{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:30:48Z","timestamp":1786595448472,"version":"build-2736575974"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Breast cancer-related lymphedema (BCRL) is a common and disabling complication after breast cancer surgery, with substantial effects on limb function and quality of life. Liposuction is an established option for selected patients with chronic BCRL. However, postoperative response is heterogeneous. This study aimed to develop a machine learning model to predict liposuction efficacy in patients with unilateral BCRL.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed 623 unilateral BCRL cases undergoing liposuction at Beijing Shijitan Hospital, randomly splitting them 7:3 into training (n=437) and validation (n=186) cohorts. Least absolute shrinkage and selection operator (LASSO) regression with cross-validation guided feature selection. Seven algorithms\u2014logistic regression (LR), support vector machines (SVM), decision trees (DT), artificial neural networks (ANN), LightGBM, XGBoost, and random forests (RF)\u2014were trained and benchmarked. Performance via AUC, calibration, DCA, and Brier score identified SVM as optimal. SHAP interpretation facilitated deployment of a web-based calculator.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The overall rate of favorable outcomes following liposuction was 64.7%. Cross-validated Lasso analysis, factoring in clinical validity and predictive importance, yielded four key predictors: history of erysipelas, preoperative affected-to-unaffected limb volume difference (Preoperative_difference), extracellular water ratio of the affected limb (r-ECW%), and body fat percentage. Among the seven models evaluated, the SVM exhibited the most balanced overall performance, achieving an accuracy of 77.42%, precision of 75.00%, specificity of 90.00%, F1-score of 0.632, Brier score of 0.163, and an AUC of 0.818 (95% CI: 0.757\u20130.876). Although not possessing the highest AUC, the SVM demonstrated exceptional resistance to overfitting, evidenced by a minimal AUC decrement of merely 0.0298 from the training to the validation set. Both calibration and decision curve analyses corroborated its robust generalizability, underscoring its tangible clinical utility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>An SVM model predicting surgical outcomes in BCRL was created and integrated into a user-friendly online tool. This calculator guides surgical choices based on predictive outputs, offering a valuable reference for refining patient management and treatment plans.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1916127","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:24:37Z","timestamp":1786595077000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based model to predict liposuction outcomes in unilateral breast cancer-related lymphedema"],"prefix":"10.3389","volume":"16","author":[{"given":"Shuai","family":"Pang","sequence":"first","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhetan","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peilin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghao","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Lymphatic Surgery, Capital Medical University Affiliated Beijing Shijitan Hospital; Clinical Center for Lymphatic Disorders, Capital Medical University (CMU)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1007\/s00520-018-4388-6","article-title":"Risk factors and prediction model for persistent breast-cancer-related lymphedema: a 5-year cohort study","volume":"27","author":"Penn","year":"2019","journal-title":"Support Care Cancer"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/s1470-2045(13)70076-7","article-title":"Incidence of unilateral arm lymphoedema after breast cancer: a systematic review and meta-analysis","volume":"14","author":"DiSipio","year":"2013","journal-title":"Lancet Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1245\/aso.2004.04.017","article-title":"Lymphedema secondary to postmastectomy radiation: incidence and risk factors","volume":"11","author":"Hinrichs","year":"2004","journal-title":"Ann Surg Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.maturitas.2015.01.012","article-title":"Modern surgical management of breast cancer therapy related upper limb and breast lymphoedema","volume":"80","author":"Leung","year":"2015","journal-title":"Maturitas"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10549-023-06947-7","article-title":"Advances in the prevention and treatment of breast cancer-related lymphedema","volume":"200","author":"Donahue","year":"2023","journal-title":"Breast Cancer Res Treat"},{"key":"B6","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1055\/s-0035-1549158","article-title":"Liposuction in lymphedema treatment","volume":"32","author":"Brorson","year":"2016","journal-title":"J Reconstr Microsurg"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2025.1651472","article-title":"Outcomes after liposuction-based treatment of lymphedema: a systematic review and meta-analysis","volume":"15","author":"Chen","year":"2025","journal-title":"Front Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejon.2021.102023","article-title":"Developing and validating a prediction model for lymphedema detection in breast cancer survivors","volume":"54","author":"Wei","year":"2021","journal-title":"Eur J Oncol Nurs"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2020.24373","article-title":"Development and validation of a risk model for breast cancer-related lymphedema","volume":"3","author":"Kwan","year":"2020","journal-title":"JAMA Netw Open"},{"key":"B10","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1186\/s12933-023-01854-z","article-title":"Machine learning-based models to predict one-year mortality among Chinese older patients with coronary artery disease combined with impaired glucose tolerance or diabetes