{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:51:58Z","timestamp":1781643118810,"version":"3.54.5"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003789","name":"Helwan University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003789","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Res Methodol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Breast cancer related lymphedema (BCRL) is a frequent postoperative complication that can substantially impair physical function and quality of life. While objective detection tools such as bioimpedance spectroscopy and imaging are accurate, they are resource intensive and difficult to deploy at scale in routine clinical workflows. Early identification of patients at elevated risk using routinely available clinical data may enable timely surveillance and intervention.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a comparative machine learning framework for postoperative BCRL risk prediction using routinely collected clinical data from 1,328 breast cancer patients treated at a single tertiary care center. Twenty four demographic, clinical, pathological, and treatment related variables were analyzed in tabular form. Nine classifiers spanning linear, ensemble, boosting, and transformer based models were systematically evaluated across seven preprocessing pipelines addressing missing data, feature scaling, class imbalance, and decision threshold optimization. Model performance was assessed using minority class F1 (F1_m), accuracy, and the Brier score to jointly evaluate discrimination and probabilistic calibration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Predictive performance varied substantially across preprocessing strategies. When emphasis was placed on minority-class discrimination and probabilistic calibration, ensemble-based models including Random Forest, CatBoost, and LightGBM, as well as the transformer-based TabPFN, achieved the strongest results under the task-specific Custom preprocessing pipeline. Among these, TabPFN attained the highest overall performance, reaching F1_m values of approximately 0.86 and accuracy around 0.89 on the held-out test set. Random Forest, CatBoost, and LightGBM demonstrated robust and competitive performance, with F1_m values in the range of approximately 0.78 to 0.80 and accuracies around 0.83 to 0.86, together with stable Brier scores. In contrast, preprocessing pipelines that avoided targeted data exclusion yielded more conservative but consistent performance, highlighting trade-offs between discrimination, calibration, and data retention in real-world clinical settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates that preprocessing choices play a critical role in BCRL risk modeling using real world clinical data. While task specific preprocessing can substantially improve minority class performance, such gains should be interpreted cautiously in light of data exclusion and potential selection bias. The proposed framework provides a transparent and reproducible foundation for retrospective BCRL risk stratification and offers a methodological template for future multi center validation studies in postoperative breast cancer care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12874-026-02805-4","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:40:18Z","timestamp":1773384018000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From raw clinical data to robust prediction: an AI framework for early lymphedema detection"],"prefix":"10.1186","volume":"26","author":[{"given":"Ibrahim","family":"Sadek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shafiq Ul","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Gehad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esraa G.","family":"Eltasawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"AbdelKader","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rawan","family":"Abdelnasser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dina","family":"Nashaat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raef Mourad","family":"Zaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lamees N.","family":"Mahmoud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"2805_CR1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.1062472","author":"MP McEvoy","year":"2022","unstructured":"McEvoy MP, Gomberawalla A, Smith M, Boccardo FM, Holmes D, Djohan R, et al. The prevention and treatment of breast cancer-related lymphedema: a review. Front Oncol. 