id-type":"doi","id":"10.12688\/f1000research.161073.1","asserted-by":"subject"}]},"ISSN":["2046-1402"],"issn-type":[{"value":"2046-1402","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"Indexed","URL":"https:\/\/f1000research.com\/articles\/14-164\/v6#article-reports","order":0,"name":"referee-status","label":"Referee status","group":{"name":"current-referee-status","label":"Current Referee Status"}},{"value":"10.5256\/f1000research.195914.r483192, Abicumaran Uthamacumaran, McGill University (Ringgold ID: 5620), Montr\u00e9al, Qu\u00e9bec, 15 Jun 2026, version 5, indexed","URL":"https:\/\/f1000research.com\/articles\/14-164\/v5#referee-response-483192","order":0,"name":"referee-response-483192","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"<b>Dola Saha<\/b>; \n<i>Posted: 16 Jun 2026<\/i>; \n<b>1) Reviewer:- <\/b>Figure 1 shows more benign B than malignant M. But the text manuscript says &quot;the manuscript states \u201c59% malignant and 41% benign&quot;. Why is that? And also we can just make the x axis Malignant and Benign for simplicity, for better readership. \n<b>Author:- <\/b>Thank you for this observation. We have carefully reviewed Figure 1 and the corresponding text. The discrepancy has been corrected in the revised manuscript, and the figure has been updated accordingly. These changes will be reflected in the updated version of the manuscript.  2) \n<b>Reviewer:-&nbsp;<\/b>Table 2 still doesn't report specificity correctly. The authors mentioned using the correct equation of TN\/ (TN + FP). If we apply this to Table 1, let's take logistic regression for instance, specificity = 83\/ (83+2) = 0.98. This is not what is reported in Table 2.&nbsp; There might also be some count number inconsistencies. The confusion matrix says 229, table 2 shows 228 as the sum. Check please. &nbsp;\n<b>Author:-&nbsp;<\/b>Thank you for identifying this issue. We have re-examined the specificity calculations and verified the confusion matrix values  3)&nbsp;\n<b>Reviewer:<\/b> Figure 4 is not a forest plot without CI (confidence intervals). I suggest renaming this to a performance-comparison dot plot or most robust and best would be to include cross-validation means with 95% CIs\/error bars. \n<b>Author:-&nbsp;&nbsp;<\/b>Thank you for identifying this issue.&nbsp;The discrepancy has been corrected in the revised manuscript.&nbsp;&nbsp;These changes will be reflected in the updated version of the manuscript.  4) &nbsp;\n<b>Reviewer:&nbsp;<\/b>For the hyperparameter section, please confirm that&nbsp;calling and feature selection were fitted only on training folds, and no test dataset bias occurred. Just one statement is sufficient to add to ensure there was no data leakage in training. \n<b>Author:-&nbsp;<\/b>Thank you for highlighting this important methodological consideration. We confirm that feature selection and hyperparameter optimization were performed exclusively within the training folds during cross-validation.  5)&nbsp;\n<b>Reviewer:<\/b> ROC curves should be generated from probability scores, not predicted class labels. Please ensure this. It looks great, but just check please as we couldn't find the ROC curve decision functions in the GitHub code. Similarly, the best_model is never used in the code, GridSearchCV only applies to the SVM-RBF.&nbsp;&nbsp;The manuscript\u2019s claim that all classifiers were similarly hyperparameter fine-tuned, remains unverified in the code. Please verify again. \n<b>Author:-&nbsp;<\/b>Thank you for this important observation. We have carefully reviewed the implementation and verified that the ROC curves were generated using predicted probability scores (or decision function outputs where applicable), rather than predicted class labels. We have clarified this in the revised manuscript.","URL":"https:\/\/f1000research.com\/articles\/14-164\/v6#referee-comment-16442","order":1,"name":"referee-comment-16442","label":"Referee Comment","group":{"name":"article-reports","label":"Article Reports"}},{"value":"10.5256\/f1000research.182136.r385232, Rolando Gonzales Martinez, University of Groningen, Groningen, 03 Jun 2025, version 3, 2 approved with reservations, 1 not approved","URL":"https:\/\/f1000research.com\/articles\/14-164\/v3#referee-response-385232","order":2,"name":"referee-response-385232","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"<b>Dola Saha<\/b>; \n<i>Posted: 04 Jun 2025<\/i>; \n<b>Response to Reviewer Comments:<\/b>  We are very grateful to the reviewer for the thoughtful feedback and for emphasizing the importance of carefully selected evaluation metrics in clinical machine learning applications. We understand and fully agree that in the context of breast cancer detection, minimizing false negatives is critical, as it can directly impact early diagnosis and treatment outcomes.  