mellitus","volume":"22","author":"Li","year":"2023","journal-title":"Cardiovasc Diabetol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view","volume":"18","author":"Luo","year":"2016","journal-title":"J Med Internet Res"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2354.1995.tb00047.x","article-title":"Volume measurement in lymphoedema treatment: examination of formulae","volume":"4","author":"Sitzia","year":"1995","journal-title":"Eur J Cancer Care (Engl)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s00520-018-4334-7","article-title":"Lymphedema symptoms and limb measurement changes in breast cancer survivors treated with neoadjuvant chemotherapy and axillary dissection: results of American College of Surgeons Oncology Group (ACOSOG) Z1071 (Alliance) substudy","volume":"27","author":"Armer","year":"2019","journal-title":"Support Care Cancer"},{"key":"B14","doi-asserted-by":"publisher","first-page":"735","DOI":"10.7326\/l15-5093","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD)","volume":"162","author":"Burke","year":"2015","journal-title":"Ann Intern Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1089\/lrb.2005.3.208","article-title":"A comparison of four diagnostic criteria for lymphedema in a post-breast cancer population","volume":"3","author":"Armer","year":"2005","journal-title":"Lymphat Res Biol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"5518","DOI":"10.1038\/s41598-025-90200-2","article-title":"The prognostic effect and mechanism of erysipelas in cancer-associated lymphedema","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep"},{"key":"B17","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s41416-020-0844-4","article-title":"Increases in arm volume predict lymphoedema and quality of life deficits after axillary surgery: a prospective cohort study","volume":"123","author":"Bundred","year":"2020","journal-title":"Br J Cancer"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2022.927312","article-title":"A review of feature selection methods for machine learning-based disease risk prediction","volume":"2","author":"Pudjihartono","year":"2022","journal-title":"Front Bioinform"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1093\/g3journal\/jkab032","article-title":"Heuristic hyperparameter optimization of deep learning models for genomic prediction","volume":"11","author":"Han","year":"2021","journal-title":"G3 (Bethesda)"},{"key":"B20","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20211033","article-title":"Understanding breast cancer as a global health concern","volume":"95","author":"Wilkinson","year":"2022","journal-title":"Br J Radiol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s10549-016-3947-0","article-title":"Descriptive epidemiology of breast cancer in China: incidence, mortality, survival and prevalence","volume":"159","author":"Li","year":"2016","journal-title":"Breast Cancer Res Treat"},{"key":"B23","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1007\/s00520-018-4388-6","article-title":"Risk factors and prediction model for persistent breast-cancer-related lymphedema: a 5-year cohort study","volume":"27","author":"Penn","year":"2019","journal-title":"Support Care Cancer"},{"key":"B24","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/s41572-019-0072-5","article-title":"Cancer-associated secondary lymphoedema","volume":"5","author":"Rockson","year":"2019","journal-title":"Nat Rev Dis Primers"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1089\/lrb.2020.0085","article-title":"Three decades of bioelectrical impedance spectroscopy in lymphedema assessment: an historical perspective","volume":"19","author":"Dylke","year":"2021","journal-title":"Lymphat Res Biol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1080\/17520363.2024.2415283","article-title":"Biomarkers in lymphedema assessment: integrating elastography and muti-frequency bioimpedance analysis","volume":"18","author":"Jeon","year":"2024","journal-title":"biomark Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14072151","article-title":"The role of bioelectrical impedance analysis in predicting secondary surgical interventions for lymphedema","volume":"14","author":"Otsuka","year":"2025","journal-title":"J Clin Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvsv.2023.07.010","article-title":"Changes in intracellular water volume after leg lymphedema onset and lymphaticovenular anastomosis as its surgical intervention","volume":"11","author":"Yasunaga","year":"2023","journal-title":"J Vasc Surg Venous Lymphat Disord"},{"key":"B29","doi-asserted-by":"publisher","first-page":"5518","DOI":"10.1038\/s41598-025-90200-2","article-title":"The prognostic effect and mechanism of erysipelas in cancer-associated lymphedema","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1097\/prs.0b013e3182450b47","article-title":"Regulation of adipogenesis by lymphatic fluid stasis: part I. Adipogenesis, fibrosis, and inflammation","volume":"129","author":"Zampell","year":"2012","journal-title":"Plast Reconstr Surg"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-323-65381-7.00044-7","article-title":"Lymphedema and obesity: is there a link","volume":"134","author":"Mehrara","year":"2014","journal-title":"Plast Reconstr Surg"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejon.2021.102023","article-title":"Developing and validating a prediction model for lymphedema detection in breast cancer survivors","volume":"54","author":"Wei","year":"2021","journal-title":"Eur J Oncol Nurs"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1916127\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T04:24:38Z","timestamp":1786595078000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1916127\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":32,"alternative-id":["10.3389\/fonc.2026.1916127"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1916127","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]},"article-number":"1916127"}}