2022. https:\/\/doi.org\/10.3389\/fonc.2022.1062472.","journal-title":"Front Oncol"},{"issue":"1","key":"2805_CR2","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","volume":"21","author":"EW Steyerberg","year":"2010","unstructured":"Steyerberg EW, Vickers AJ, Cook NR, Gerds T, Gonen M, Obuchowski N, et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2010;21(1):128\u201338. https:\/\/doi.org\/10.1097\/EDE.0b013e3181c30fb2.","journal-title":"Epidemiology"},{"key":"2805_CR3","doi-asserted-by":"publisher","first-page":"2243","DOI":"10.21037\/gs-24-252","volume":"13","author":"Y Sun","year":"2024","unstructured":"Sun Y, Xia X, Liu X. Predictive modeling of breast cancer-related lymphedema using machine learning algorithms. Gland Surg. 2024;13:2243\u201352. https:\/\/doi.org\/10.21037\/gs-24-252.","journal-title":"Gland Surg"},{"key":"2805_CR4","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1334082","author":"J Du","year":"2024","unstructured":"Du J, Yang J, Yang Q, Zhang X, Yuan L, Fu B. Comparison of machine learning models to predict the risk of breast cancer-related lymphedema among breast cancer survivors: a cross-sectional study in China. Front Oncol. 2024. https:\/\/doi.org\/10.3389\/fonc.2024.1334082.","journal-title":"Front Oncol"},{"key":"2805_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejon.2021.102023","volume":"54","author":"X Wei","year":"2021","unstructured":"Wei X, Lu Q, Jin S, Li F, Zhao Q, Cui Y, et al. Developing and validating a prediction model for lymphedema detection in breast cancer survivors. Eur J Oncol Nurs. 2021;54:102023. https:\/\/doi.org\/10.1016\/j.ejon.2021.102023.","journal-title":"Eur J Oncol Nurs"},{"key":"2805_CR6","volume-title":"Lymphedema Management: The Comprehensive Guide for Practitioners","author":"JE Zuther","year":"2018","unstructured":"Zuther JE, Norton S. Lymphedema Management: The Comprehensive Guide for Practitioners. 4th ed. New York: Thieme; 2018.","edition":"4th ed"},{"key":"2805_CR7","unstructured":"British Lymphology Society. Lymphoedema Clinical Definitions and Assessment Guide (5S). UK; 2025."},{"key":"2805_CR8","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s10462-024-10884-2","volume":"57","author":"M Salmi","year":"2024","unstructured":"Salmi M, Atif D, Oliva D, Abraham A, Ventura S. Handling imbalanced medical datasets: review of a decade of research. Artif Intell Rev. 2024;57:273\u2013312. https:\/\/doi.org\/10.1007\/s10462-024-10884-2.","journal-title":"Artif Intell Rev"},{"key":"2805_CR9","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven DJ, B\u00fchlmann P. MissForest\u2013non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28:112\u20138. https:\/\/doi.org\/10.1093\/bioinformatics\/btr597.","journal-title":"Bioinformatics"},{"key":"2805_CR10","doi-asserted-by":"publisher","first-page":"281","DOI":"10.5555\/2188385.2188395","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res. 2012;13:281\u2013305. https:\/\/doi.org\/10.5555\/2188385.2188395.","journal-title":"J Mach Learn Res"},{"key":"2805_CR11","doi-asserted-by":"publisher","unstructured":"KeG, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM: A highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems.\u00a0Curran Associates Inc, Red Hook, NY, USA. 2017. pp. 3149\u201357. https:\/\/doi.org\/10.5555\/3294996.3295074.","DOI":"10.5555\/3294996.3295074"},{"key":"2805_CR12","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. XGBoost. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016. pp. 785\u2013794. https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"2805_CR13","unstructured":"Hollmann N, M\u00fcller S, Eggensperger K, Hutter F. TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second. 2022. arXiv preprint arXiv:2207.01848."}],"container-title":["BMC Medical Research Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12874-026-02805-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12874-026-02805-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12874-026-02805-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:56:40Z","timestamp":1781639800000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12874-026-02805-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":13,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2805"],"URL":"https:\/\/doi.org\/10.1186\/s12874-026-02805-4","relation":{},"ISSN":["1471-2288"],"issn-type":[{"value":"1471-2288","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"assertion":[{"value":"2 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"the graphical abstract has been updated.","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by the Baheya Research Center Ethics Committee (Baheya IRB Protocol Number: 202411270053). Approval was granted on 27 November 2024. All participants were recruited from the Baheya Centre for Early Detection and Treatment of Breast Cancer & Baheya Research Centre. Written informed consent was obtained from all participants prior to inclusion in the study. Participation was voluntary, and participants could withdraw at any time. All data were treated confidentially and analyzed in anonymized form. The study was performed in accordance with relevant guidelines and regulations, including the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Consent for publication was obtained from all participants in accordance with institutional and ethical guidelines.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"80"}}