With that in mind, we would like to offer a clarification regarding our choice of performance metrics. While we acknowledge that False Negative Rate (FNR) and False Omission Rate (FOR) are highly relevant for this kind of diagnostic work, we believe that the metrics we have already included\u2014namely, \n<b>accuracy, precision, sensitivity (recall), specificity, and F1-score<\/b>\u2014are collectively sufficient to assess the model\u2019s practical utility and reliability. In particular, we highlight that \n<b>sensitivity<\/b> is already part of our evaluation, and since FNR is the direct complement of sensitivity (i.e., FNR = 1 \u2013 sensitivity), the paper does reflect how well the models are performing in identifying positive cases. We also believe that \n<b>F1-score<\/b>, which balances both precision and recall, offers an appropriate and well-accepted measure for dealing with class imbalance, which we were aware of and considered throughout the analysis.  As for the suggestion to include FOR, we appreciate its relevance. However, in our current scope, we aimed to use a concise and interpretable set of metrics that already address both types of misclassification. \n<b>Specificity<\/b>, combined with sensitivity and precision, provides readers with a clear picture of how false positives and false negatives are handled by each model.  Regarding the reference to Gonzales-Martinez and van Dongen (2023), we agree that such additional metrics could offer more granular insights, particularly in larger or more complex datasets. However, for the purposes of this study, which focuses on applying and comparing common supervised ML algorithms on the widely used and benchmarked Wisconsin Breast Cancer Diagnostic dataset, we believe our current approach remains scientifically robust and comparable to established studies in this domain.  While we sincerely appreciate the reviewer\u2019s recommendation, we respectfully submit that the performance metrics already included are widely accepted and meaningful for evaluating classification models in medical data settings. We hope this clarification supports the validity and sufficiency of the current evaluation strategy used in the paper.","URL":"https:\/\/f1000research.com\/articles\/14-164\/v6#referee-comment-14013","order":3,"name":"referee-comment-14013","label":"Referee Comment","group":{"name":"article-reports","label":"Article Reports"}},{"value":"10.5256\/f1000research.187487.r411911, Chandrakanta Mahanty, GITAM Deemed to Be University, Visakhapatnam, 19 Sep 2025, version 4, 1 approved, 2 not approved","URL":"https:\/\/f1000research.com\/articles\/14-164\/v4#referee-response-411911","order":4,"name":"referee-response-411911","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"10.5256\/f1000research.195914.r487176, Musatafa Abbas Abbood Albadr, Basrah University for Oil and Gas, Al Basrah, 02 Jun 2026, version 5, indexed","URL":"https:\/\/f1000research.com\/articles\/14-164\/v5#referee-response-487176","order":5,"name":"referee-response-487176","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"<b>Dola Saha<\/b>; \n<i>Posted: 06 Jun 2026<\/i>; Reviewer Comments-1   \n<b>1.<\/b> \n<b>Reviewer Comments: - Numerous<\/b>&nbsp;facts that have been mentioned in the manuscript need to be supported with recent references, check the whole manuscript.  \n<b>Author Response: -<\/b>&nbsp;Thank you for the suggestion, changes have been made accordingly in manuscript.  \n<b>2.<\/b> \n<b>Reviewer Comments:<\/b> I advise the authors to write the \u201c1. Introduction\u201d as follow: &nbsp;start with a brief introduction of the Breast cancer, then discuss the effectiveness of ML and DL techniques in the health care generally and specifically in Breast cancer detection and deeply deliberate about the issues that the authors want to tackle in the present work (support that with recent references). Subsequently, highlight the strength of the proposed techniques and justify why they are proposing them for the Breast cancer detection. Conclude with the main goals of the current work presented as bullet points. Immediately following the bullet points, outline the organization of the paper.&nbsp;  \n<b>Author Response: -&nbsp;<\/b> Thank you for the valuable suggestion. The Introduction has been revised to improve its structure, incorporate recent literature, highlight the rationale for the proposed classifiers, and clearly state the study objectives and manuscript organisation.  \n<b>3.<\/b> \n<b>Reviewer Comments:<\/b>&nbsp; The authors need to add a related work section and deeply elaborate each work of the related works. Besides, they are required to summarize the related works in a table alongside with their weaknesses. The table can be as follow: First column: Reference, Second column: Dataset, Third column: Features Extraction, Fourth column: Model, Fifth column: Results, and Sixth column: Weaknesses.  \n<b>Author Response:&nbsp; <\/b>Thank you for the suggestion. A comparative table summarizing related studies and their limitations has been added, along with additional discussion to position the present work within the existing literature.  \n<b>4.<\/b> \n<b>Reviewer Comments:<\/b> The authors need to evaluate their proposed work on more evaluation measurements such as G-Mean and MCC.  \n<b>Author Response:<\/b> Thank&nbsp;you for this valuable suggestion. We have included two additional performance measures, namely Geometric Mean (G-Mean) and Matthews Correlation Coefficient (MCC), to provide a more comprehensive assessment of classifier performance. These metrics are particularly useful in evaluating classification models where balanced performance across classes is important.  \n<b>5.<\/b> \n<b>Reviewer Comments:&nbsp;<\/b> The authors need to add the equations for the evaluation measurements alongside with their references.  \n<b>Author Response:<\/b>&nbsp; Thank you for the suggestion. The mathematical equations for accuracy, precision, sensitivity, specificity, and F1-score have been added to the Performance Evaluation section along with appropriate references.  \n<b>6.<\/b> &nbsp;\n<b>Reviewer Comments:<\/b>&nbsp; In \u201c3. Results\u201d section, the authors need to provide the description of the environment that they have conducted their experiments on.  \n<b>Author Response:&nbsp;<\/b> Thank you for the suggestion. Details of the experimental environment, including software tools, hardware specifications, and computing platform, have been added to the manuscript to improve the reproducibility of the study.  \n<b>7.<\/b> \n<b>Reviewer Comments:&nbsp;<\/b> The authors are required to statistically evaluate their proposed work based on Mean, RMSE, and STD of the evaluation measurements in order to make sure that the achieved results were not by accident or chance.  \n<b>Author Response: <\/b>Thank you for the suggestion. Mean Accuracy, Standard Deviation (STD), and RMSE obtained through five-fold cross-validation have been added to the Results section to further validate the robustness and reliability of the proposed classifiers  \n<b>8.<\/b> \n<b>Reviewer Comments:<\/b> The authors must add the explanation of the statistical evaluation measurements alongside with their equations. For conducting\/reporting\/plotting\/discussing the statistical outcomes, the authors can have a look at the following paper in order to get an idea on how to conduct\/report\/plotting\/discuss the statistical results. \u201cAlbadr, M. A. A., Ayob, M., Tiun, S., AL-Dhief, F. T., Arram, A., &amp; Khalaf, S. (2023). Breast cancer diagnosis using the fast-learning network algorithm. Frontiers in Oncology, 13, 1150840\u201d.  \n<b>Author Response: <\/b>&nbsp;Thank you for the suggestion. Explanations and equations for the evaluation metrics, including accuracy, precision, sensitivity, specificity, F1-score, and RMSE, have been added. The statistical outcomes from five-fold cross-validation have also been reported and discussed.  \n<b>9.<\/b> \n<b>Reviewer Comments:&nbsp;<\/b>The authors are required to compare the performance of the proposed work against some recent studies that have used the same dataset in terms of accuracy.  \n<b>Author Response: <\/b>&nbsp;Thank you for the suggestion. A direct comparison with studies that utilized the Wisconsin Breast Cancer Dataset has been added to the Discussion section. The classification accuracy achieved by the proposed model is compared with previously reported results to highlight its relative performance.  \n<b>10.<\/b> \n<b>Reviewer Comments:&nbsp;<\/b>The authors must write the conclusion in more effective way alongside with the limitations of the current work and real future works.  \n<b>Author Response:&nbsp;<\/b>Thank you for the valuable suggestion. The Conclusion section has been revised to provide a clearer summary of the main findings of the study. In addition, the key limitations of the current work and realistic future research directions have been explicitly discussed.","URL":"https:\/\/f1000research.com\/articles\/14-164\/v6#referee-comment-16370","order":6,"name":"referee-comment-16370","label":"Referee Comment","group":{"name":"article-reports","label":"Article Reports"}},{"value":"10.5256\/f1000research.195914.r484567, Manna Debnath, Department of Medical Imaging Technology, Bapubhai Desaibhai Patel Institute of Paramedical Sciences, Charotar University of Science and Technology, Changa, Gujarat, 03 Jun 2026, version 5, indexed","URL":"https:\/\/f1000research.com\/articles\/14-164\/v5#referee-response-484567","order":7,"name":"referee-response-484567","label":"Referee Report","group":{"name":"article-reports","label":"Article Reports"}},{"value":"<b>Dola Saha<\/b>; \n<i>Posted: 06 Jun 2026<\/i>; \n<b>1.<\/b> \n<b>Reviewer Comments:-<\/b> In the Abstract under the Methods section, the authors mentioned that the dataset comprised 569 samples with 32 features, whereas in the Methods section (Page 4, Section 2.2: Data source and inclusion criteria), it is stated that the dataset consisted of 569 records and 33 features. Please verify the dataset and maintain consistency in reporting.  \n<b>Author Response: -&nbsp;<\/b>We thank the reviewer for identifying this inconsistency. The dataset information was verified and corrected. The manuscript now consistently reports the dataset characteristics in both the Abstract and Methods sections\n<b>.<\/b>  \n<b>2.<\/b> \n<b>Reviewer Comments: -&nbsp;<\/b>In the introduction, add one or two points about the limitations of the previous study, which will show the gap that the present study addresses.  \n<b>Author Response: - We<\/b>&nbsp;thank the reviewer for this valuable suggestion. Accordingly, we have revised the Introduction to include the limitations of previous machine learning studies.  \n<b>3.<\/b> \n<b>Reviewer Comments: -&nbsp;<\/b>In Section 2.2 (Data source and inclusion criteria), the authors utilized the Wisconsin Breast Cancer Diagnostic dataset available on Kaggle; however, the dataset does not contain patient age information. Please verify the statement.  \n<b>Author Response: -&nbsp;<\/b>We thank the reviewer for identifying this issue. Upon verification, we confirm that the Wisconsin Breast Cancer Diagnostic dataset does not contain patient age information. The statement has been corrected in the revised manuscript, and any reference to age as a dataset variable has been removed to ensure accuracy and consistency.  \n<b>4.<\/b> \n<b>Reviewer Comments: -&nbsp;<\/b>On Page 5, the authors reported that the dataset consisted of 59% malignant (M) cases and 41% benign (B) cases. However, Figure 1 does not appear to reflect this distribution accurately. Specifically, the bar representing B (41%) appears visually higher than M (59%), which contradicts the textual description. Please verify the dataset distribution and revise the figure.  \n<b>Author Response: -&nbsp;<\/b>We thank the reviewer for identifying this error. Upon verification of the dataset, we found that the percentages for malignant and benign cases had been incorrectly reported. The manuscript has been revised to reflect the correct distribution of the target variable, and the text has been aligned.  \n<b>5.<\/b> \n<b>Reviewer Comments: -&nbsp;<\/b>Add strengths and limitations of the study at the end of the discussion section.  \n<b>Author Response: -&nbsp;<\/b>We thank the reviewer for this valuable suggestion. Accordingly, a dedicated paragraph outlining the strengths and limitations of the study has been added at the end of the Discussion section to provide a balanced interpretation of the findings and highlight areas for future research.","URL":"https:\/\/f1000research.com\/articles\/14-164\/v6#referee-comment-16371","order":8,"name":"referee-comment-16371","label":"Referee Comment","group":{"name":"article-reports","label":"Article Reports"}},{"value":"The author(s) declared that no grants were involved in supporting this work","order":9,"name":"grant-information","label":"Grant Information"},{"value":"This is an open access article distributed under the terms of the Creative Commons Attribution Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.","order":0,"name":"copyright-info","label":"Copyright"}]}}